That Was The Week (Keith Teare)

For those interested, I have embedded an Excel file with a list of 2023 issues of That Was The Week, ordered by the largest number opened and read on Substack. Each issue is linked.

The newsletter is also published on X, Facebook, Linkedin, and the Video on Youtube.

The total Substack views in 2023 will be about 250,000, with 150,000 users. I have over 60,000 LinkedIn followers and contacts, 6500 on X, and 4800 Friends on Facebook, with a further 35,000 or so followers. These people all have access to That Was The Week for each issue.

Keith Teare has decades of experience as an entrepreneur, with multiple success stories, starting in political activism, and then tech. He is the Founder of SignalRank which is a data-only company using AI to transform the venture game, and writes a weekly newsletter ‘That Was the Week’ which is also a show.There is no newsletter until January 19th so here is a New Year gift. Maria Matloub of ggutt interviewed me. I promised to help her distribute it.

That Was The Week is an editorialized and curated weekly look at developments in tech, startups, and venture investing with a video and podcast for paid subscribers. All free subscribers get a 6-month complementary paid subscription. This episode asks what 2024 has in store.

A reminder for new readers. That Was The Week collects the best writing on critical issues in tech, startups, and venture capital. I selected the articles because they are of interest. The selections often include things I entirely disagree with. But they express common opinions, or they provoke me to think. The articles are only snippets. Click on the headline to go to the original. I express my point of view in the editorial and the weekly video below.

Thanks To This Week’s Contributors: @TEDchris, @LilyWhitsitt, @RocketToLulu, @saeedtaji, @geneteare, @EricNewcomer, @jeffbeckervc, @jasonlk, @elonmusk, @benshapiro, @StevenLevy, @apple, @bheater, @bmw, @Growcoot, @illscience, @venturetwins, @omooretweets, @conniechan

Contents

* Editorial: Civility and Civilization

* Essays of the Week

* US Seed Investment Actually Held Up Pretty Well For The Past 2 Years. Here’s What That Means For 2024

* Lower Valuations, Higher Bar: What It’s Like To Raise A Seed Round In 2024 

* Unicorns & Inevitabilities

* Sequoia, Founders Fund, USV, Elad Gil & Benchmark Top Venture Manager Survey

* Why 2024 May Be Tougher on Venture Capital Than 2023

* Video of the Week

* The Mac at 40

* AI of the Week

* BMW will deploy Figure’s humanoid robot at South Carolina plant

* Google’s New AI Video Generator Looks Incredible

* OpenAI’s Sam Altman seeks funds for AI chip factories as demands surge

* The Future of Prosumer: The Rise of “AI Native” Workflows

* Andreessen Horowitz’s Connie Chan to Leave as Consumer Focus Shifts to AI

* OpenAI Is a (Relative) Steal

* News Of the Week

* Ted fellows resign from organisation after Bill Ackman named as speaker

* Tesla’s Slowdown Disqualifies It From ‘Magnificent Seven’ Group

* TikTok’s Testing 30 Minute Uploads as It Looks To Expand Its Content Options

* Instagram to scan under-18s’ messages to protect against ‘inappropriate images’

* Tiger Global Investor Relations Staff Depart After Fundraising Challenges

* Worldcoin hints at new Orb for a friendlier iris-scanning experience

* Startup of the Week

* Loyalty Startup Bilt Rewards Hits $3.1B Valuation After $200M Round

* X of the Week

* Elon Musk visits Auschwitz with Ben Shapiro

Editorial

There is a lot to digest in this week’s newsletter. Gené Teare’s two essays on Seed investing head up the Essays of the Week, along with Jeff Becker talking about unicorns and inevitabilities, Eric Newcomer on who are the top investors and Jason Lemkin on the reasons 2024 might be harder for Venture Capital than 2023.

But my attention was distracted from venture capital by a Guardian article announcing (triumphantly, I might add) that several TED fellows had resigned from the organization due to an invite to Bill Ackman to speak at this year’s TED event in Vancouver.

“Lucianne Walkowicz and Saeed Taji Farouky accuse Ted of taking anti-Palestinian stand over controversial billionaire’s inclusion”

It seems Ackman is not alone. They also object to Bari Weiss being invited. The leavers are also not alone; up to 30 others have signed a “solidarity” letter.

The accusations echo much of the discussion around the medieval assassination of Jews on 7 October and Israel’s efforts to defeat Hamas in the aftermath. Because these speakers are against anti-Semitism and so supportive of Israel’s war against Hamas, they are accused of the ridiculous claim of supporting “Genocide” against Palestinians.

“We refuse for our work and identities to be exploited to promote the Ted brand while the organisation and its speakers generate income and advance their careers through dehumanising Palestinians and justifying their genocide,” the pair said.

It probably will not surprise readers of this newsletter that I applaud TED curators Chris Anderson and Lily James Olds for not backing down on the invitations. Whatever one believes about the current conflict in Israel, it is clear that banning opponents of anti-Semitism because of their stance is not a solution to anything.

I believe the cause of fighting anti-Semitism should be close to the heart of any progressive person.

It is not anti-Palestinian to support Jews against being slaughtered in the street, to oppose anti-Semitism, or to condemn Hamas as anti-Jewish murderers.

Supporting Jews against slaughter by Hamas is not incompatible with supporting Palestinians.

The Guardian reported that Ackman responded to the resignations with a statement:

“I stand unapologetically with Israel and against antisemitism and terrorism, while strongly supporting the Palestinian people. Attempts to cancel speech and eliminate the free and respectful exchange of ideas among people with differing views are driving much of the divisiveness that plagues our nation. Truth, wisdom and ultimately peace are the result of the free exchange of ideas and debate, precisely what Ted is all about. It is sad that this is not more widely understood,”

Unsurprisingly, one of the resigners, Farouky, told the Guardian he did not regard the issue as freedom of speech. It clearly IS about freedom of speech. Speech only needs protecting when opinions are wide apart and strongly held.

For example, here are my views on the actual issues:

These are trying times. Over 25,000 deaths in Gaza are hard to comprehend. And I certainly cannot. But I can understand that Jews have to defend themselves. And I can understand that progressive thinkers MUST stand up to anti-Semitism, whatever form it takes.

In case there is doubt about my support for Muslim victims of racism, my book Under Seige is about the attacks on Muslims in the UK between 1961 and 1981.

It starts with recognizing that racism targets differences and that Jews and Muslims are both targets. Indeed, the very ghettoes that Pakistani and Bengali immigrants were being attacked in had earlier, in the 1930s, been inhabited by Jewish settlers fleeing pogroms.

I am not Jewish, and I am not Muslim. But I will always be on both of their sides when they are attacked for their ethnic and racial origin.

In Israel, Jews were killed for being Jews. Palestinians are being killed because Hamas is hiding in their cities and buildings. I do not consider Israel’s response to be racist against Palestinians. I consider it reasonable in the context of 7 October. I consider that Hamas has done this to Palestinians and probably wanted that outcome. I am sad that Hamas has done this for the Palestinian victims. But I do not doubt that Hamas is to blame.

My views may anger you. But do you want me banned or silenced?

My title this week is Civility and Civilization. The TED events bring both to the fore. Like those I write here, opinions are there to be disagreed with, debated, and interrogated. Civilized behavior requires dialogue and civility within the dialogue. I certainly understand opinions I disagree with, and far from banning them or walking away so that I do not have to hear them, I want to hear them. We all should.

This is a different editorial than usual. I hope the humanity of refusing to forget 7 October and the determination to preserve the view that fighting anti-Semitism is a non-negotiable minimum requirement of civilization are grasped. By the same token, Islamaphobia must be fought. But in Israel, there is no Islamophobia at work. Jews are simply reacting to an atrocity. They are right to blame Hamas.

Essays of the Week

US Seed Investment Actually Held Up Pretty Well For The Past 2 Years. Here’s What That Means For 2024

Gené Teare, January 24, 2024, @geneteare

Editor’s note: This is the first in a two-part series on the state of seed startup investing at the start of 2024. Check back tomorrow for Part 2.

Despite a broad pullback in global startup investment over the past two years, investors say the U.S. seed funding environment was the most vibrant compared to other funding stages during the downturn.

In fact, U.S. seed funding in 2022 grew by close to 10% in terms of dollars invested, in contrast to a downturn at all other funding stages. In 2023, U.S. seed funding fell 31% — a significant proportion — but still less than other funding stages year over year, an analysis of Crunchbase data shows. (It’s also worth noting that those other stages had already experienced year-over-year declines in 2022.)

In the current startup funding market, “we’re seeing a lot more great talent excited about starting things,” said Renata Quintini, co-founder of Renegade Partners, a Bay Area-based investment firm that focuses on Series A companies and is therefore close to the seed ecosystem.

Other investors share that enthusiasm. “Valuations are coming down, more talent is available in the market,” said Michael Cardamone of New York-based seed investor Forum Ventures. “A lot of these companies at seed and Series A are going to scale into what will likely be the next bull market.”

Seed trends over the decade

Seed as an asset class, not surprisingly, has grown in the U.S. over the past decade. In 2014 less than $5 billion was invested at seed. At the market peak in 2022, seed investment was more than $16 billion, although it fell to $11.5 billion in 2023.

Despite the downturn, seed funding in 2023 was still $2 billion to $3 billion higher in the U.S. than in the pre-pandemic years of 2019 and 2020.

Higher bar, pricier rounds, better valued

But in a tougher market, seed investors are being more selective about which companies they fund.

“We’re being far more disciplined and patient knowing how hard it is for these companies to get to Series A and beyond,” said Jenny Lefcourt, a general partner at Bay Area-based seed investor Freestyle Capital. “Our bar for conviction is higher than it had been in the heyday where everything was getting funded.”

In the slower funding environment, the firm has been investing later at the seed stage, “gravitating toward ‘seed plus’ or ‘A minus’ — pick your favorite term for it — because I feel like I get to see more risk mitigated. I get to see more data,” she said.

Freestyle seeks to have ownership of around 12% to 15% in the companies it backs. “The reason is because of our model,” Lefcourt said. “We are low-volume, high-conviction investors.”

And because the firm invests in companies that are pre-Series A, “our reality has been that our valuations have actually been higher in this market, which is not what we would have predicted.

“But the data we’ve seen is, we’re not alone in that,” she said.

…More

Lower Valuations, Higher Bar: What It’s Like To Raise A Seed Round In 2024 

Gené Teare, January 25, 2024, @geneteare

Editor’s note: This is the second in a two-part series on the state of seed startup investing at the start of 2024. Read Part 1, which looked at seed funding trends over the past decade and the median time period between seed and Series A funding, here.

Seed funding to startups has grown into its own asset class over the past decade, with round sizes trending larger, and a bigger pool of investors backing these nascent startups. But in the aftermath of 2021’s venture funding heyday and subsequent pullback, investors say that while seed funding has held up better than other startup investment stages, these very young startups will see lower valuations and must now clear a much higher bar to get backing.

More companies raised seed funding above $1 million in 2021. Those companies — which raised during a record-smashing year for venture funding — are saddled with valuations that could be too high for this current market — even at seed. Many of those startups have been forced to cut costs to extend their runways, and face a tougher sales environment.

“You could then be sacrificing growth, which is one of the main levers that Series A investors are looking for,” said Michael Cardamone of New York-based seed investor Forum Ventures.

2021 after effects

In 2021 it was “grow, grow, grow, grow,” said Jenny Lefcourt, a general partner at Bay Area-based seed investor Freestyle Capital. “It’s embarrassing to look back on, but that was the game being played.”

Investors got sloppy during the boom times, she said. “I think a lot of VCs were thrilled to back you, and then say, ‘we’ll figure it out.’ ”

“The reality is that almost anything that was done then — call it 2021 — was the wrong price,” she said.

This led to down rounds, even at seed, though those are generally not viewed negatively like they were in the past, she said.

In fact, “when our companies get their down rounds done, it’s a sign of it’s a good business. It just had the wrong price on it,” she said.

While the bar is higher to raise funding these days, “I think it’s so much better for a company who gets to start in this environment,” Lefcourt said.

Down rounds can actually be a sign of conviction, she said. “None of us would do all the heavy lifting to not only give the company more capital, but recap it, which takes a lot. It’s a heavy lift — none of us would do that if we weren’t super jazzed about the company. The lazier approach, the easier approach, is to just put it on the note, keep it flat, and be done,” she said.

Renata Quintini, co-founder of Renegade Partners, a Bay Area-based investment firm that focuses on Series A companies, is hearing of “more ‘pay-to-play’ these days and it’s starting to get ugly.” This happens when new investors wipe out the prior investors, and anyone seeking equity needs to pony up into the new funding round.

Median and averages climb

Nonetheless, “seed round valuations haven’t dropped a ton from even the peak,” according to Forum Ventures’ Cardamone. But, “the bar to raise a seed [round] is a lot higher.”

“Most first-time founders especially, and the vast majority of founders generally — they have to get significant traction to be able to raise that same round they used to be able to raise. And a lot fewer of those rounds are happening,” he said.

“A priced seed round of $3 million at $15 million [pre-money] is still happening, but you might have to be at $500,000 ARR, to raise that round now. Whereas in 2021, it was the norm to raise that round pre-revenue,” he said.

Series A fundings have gotten harder as “companies are going out and raising three seed rounds,” said Cardamone.

Based on an analysis of Crunchbase data, median and average seed round sizes in the U.S. have climbed through the past decade.

In 2023, median and average raises are not far from the peak of 2022, Crunchbase data shows, and were well above pre-pandemic levels. (However, this will shift downward somewhat as the long tail of seed fundings are retroactively added to the Crunchbase database.)

Seed rounds got larger

“If I have conviction, we may need them to have more money, cause we know it’s going to take them longer to reach the milestones that are now higher,” said Lefcourt.

Per an analysis of Crunchbase data, larger seed rounds — those $1 million and above — have increased through the decade.

The amount of funding to seed-stage companies below $1 million hasn’t budged much, and is a fraction of what it was earlier in the decade.

Seed below $1 million in 2014 represented around 25% of all seed funding.

That has come down as a proportion every year since then.

And as of 2021 that proportion has dipped below 10% for the first time, ranging from 5% to 7% of all seed dollars invested in the U.S. since then.

Earlier in the past decade, the number of seed deals in rounds below $1 million outpaced those rounds at $1 million and above significantly.

But 2021 was once again a pivotal year. That’s when $1 million and above seed rounds outpaced smaller seed for the first time.

In 2023, they are neck and neck in count. (That might shift as the long tail of seed rounds are added to the Crunchbase database long after they close.)

What this all shows is that seed has become an increasingly significant and elongated phase in a company’s early life cycle, where companies are raising multiple million-dollar seed rounds. And as of late, more companies than ever before are wading in the seed pool.

What does this mean for the seed funding market in 2024?

…More

Unicorns & Inevitabilities

Up and to the right, or not so much?

JEFF BECKER, JAN 22, 2024

TLDR: Go read Aileen Lee’s update to the Unicorn Club… and a few inevitabilities.

Did anyone catch Aileen Lee & Allegra Simon’s Welcome Back to the Unicorn Club, 10 Years Later?

If not, go read it. That’s your MMM.

If you did read it, you can’t help but wonder if the tech sector isn’t going to resemble the public markets over time. Ups and downs, but consistently up and to the right over a long enough period.

After all, we are creating leverage in ways we’ve never seen before.

And for unicorns, that meant 14X growth over a 10-year period.

Could you imagine another 14 or even 10X from here? That would be stratospheric, from ~500 to ~5,000 unicorns? What if the exit sizes did too? $5B, $10B, $50B?

Crazy to think, but hardly impossible. After all, we’ve already seen near-centicorns like Uber’s IPO at $75B in 2019.

The interesting part about that thought exercise though is not the crazy zero interest rate IPO’s, but the fact that entry valuations didn’t and don’t move nearly as fast as top end outcomes because of the time horizon to realizing them.

For example, Airbnb raised $20K from Y Combinator for 6%, then they took another $600K for 20% in their seed.

That was 2009. The idea of an IPO for $47B just 11 years later in 2020 probably wasn’t even a consideration. Paul Graham and the YC team would’ve had to believe Airbnb’s IPO could compete with AT&T, General Motors, and Visa.

Insane.

Fast forward, that $333,333 valuation at YC has moved to $1.78m (125K for 7%), and they’ll stack another 2.6% ownership on average from their $375K MFN with the average YC company raising seed at a $14.4m cap instead of Airbnb’s $3m.

That’s a ~5X increase in valuation at pre-seed & seed for a 47X increase in IPO size if you were modeling $1B outcomes into your VC fund model in 2009.

I’m not saying that will continue. There are counterforces of course.

* Margins are way too high. The fact that software margins have persisted at 80% or more is just craziness. Companies will start to use price more aggressively to compete for market share as cheap AI tools enter the market and try to unseat them. This compression will change the value of discounted cash flow models.

* Pricing models need to change. One way to reduce sticker price and maintain some semblance of healthy long-term margins is to pay a smaller implementation fee, but incur ongoing services & upgrade costs. This is a more traditional pricing model, and creative economics that leverage this kind of thinking run rampant in the titans of tech. It’s a game of deeper roots, higher switching costs, and long-term contracts. With API calls and data usage more prevalent, we’ll also see more pay-per-use models, the same way we buy copiers. We’ll also see more pay-for-performance models with attributable ROI, akin to Amazon’s ACoS model or Rakuten’s affiliate marketing model. Customers will prefer it too, placing a higher emphasis customer value. This will also drive margins to condense.

* AI, AI, AI. AI will cut OpEx costs dramatically. SDR teams, gone. Copywriters at agencies, you don’t need as many. Data scientists? Just run a query against your data lakes. The list goes on. Costs of running these companies is going to get shellacked. Good for margins for sure, but also a compelling opportunity for newcomers to undercut and unseat incumbents too.

* More hardware. With software margins condensing, hardware margins will start to feel more attractive too, the maintenance and upgrade fees will resemble what we see in SaaS, and the software that powers these machines will be incredible. Skynet for autonomous off-road vehicles, absolutely.

* Less dilution, earlier exits, and stratification. We already see it in the S&P 500 with the top end accounting for an outsized share of total value. With that kind of cash on balance sheets, bigger companies will just buy the smaller ones. Think about how Broadcom rolls up companies. If you’ve built the business more efficiently, you’ve also raised less, incurred less dilution, and that $100m exit when you still own 50% is looking pretty prett-ty good compared to the same outcome 5-10 grueling years later to own 5% of $1B.

* Massive founder salaries, less emphasis on growth. If you’ve built a company that’s profitable from day one, and you have complete control of your board, what’s your incentive to keep the pedal down on growth, or stay on the VC treadmill? World domination? Why not pay yourself 10X, stop fundraising, and continue to tighten the core business until someone acquires you? It’s better for the founding team and employees for sure, and it’s probably better for customers in most instances too.

These are just some of things I think we’ll see over the next five years until we approach ZIRPy-dirpy times again and massive growth becomes irresistible.

But there are also a whole slew of things I think are inevitabilities that will benefit from these dynamics because we will not only have new technologies, with more attractive pricing, but we will be tackling new opportunities that were created by the prior evolutions across adjacent industries.

For example…

* Cost of energy is going to zero with nuclear fusion

* Longevity is starting to work; check out Loyal for Dogs

* Batteries & cameras continue to improve; medical devices, for one, will be more personal & affordable

* Disintermediation of big ad networks with new global distribution channels; check out Benjamin

* Massive cost reductions driven by AI

* Software will be built by software

* An aging population is retiring (10,000 per day); wealth transfer & SMB’s with no exit paths

* Climate change

* …and so on and so on and so on

The list is long. Much longer than this. If you want the rest, just reply or comment so that I know, and I’ll go deeper next week.

Net of all of it, I think we’re going to see a tale of two cities. Stronger, more profitable businesses, with smaller, but better founder founder exits in the near term, and a continued growth both in number of total unicorns, and what that top-end outcomes look like in the longer-term.

And like I said, go read Aileen’s post.

Sequoia, Founders Fund, USV, Elad Gil & Benchmark Top Venture Manager Survey

I got my hands on a VC scorecard circulating among top founders & VCs

ERIC NEWCOMER

JAN 25, 2024

Before we get started, I want to be clear — this isn’t the end-all, be-all list of the top venture capital firms or the most promising startups.

But I got my hands on a survey of 91 people at 69 different venture capital firms conducted by a well-respected investor in venture capital firms.

The survey results are spreading hand-to-hand in Silicon Valley. The results of the survey rank the most desirable venture capital firms and companies, according to VCs themselves. When I was out in San Francisco last week for The Information’s 10th anniversary gala, sources kept bringing it up.

My sources tell me that the survey was conducted by Ed Hutchinson, managing partner at Golden Bell Partners. Hutchinson is ignoring my emails.

Which firms and companies would top VCs themselves put their money into? It’s a question everyone wants to know the answer to.

I’ve got my hands on their list of favorites:

Firms

* (1) Sequoia

* (2) Founders Fund

* (3) Union Square

* (4) Elad Gil

* (5) Benchmark

…Much More (but only for subscribers)

Why 2024 May Be Tougher on Venture Capital Than 2023

by Jason Lemkin | Blog Posts, Fundraising, Scale

So I thought the toughest times for venture would be behind us now.  In 2022, we were in free fall, with public market caps falling like a knife, and the IPO markets frozen.  And 2023 was the year of the Work Out in venture.  Bridge rounds slowed down, and VCs acknowledged a lot of portfolio companies just weren’t going to make it.  It got real in 2023, and that realness got normalized.  The drama mostly was behind us.  And public SaaS stocks in many cases did really, really well in 2023.  So shouldn’t 2024 at least be better for venture?

So I thought.

But the reality is I’m a bit more worried the venture drama in 2024 will be bigger than 2023.  Why?  Four core reasons:

#1:  Now We Have to Deal With the Reality of the Stumbling Unicorns.

The ones that are doing $100m+ ARR, still growing, but there just isn’t going to be any more money coming.  This is going to burn up a ton of energy in VC funds.  Even tougher, the reality is while many VC funds marked down their unicorns to lower valuations in 2023, they often didn’t mark them down enough.

#2.  The Chase for AI Unicorns and Decacorns is All-consuming.  It’s Still 2021 There.

The one place where paper money seems easy to come by is Hot AI Startups.   And that’s probably not you.  It’s just consuming all the oxygen in venture, trying to get into the next Imaging AI startup worth $1B in 10 months.  In AI, 2021 never went away.  In AI, it’s still 2021.

#3.  A Lot of Seasoned VCs are Discouraged. This Doesn’t Help Founders.

A lot of VCs who have been around for a while are quietly discouraged.  They just don’t see a great path to making a ton of money in venture these days.  We’re in Year 3 of a venture downturn, and that weighs of most of us.  At a practical level, for founders, it makes it harder to lean it.

#4.  More Valuation Markdowns Are Still to Come

Related to the first point, but more markdowns are like mutliple rounds of layoffs.  They’re just tough.  LPs lose confidence.  Coworkers lose confidence.  We should have gotten through a lot of this in 2023, but we didn’t.  Personally, I’ve got several investments for example that I marked down. 70%-80% or more — that my co-investors didn’t mark down at all.

#5.  VCs Have Run out of Reserves

VCs used what extra “reserve” capital they had for bridge rounds in 2022 and 2023.  Now it’s gone.  That’s adds to the stress as companies struggle.  You don’t have a play anymore.

The bottom line is there likely is at least another full year of working through the excesses of 2021.  That will weigh across venture.  No matter what some AI headlines suggest.

Video of the Week

The Mac at 40

Apple Shares the Secret of Why the 40-Year-Old Mac Still Rules

The pioneering PC revolutionized how people interact with computers. As the Mac enters its fifth decade, Apple says it will continue to evolve.

STEVEN LEVY, Jan 19, 2024 10:00 AM

ON JANUARY 24, Apple’s Macintosh computer turns 40. Normally that number is an inexorable milestone of middle age. Indeed, in the last reported sales year, Macintosh sales dipped below $30 billion, more than a 25 percent drop from the previous year’s $40 billion. But unlike an aging person, Macs now are slimmer, faster, and last much longer before having to recharge.

My own relationship with the computer dates back to its beginnings, when I got a prelaunch peek some weeks before its January 1984 launch. I even wrote a book about the Mac—Insanely Great—in which I described it as “the computer that changed everything.” Unlike every other nonfiction subtitle, the hyperbole was justified. The Mac introduced the way all computers would one day work, and the break from controlling a machine with typed commands ushered us into an era that extends to our mobile interactions. It also heralded a focus on design that transformed our devices.

That legacy has been long-lasting. For the first half of its existence, the Mac occupied only a slice of the market, even as it inspired so many rivals; now it’s a substantial chunk of PC sales. Even within the Apple juggernaut, $30 billion isn’t chicken feed! What’s more, when people think of PCs these days, many will envision a Macintosh. More often than not, the open laptops populating coffee shops and tech company workstations beam out glowing Apples from their covers. Apple claims that its Macbook Air is the world’s best-selling computer model. One 2019 survey reported that more than two-thirds of all college students prefer a Mac. And Apple has relentlessly improved the product, whether with the increasingly slim profile of the iMac or the 22-hour battery life of the Macbook Pro. Moreover, the Mac is still a thing. Chromebooks and Surface PCs come and go, but Apple’s creation remains the pinnacle of PC-dom. “It’s not a story of nostalgia, or history passing us by,” says Greg “Joz” Joswiak, Apple’s senior vice president of worldwide marketing, in a rare on-the-record interview with five Apple executives involved in its Macintosh operation. “The fact we did this for 40 years is unbelievable.”

…Much More

AI of the Week

BMW will deploy Figure’s humanoid robot at South Carolina plant

Brian Heater @bheater / 3:00 AM PST•January 18, 2024

Image Credits: Figure

Figure today announced a “commercial agreement” that will bring its first humanoid robot to a BMW manufacturing facility in South Carolina. The Spartanburg plant is BMW’s only in the United States. As of 2019, the 8 million-square-foot campus boasted the highest yield among the German manufacturer’s factories anywhere in the world.

BMW has not disclosed how many Figure 01 models it will deploy initially. Nor do we know precisely what jobs the robot will be tasked with when it starts work. Figure did, however, confirm with TechCrunch that it is beginning with an initial five tasks, which will be rolled out one at a time.

While folks in the space have been cavalierly tossing out the term “general purpose” to describe these sorts of systems, it’s important to temper expectations and point out that they will all arrive as single- or multi-purpose systems, growing their skillset over time. Figure CEO Brett Adcock likens the approach to an app store — something that Boston Dynamics currently offers with its Spot robot via SDK.

Likely initial applications include standard manufacturing tasks such as box moving, pick and place and pallet unloading and loading — basically the sort of repetitive tasks for which factory owners claim to have difficulty retaining human workers. Adcock says that Figure expects to ship its first commercial robot within a year, an ambitious timeline even for a company that prides itself on quick turnaround times.

The initial batch of applications will be largely determined by Figure’s early partners like BMW. The system will, for instance, likely be working with sheet metal to start. Adcock adds that the company has signed up additional clients, but declined to disclose their names. It seems likely Figure will instead opt to announce each individually to keep the news cycle spinning in the intervening 12 months.

Unlike some other humanoid designers (including Agility), Figure is focused on creating a dexterous, human like hand for manipulation. The thinking behind such an end effector is the same that’s driving many toward the humanoid form factor in the first place: Namely, we’ve designed our workspaces with us in mind. Adcock alludes to Figure 01 being tasked with an initial set of jobs that require high dexterity.

As for the importance of legs, the executive suggests that their importance for maneuvering during certain tasks is as — or more — important than things like walking up stairs and over uneven terrain, which tend to get most of the love during these conversations.

…More

Google’s New AI Video Generator Looks Incredible

JAN 25, 2024

MATT GROWCOOT

Google has announced Lumiere: an AI video generator that looks to be one of the most advanced text-to-video models yet.

The name Lumiere is seemingly a nod to the Lumiere brothers who are credited with putting on the first ever cinema showing in 1895. Just as motion picture was cutting-edge technology at the end of the 19th century, the Lumiere name is once more being associated with something new and original.

The demo of Lumiere that Google put out focuses firmly on animals. The model can generate a scene using just text; much the same way AI image generators work, the user can dream up any scenario they would like to see a short video clip of.

However, the user can also use an image as a prompt. Google provided multiple examples: including some that are real photos such as Joe Rosenthal’s iconic Raising the Flag photo; “Soldiers raising the united states flag on a windy day” saw one of the 20th-centuries most recognizable photos suddently come to life as the soliders struggle with the flag that’s being affected by gusts.

Also in Lumiere is a “Video Stylization” setting which allows users to upload a source video and then ask the generative AI model for various element changes. For example, a person running may be suddenly turned into a toy made of colorful bricks.

Another feature Google showed off is “Cinemagraphs”, where just a section of an image is animated while the rest stays still. “Video Inpainting” is included too which involves masking part of the image so that section can be changed to the user’s desire.

Space-Time Diffusion Model

Lumiere is powered by “Space-Time U-Net architecture that generates the entire temporal duration of the video at once, through a single pass in the model.”

This difficult-to-understand concept is apparently in contrast to existing video models which “synthesize distant keyframes followed by temporal super-resolution — an approach that inherently makes global temporal consistency difficult to achieve.”

…Much More

OpenAI’s Sam Altman seeks funds for AI chip factories as demands surge

OpenAI CEO Sam Altman has opened discussions with global investors over the possibility of funding a network of artificial intelligence (AI) chip factories to keep pace with soaring demand.

Altman is seeking around $8 billion to $10 billion worth of funds to set up several AI chip fabrication plants around the globe, an endeavor that will require synergy between leading chip manufacturers backed by investment giants.

Altman is reportedly in talks with Japanese-based financial giant SoftBank Group (NASDAQ: SFTBF) and Abu Dhabi’s G42 over funding plans, but details remain sparse. The discussions with G42 have been underway since 2023, with Altman describing a potential chip partnership as laying the foundation “for equitable advancements in generative AI across the globe.”

Aside from SoftBank and G42, insiders say that Altman is still pursuing collaborations with other industry players to set up a network of chip fabrication plants. Although exact entities were not namechecked, industry experts are noting Intel Corporation (NASDAQ: INTC), Samsung Electronics, and Taiwan Semiconductor Manufacturing Co. (NASDAQ: TSM) as potential partners.

Altman’s approach to raising funds hinges on concerns that the chip supply will not be able to meet global demands for AI offerings by 2030. The OpenAI’s CEO argues that the ideal solution will be a collaborative effort to set up chip manufacturing plants rather than build in silos.

OpenAI has had its fair share of chip scarcity, rolling back a number of its offerings over a steady chip supply. To meet the rising demand, the company is reportedly mulling several options, including the prospect of building its chips from scratch and joining ranks with Google (NASDAQ: GOOGL) and Amazon (NASDAQ: AMZN) to explore an in-house solution.

Given the costs associated with an in-house approach, OpenAI may pursue the acquisition of a chip manufacturer as a short-term solution or expand its collaboration with existing partners. However, a potential acquisition opens its own can of worms, including an inquiry by antitrust regulators.

Governments are also involved

In 2023, Altman urged the South Korean government to double their investments in AI chip manufacturing as a veritable strategy to play a leading role in the nascent ecosystem. Currently, South Korea ranks behind the U.S., China, and Japan in chip manufacturing, but a concerted government involvement could see the country climb up the charts.

The OpenAI boss disclosed during his visit to South Korea that his firm will back local entities building chips for AI and other emerging technologies, with Samsung rumored to be in top position.

“We are exploring how to increase our investment in Korean startups,” said Altman. “We are excited to meet as many as we can here today. I think this type of collaboration is essential to our work.”

..More

The Future of Prosumer: The Rise of “AI Native” Workflows

Anish Acharya, Justine Moore, and Olivia Moore

Posted January 25, 2024

Few people love the software they use to get things done. And it’s no surprise why. Whether it’s a slide deck builder, a video editor, or a photo enhancer, today’s work tools were conceived decades ago — and it shows! Even best-in-class products often feel either too inflexible and unsophisticated to do real work, or have steep, inaccessible learning curves (we’re looking at you, Adobe InDesign). 

Generative AI offers founders an opportunity to completely reinvent workflows — and will spawn a new cohort of companies that are not just AI-augmented, but fully AI-native. These companies will start from scratch with the technology we have now, and build new products around the generation, editing, and composition capabilities that are uniquely possible due to AI. 

On the most surface level, we believe AI will help users do their existing work more efficiently. AI-native platforms will “up level” user interactions with software, allowing them to delegate lower skill tasks to an AI assistant and spend their time on higher-level thinking. This applies not only to traditional office workers, but to small business owners, freelancers, creators, and artists — who arguably have even more complex demands on their time. 

But AI will also help users unlock completely new skill sets, on both a technical and an aesthetic level. We’ve already seen this with products like Midjourney and ChatGPT’s Code Interpreter. Everyone can now be a programmer, a producer, a designer, or a musician, shrinking the gap between creativity and craft. With access to professional-grade yet consumer-friendly products with AI-powered workflows, everyone can be a part of a new generation of “prosumers.”

In this piece, we aim to highlight the features of today’s — and tomorrow’s — most successful Gen AI-native workflows, as well as hypothesize about how we see these products evolving.

What Will GenAI Native Prosumer Products Look Like?

All products with Gen AI-native workflows will share one crucial trait: translating cutting-edge models into an accessible, effective UI.

Users of workflow tools typically don’t care what infrastructure is behind a product; they care about how it helps them! While the technological leaps we’ve made with Generative AI are amazing, successful products will importantly still start from a deep understanding of the user and their pain points. What can be abstracted away with AI? Where are the key “decision points” that need approval, if any? And where are the highest points of leverage? 

There are a few key features we believe products in this category will have: 

* Generation tools that kill the “blank page” problem. The earliest and most obvious consumer AI use cases have come from translating a natural language prompt into a media output — e.g., image, video, and text generators. The same will be true in prosumer. These tools might help transform true “blank pages” (e.g., a text prompt to slide deck), or take incremental assets (e.g., a sketch or an outline) and turn them into a more fleshed-out product.

Some companies will do this via a proprietary model, while others may mix or stitch together multiple models (open source, proprietary, or via API) behind the scenes. One example here is Vizcom’s rendering tool. Users can input a text prompt, sketch, or 3D model, and instantly get a photorealistic rendering to further iterate on.

Another example is Durable’s website builder product, which the company says has been used to generate more than 6 million sites so far. Users input their company name, segment, and location, and Durable will spit out a site for them to customize. As LLMs get more powerful, we expect to see products like Durable pull real information about your business from elsewhere on the internet and social media — the history, team, reviews, logos, etc. — and generate an even more sophisticated output from just one generation. 

* Multimodal (and multimedia!) combinations. Many creative projects require more than one type of content. For example, you may want to combine an image with text, music with video, or an animation with a voiceover. As of now, there isn’t one model that can generate all of these asset types. This creates an opportunity for workflow products which allow users to generate, refine, and stitch different content types in one place.

…More

Andreessen Horowitz’s Connie Chan to Leave as Consumer Focus Shifts to AI

By Kate Clark, Erin Woo and Cory Weinberg

Jan 23, 2024, 7:22am PST

For years, partners at Andreessen Horowitz proclaimed they would scour the startup world for the next big consumer marketplace like Airbnb or the next hit consumer app out of China, areas in which the firm had unique expertise. Now, it’s shifting toward an area more en vogue across venture capital: consumer apps powered by artificial intelligence.

Those changes are happening amid an overhaul of its consumer team. Connie Chan, a general partner at Andreessen Horowitz who formerly led a team of consumer investors and was known for spotting internet trends coming from China, said she is leaving the firm.  She may raise her own fund, a person familiar with the matter said. Anish Acharya, a general partner at the firm who invested in enterprise-focused and financial technology businesses, now leads the consumer team, said people familiar with the change.

Chan’s move also follows a distancing by U.S. VC firms from investments in China tech, once a hotbed for U.S.  investors. In recent months, Chan has privately said it’s becoming more difficult for her to work at Andreessen Horowitz because the partners have been increasingly disinterested in anything China related, another person said.

The Takeaway

• Fintech-focused GP Anish Acharya leading consumer deals• Consumer GP Connie Chan is leaving the firm• Consumer partner Anne Lee Skates left to start own fund

The changes are part of a broader personnel shakeup, including the decision by senior consumer investor and Airbnb board member Jeff Jordan to step back from making new investments last year. Of the four general partners that led the firm through a consumer deal blitz, none remain on the consumer team.

Meanwhile, Anne Lee Skates, a consumer partner who worked on the firm’s investment in live shopping app WhatNot, left in the fall to raise her own fund, according to two people familiar with the matter. Axios first reported that Chan was leaving the firm.

The Andreessen Horowitz changes are emblematic of a broader VC industry gravitation toward AI and away from once-hot sectors like consumer marketplaces and financial technology, as a spike in interest rates undercut the growth aspirations of startups trying to elbow out incumbent social platforms and banking institutions.

“We’ve gotten into this cycle now where, generally speaking, investors are less interested in consumer,” said Ben Lerer, managing partner at Lerer Hippeau. Known for its consumer investments in Warby Parker and Allbirds, the firm has invested 70% of its latest fund in enterprise companies, he said. “And AI feels like this very hopeful, very exciting, fresh thing.”

Founders of some consumer startups have noticed the shift at Andreessen Horowitz. One founder of a consumer startup in the firm’s portfolio said they had heard little from investment partners over the last year, a contrast to a steady drumbeat of emails the founder got in prior years from Andreessen staff who support portfolio companies with marketing and operations advice.

Andreessen Horowitz’s consumer investing team has been perhaps most well known for its focus on backing digital marketplaces, from peer-to-peer self-storage to real estate investment marketplaces, that could turn into the next Airbnb. Every year, it releases a ranking of top marketplace startups. “We are obsessed with marketplaces and have been since our inception,” Chan, who led investments in  social fashion startup Cider for the firm in 2021.

But some of those startups backed by the firm, such as self-storage startup Neighbor, have struggled to take off in recent years. And like other venture firms, Andreessen Horowitz has also stepped back from investing in Chinese startups, an area of focus for Chan. She had championed the idea that the next wave of breakout U.S. consumer startups will model themselves after China’s internet success stories, like all-in-one app WeChat.

With $53 billion in assets under management, Andreessen Horowitz is one of the largest of traditional Silicon Valley firms and closely watched among other VC firms as a trend setter. And its track record of sniffing out hitmakers primed its partners to find the next trendy consumer app.

The number of consumer deals Andreessen Horowitz has led dropped to 13 last year from 30 in 2021, a record for the firm, according to PitchBook data. It's possible the firm completed more consumer deals and that those investments haven’t been announced. Its investments in AI companies have jumped to 23 from nine over the same years, including leading a $415 million investment in Mistral, the French developer of an open-source large language model.

The firm has beefed up this team of investors primarily focused on enterprise, software infrastructure and AI startups. Led by Martin Casado, a close confidante to the firm’s founders Horowitz and Marc Andreessen, it is raising its first standalone fund and has brought on two new general partners, Anjney Midha and Zane Lackey, since 2022, as well as a number of junior partners.

As the infrastructure team gained power, the consumer team’s profile shrank. The firm in 2023 combined its consumer and fintech teams and created a new group, called apps, led by general partner Alex Rampell, who previously co-founded installment lender Affirm, The Information reported last year. Under Rampell’s leadership, the newly formed apps team will also soon launch a dedicated apps fund, according to people with direct knowledge of the matter. The consolidated team has been encouraged to pursue AI deals.

Within Rampell’s apps group, Acharya now leads the consumer sub-group. His portfolio of companies includes payroll company Deel and Silo, a provider of supply chain automation software. He’s also an investor in Titan, a consumer investment application.

Fueling the firm’s shift away from consumer apps are likely disappointing returns. The startups that captivated consumers during the pandemic shutdowns have failed to retain their attention. Growth at companies the consumer team bet on, like Clubhouse, which Andreessen Horowitz backed three times in one year, and photo-sharing app BeReal, which it backed in 2021, has stalled.

…More

OpenAI Is a (Relative) Steal

By Stephanie Palazzolo

Jan 22, 2024, 7:35am PST

Over the past year, we’ve seen billions in funding thrown at AI startups at eye-popping valuations. More important than the absolute valuation figures, though, is how they stack up to those startups’ revenue numbers.

In the chart above, we’ve tracked the valuations of eight AI startups that have recently raised funding, calculated against their projected revenue. On average, these companies raised money at a price that is 83 times their projected sales for the next twelve months. That’s a big multiple by any measure, reflecting the rocket ship nature of these startups. But what makes the comparison noteworthy is that OpenAI has one of the lowest multiples, even though its business has the most traction.

Venture capitalists tend to value early-stage startups at a premium based on their growth rates. OpenAI’s business is far bigger and more mature—if we can use that word for a company growing as fast as OpenAI—than other generative AI companies. So, as fast as its revenue pace is growing—more than 20% in just two months most recently—newer firms are growing even faster.

For instance, AI-powered search engine Perplexity AI doubled its annual recurring revenue from $3 million to $6 million from October to January. VCs were likely taking that expected growth into account at the time of investment, as the company would have garnered a much lower 75-times forward revenue multiple if it had raised at the same price just a few months later. 

Similarly, even though OpenAI rival Anthropic was likely generating around $200 million in annualized revenue at the end of last year (according to its October estimates), its projection that it would reach $850 million in annualized revenue by the end of this year surely made its mind-boggling valuation more palatable to investors.

When you see the details of these AI startup funding rounds, it can sometimes feel like investors are throwing darts at nine-figure numbers on a wall. The chart suggests there’s a method to the madness. 

Typically, startups selling to companies are valued based on the sector in which they operate. The lowest valuation multiples are accorded to startups offering industry-specific applications, while those offering more generalized applications draw a premium. The most highly valued firms are often infrastructure startups, which create the tools that developers use to build these apps. This order stems from how big the target market of these startups are, ranging from a specific industry (like healthcare or education) to all developers. 

We can see that general order reflected in burgeoning AI startups. For instance, Harvey, which sells an AI application for lawyers, has one of the lower multiples, while broader-reaching companies like Glean and VAST Data land higher multiples.

It seems like investors aren’t quite sure yet where model developers like OpenAI and Anthropic fall on this spectrum. Their costs are very different from a typical software startup due to how much computing power they need, and many investors are still worried that closed-source model developers may be overtaken by their cheaper, open-source counterparts.

…More

News Of the Week

Ted fellows resign from organisation after Bill Ackman named as speaker

Lucianne Walkowicz and Saeed Taji Farouky accuse Ted of taking anti-Palestinian stand over controversial billionaire’s inclusion

Chris McGreal

The Ted organisation has been hit with resignations and criticisms after naming the controversial activist billionaire Bill Ackman, who was instrumental in forcing out Harvard’s president over antisemitism allegations, among its main speakers at this year’s conference.

Four Ted fellows, led by the astronomer Lucianne Walkowicz and the filmmaker Saeed Taji Farouky, resigned from the group on Wednesday, accusing it of taking an anti-Palestinian stand and aligning itself “with enablers and supporters of genocide” in Gaza.

“2024 main stage speaker Bill Ackman has defended Israel’s genocide and ethnic cleansing of the Palestinian people and has cynically weaponised antisemitism in his programme to purge American universities of Pro-Palestinian freedom of speech,” the pair wrote to Chris Anderson, who leads Ted, and Lily James Olds, director of the fellows programme.

“We’ve become increasingly concerned about the fundamental values and moral compass of the organisation over the years, but with this year’s speaker selection, it is clear Ted has crossed a red line.”

The conference will be held in Vancouver, Canada, in April, under the banner The Brave and the Brilliant”. The theme of Ackman’s talk has not been revealed but his selection was announced last week after he was accused of using his money and influence to help force Claudine Gay’s resignation as Harvard’s president following her disastrous appearance before Congress in December when she was questioned about on-campus antisemitism during the Israel-Gaza war.

Ackman has taken stridently pro-Israel positions, including justifying the scale of the attacks on Gaza in which more than 25,000 Palestinians have been killed, mostly civilians, and the forced removal of about 2 million Palestinians from their homes. He has described criticism of Israel as antisemitism and called for the blacklisting from employment of American students who signed petitions denouncing the offensive in Gaza in the wake of the 7 October Hamas attack on Israel.

Farouky and Walkowicz’s resignation letter noted that other speakers announced by Ted include the journalist Bari Weiss, who they describe as having “a long, sordid, and well-documented history of anti-Palestinian speech”, but that there are no Palestinians in the line-up.

“We refuse for our work and identities to be exploited to promote the Ted brand while the organisation and its speakers generate income and advance their careers through dehumanising Palestinians and justifying their genocide,” the pair said.

After the resignation letter was published, two other fellows – the entrepreneur Ayah Bdeir and cosmologist Renée Hlozek – also quit. Nearly 30 others added their names “in solidarity” without leaving Ted.

…More

Tesla’s Slowdown Disqualifies It From ‘Magnificent Seven’ Group

By Martin Peers, Jan 24, 2024, 5:00pm PST

Stock market pundits may want to come up with a new name for the big tech stocks driving the overall market. The “magnificent seven” descriptor—referring to Apple, Microsoft, Alphabet, Amazon, Meta Platforms, Nvidia and Tesla—no longer seems to make much sense. I’d like to suggest that’s because none of the company CEOs look like cowboy gunslingers from the 1960 movie that made the phrase famous. It’s hard to imagine Steve McQueen playing Tim Cook or Andy Jassy, for instance (although Yul Brynner admittedly could have filled the role of horseback-riding Jeff Bezos).

The real reason the moniker no longer works, however, is that at least one member of the group, Tesla, has had anything but a magnificent 2024 so far, and its fourth-quarter earnings report, released Wednesday, only made things worse. Before Tesla reported earnings tonight, its stock had fallen 16% so far this year, and it tumbled another 3% after hours to around $200 a share. This isn’t a reaction to CEO Elon Musk’s antics, which include asking for a bunch more stock, although that surely doesn’t help. The stock decline reflects the slowdown in sales suffered by Tesla, which observers attribute to increased competition and a loss of government incentives. Automotive revenues, which make up the bulk of Tesla’s top line, grew just 1% in the fourth quarter—down from 18% in the first quarter.

In its outlook for this year issued today, the company said its growth in the volume of car sales would be lower than in 2023, and noted that its team is working on its “next-generation vehicle.” Meantime, expenses have been skyrocketing, eroding its profit margin. But our less-than-rigorous takedown of the magnificent seven branding isn’t just about Tesla. If you look at the year-to-date performance of big tech stocks, or even their 2023 performance, you can see that just two tech stocks have roared this year. One is Nvidia, which is in a class of its own: up 27% since Jan. 1, thanks to its stranglehold on the specialized chips used in artificial intelligence. The other is Meta Platforms, which is up nearly 13%, reflecting confidence in its ad business.  

In comparison, Microsoft and Alphabet are each up around 8%, likely thanks to expectations that AI will lift their businesses, while Apple and Amazon lag behind with year-to-date stock price rises of less than 5% each. Instead of the magnificent seven, it might be more appropriate to refer to the group as Nvidia, Meta and the humble five.

… More

TikTok’s Testing 30 Minute Uploads as It Looks To Expand Its Content Options

By Andrew Hutchinson Content and Social Media Manager

The next stage of TikTok is coming, with some users now seeing the option to upload 30 minute long videos in the app.

As you can see in this example, shared by social media expert Matt Navarra, TikTok’s currently testing the new 30 minute upload option in the beta version of the app.

Which, if you’ve been paying attention, is not really any big surprise.

TikTok has been steadily increasing its maximum post limit for years, with the platform originally starting at 15 seconds per clip, which was then extended to 60 seconds, then 3 minutes, then 5 minutes, before rising to 10 minutes in 2022.

Last October, TikTok began experimenting with 15 minute uploads, so the trend towards longer clips isn’t new.

Though 30 minutes is likely the upper limit, based on the Chinese version of the app. Douyin, which is TikTok in China, expanded its upload limit to 30 minutes per clip in 2022, and it hasn’t gone any further as yet.

And presumably, Douyin has also seen good response to this longer time limit, which is why TikTok is now looking to implement the same, though it does seem like a long time to be watching a TikTok clip in-stream.

Will users really warm to TV show length clips in the app?

…More

Instagram to scan under-18s’ messages to protect against ‘inappropriate images’

Feature will work even on encrypted messages, suggesting platform plans to implement client-side scanning

Alex Hern and Dan Milmo

Instagram will begin scanning messages sent to and from under-18s to protect them from “inappropriate images”, Meta has announced.

The feature, being kept under wraps until later this year, would work even on encrypted messages, a spokesperson said, suggesting the company intends to implement a so-called client-side scanning service for the first time.

But the update will not meet controversial demands for inappropriate messages to be reported back to Instagram servers.

Instead, only a user’s personal device will ever know whether or not a message has been filtered out, leading to criticism of the promise as another example of the company “grading its own homework”.

“We’re planning to launch a new feature designed to help protect teens from seeing unwanted and potentially inappropriate images in their messages from people they’re already connected to,” the company said in a blogpost, “and to discourage them from sending these types of images themselves. We’ll have more to share on this feature, which will also work in encrypted chats, later this year.”

…Much More

Tiger Global Investor Relations Staff Depart After Fundraising Challenges

By Francesca Friday and Maria Heeter

Jan 24, 2024, 4:46pm PST

Several Tiger Global Management employees focused on raising capital for the New York firm’s venture funds have taken buyout offers, according to a person familiar with the matter. The departures of the staff, who worked with prospective investors, come as the firm has struggled to raise money for its latest venture capital fund after a collapse in startup valuations soured its paper returns for earlier funds.

As of the second quarter of 2023, a $12.7 billion fund that Tiger started making investments from in October 2021 had a paper loss of 18%, calculated as an annualized return net of management fees, according to internal data distributed to investors in the fund. That’s a slight improvement from six months earlier, when the 2021 fund showed a loss of 20%. The fund’s performance is in the bottom quartile of funds started that year, the document said, and has also lagged the S&P 500’s annualized net return in the same period.

The Takeaway

• Tiger employee buyouts are the latest example of VC cost-cutting• Tiger’s $12.7 billion had lost 18% on paper as of June* Tiger could soon show a $350 million gain from OpenAI stake

As of June 30, 2023, the $12.7 billion fund hadn’t returned any cash to investors, which isn’t unusual for such a young fund. But the paper losses are closely guarded secrets that reflect the kind of write-downs other venture firms have been making over the past two years as tech valuations have fallen.

It isn’t clear how big Tiger’s investor relations team is, but the departures are the latest example of belt-tightening across the venture industry. Firms are raising smaller funds and striking fewer deals, reducing the need for sprawling support staff—including those who help firms raise money from pension funds and endowments.

..More

Worldcoin hints at new Orb for a friendlier iris-scanning experience

by Vivian Nguyen

The next-gen device will feature various colors and shapes to enhance its visual appeal.

Worldcoin, an iris biometric crypto project, is set to launch a new Orb that aims to offer a more user-friendly iris-scanning experience, said Alex Blania, CEO and co-founder of Tools for Humanity, the developer behind the project, in an exclusive interview with TechCrunch today.

“The next Orb will roll out in the first half of this year and will feature alternative colors and form factors in an effort to look ‘much more friendly,’” Blania explained. “Overall, it is going to look way more tuned down and similar to an Apple product.”

Blania acknowledges that the initial design of the Orb predated his time at the company. “The new orb is coming and the next iterations will look quite different,” he remarked during a fireside chat at a recent StrictlyVC event, signaling a departure from the current, more controversial design.

The goal of Worldcoin, as described by Blania, is to reach billions of users as fast as possible.

“The thesis is very simple. We race toward billions of users as fast as we possibly can,” said Blania.

Founded by Blania, Sam Altman, and Max Novendstern, Tools for Humanity has raised around $250 million from prominent investors like a16z and Bain Capital Crypto, among others. The project is famous for its unique Orb device designed to scan people’s irises and assign them a “World ID,” granting access to Worldcoin’s application and a digital passport. Worldcoin’s vision is to authenticate individual identities and prevent the creation of multiple accounts.

The current design of the Orb has been a topic of much debate due to its intimidating look, similar to a prop from a sci-fi movie, according to Blania. The company has also faced criticism for its beta testing approaches in developing economies and concerns over privacy and data security.

Despite some skepticism, the Orb has seen practical use. At the StrictlyVC event in downtown San Francisco, a Tools for Humanity employee reported that a “couple dozen” attendees scanned their iris to receive a World ID. There has also been “field testing” of the new Orb design.

…More

Startup of the Week

Loyalty Startup Bilt Rewards Hits $3.1B Valuation After $200M Round

Chris Metinko

January 24, 2024

Bilt Rewards, a loyalty rewards startup, raised a $200 million round led by General Catalyst at a $3.1 billion valuation — more than double the number after its last fundraising in 2022.

The round also included participation from Eldridge Industries, Left Lane Capital, Camber Creek and Prosus Ventures.

The New York-based startup allows consumers to earn rewards on the rent they pay. Bilt plans to use some of the proceeds to expand its network to include local dining, grocery stores, ridesharing and other retail purchases.

“We’re not just building a loyalty program; we’re creating a community-centric ecosystem that benefits everyone from renters to local businesses,” said founder and CEO Ankur Jain.

The company also appointed some big names to roles in the company. Bilt named Ken Chenault, former chairman and CEO of American Express, as its chairman, and Roger Goodell, the commissioner of the NFL, as an independent director.

Big money

The company reported its annualized member spend is nearing $20 billion. It also became profitable on an earnings before interest, taxes, depreciation and amortization basis last year.

Those metrics must have impressed investors, as Bilt has seen its valuation shoot up after raising a $150 million Series B at a pre-money valuation of $1.4 billion in October 2022. Founded in 2021, the company has raised a total of $413 million, per Crunchbase.

Last year was a slow go for loyalty startups. Such companies raised only $74 million, per Crunchbase data. However in 2022, loyalty startups raised more than a half-billion dollars thanks to big raises that included Bilt’s Series B and Madison, Wisconsin-based Fetch’s $240 million Series E.

With this fundraise, things are looking up for loyalty startups again.

X of the Week

A reminder for new readers. That Was The Week collects the best writing on critical issues in tech, startups, and venture capital. I selected the articles because they are of interest. The selections often include things I entirely disagree with. But they express common opinions, or they provoke me to think. The articles are only snippets. Click on the headline to go to the original. I express my point of view in the editorial and the weekly video below.

This Week’s Audio:

Thanks To This Week’s Contributors: @jeffbeckervc, @eshap, @stevesi, @gruber, @daringfireball, @SamuelStolton, @leah_nylen, @mattmday, @chrisheuer, @JoannaStern, @Om, @sarahpereztc, @GeorgeNHammond, @Tabby_Kinder, @NicholasMegaw, @PeterJ_Walker, @SteveAbbott415, @adamlashinsky

Contents

* Editorial: 

* Essays of the Week

* Changing the Customer of Venture Capital (Jeff Becker)

* What A Drag It Is (Evan Shapiro)

* Building Under Regulation (Steven Sinovsky)

* Apple’s Plans for the DMA in the European Union (John Gruber)

* Amazon Drops iRobot Deal; Roomba Maker Cuts 31% of Staff (By Samuel Stolton, Leah Nylen, and Matt Day)

* Envisioning the Future of Human Work in the Age of AI: The 2024 Forecast (Chris Heuer)

* Video of the Week

* Joanna Stern Wears a Vision Pro for 24 Hours

* Product of the Week

* The Vision Pro (Daring Fireball)

* Apple’s Vision Pro -The Meta-Review. (Om Malik)

* My 4 magic moments with Vision Pro (Om Malik)

* Apple Vision Pro Review: The Best Headset Yet Is Just a Glimpse of the Future (Joanna Stern)

* News Of the Week

* Spotify calls Apple’s DMA compliance plan ‘extortion’ and a ‘complete and total farce’ (Sarah Perez)

* Investors raise billions to buy discounted stakes in start-ups (George Hammond, Tabby Kinder, Nicholas Megaw)

* Founders: getting to the next venture stage may take longer than you expect (Peter Walker)

* The State of the SaaS Capital Markets: A Look Back at 2023 and Look Forward to 2024 (STEVE ABBOTT Partner, Capital Markets, KEVIN BURKE Partner, Strategy)

* PayPal is laying off 2,500 employees (Pranav Dixit)

* Startup of the Week

* Zum Raises $140M At $1.3B Valuation To Help Kids Get to School Faster With AI (Chris Metinko)

* X of the Week

* For a moment, I almost felt sorry for Mark Zuckerberg. (Adam Lashinsky)

Editorial

You didn’t hear it here first but Apple’s Vision Pro is a hit.Some wonderful essays in this week’s newsletter. I lead with Jeff Becker’s look at venture capital, focusing on who the customer is. The question “Who is the customer?” is crucial for any product. The answer is easy when the product is an asset class - the customer is the person investing money. Yet most of the venture world pretends that the customer is the entrepreneur. In reality, the entrepreneur is a supplier. She or He supplies opportunity, commitment, and execution; the goal is to grow value by investing customer cash into that supply.

Now it is easy to understand why venture investors sometimes describe the recipient of funding as the customer. It is important that the company feels served by the VC. But serving an investee company is clearly a mission carried out for the VC fund investors, the real customer.

Jeff is addressing a real problem - how to best invest in the supply. I will leave you to read his essay and ponder it, but he proposes a radical re-think of how to do early-stage investing, and for the most part, it argues for a more liberal spread of cash, in larger numbers, to far more founders. It's interesting, to say the least.

Evan Shapiro focuses on the rapid aging of the US population. He makes a strong case:

Since 2019, America’s population has grown by 7.8 million. Yet, the US now has 2.7 million fewer kids under 15 than it did in 2019. Meanwhile, there are now 7.1 million more Americans 65-80 than five years ago. America now has half a million fewer people under 40 than it did in 2019 and almost 8.4 million more people over 40.

At a time when politicians from both sides are falling over themselves to point a finger at immigration as a major problem, it is refreshing to see analysis demonstrating that the US needs more immigrants. And in a context where there is virtual full employment this needs to be across all skill levels and needs to trend young. The essay is great.

Part of the anti-immigrant narrative has focused on DACA - Consideration of Deferred Action for Childhood Arrivals (DACA). Ron Conway is part of a group of over 50 businesses signing an amicus brief to support DACA. Bravo to him.

Hostility to immigrants is never OK. It is even less OK when the economy is desperate for skilled and unskilled willing hands.

Politically inspired propaganda dominated elsewhere this week. Amazon was prevented from closing the acquisition of iRobot due to EU objections based on competitive concerns. Well done, EU. Amazon dropped the deal, and iRobot may well be in trouble as a result. Thirty percent of staff were laid off. And more EU interference when Apple was ordered to allow alternative app stores on the iPhone. Steven Sinofsky's wonderful essay, “Building Under Regulation,” leverages his vast experience at Microsoft. It seems every day it becomes more obvious that the EU is against innovation, especially when it produces successful big companies.

The Congress got in on the act too (see X of the Week), calling social media leaders to DC to be accused, show-trial-like, of being responsible for teen suicides. Sadly, the Meta CEO apologized as if admitting culpability.

Teen suicide and causality is a non-trivial issue, but it is fair to say that Social Media does not cause it. Teens (I have one and another two recently in their post-teen phase). All have had growing up challenges. As I recall, I did also. The world can be harsh in the face of those challenges. But to see social media as the only factor, or even a major one, seems superficial and plain wrong. I wish one of the executives had the nerve to push back against the accusations. Adam Lashinsky’s piece is interesting.

Finally, Chris Heuer has a research piece on AI and the Future of Work. Well done, Chris, this is such an important issue. My PoV is that work, defined as paid labor, will inevitably decline and the average working day will decline. I believe this is a fundamental good for humanity. I also believe it poses enormous global questions about how the abundance made possible will be distributed to improve life for everybody. I do. not think this is the end of human effort. Just the beginning of the end of the need to do paid labor in order to live.

Essays of the Week

Changing the Customer of Venture Capital

The gift of technology

JEFF BECKER

JAN 29, 2024

TLDR: We need to change the customer of early-stage venture capital so that we can fund the future of technology and build global prosperity for decades to come.

Recently, I hosted a group of students from Wharton at Antler’s offices and we talked about the future of early-stage VC.

I alluded to this a couple weeks ago when I said:

…for $5B per year, you could seed the vast majority of meaningful tech companies for 8 years with the amount of money Elon Musk spent on Twitter. (Link here)

The reality is, $5B per year just isn’t that much money in the grand scheme of private equities—roughly .5-1% depending how you slice it.

As a former salesperson, that fact often leaves me wondering, “what if you changed the customer of venture capital?”

Could you attract more money, create more impact, and actually produce more returns?

Classically, putting your name on building was a way to not only have a fairly durable legacy, but let’s be honest, that gift is outdated.

And it hardly does any good in the world.

Instead, legacies and the world’s most important problems alike would be better served by a consolidation of brilliant minds and capital, combined with the speed and leverage of startups.

I think there are two interesting solutions, and both should be built.

The first is something I’d call the 501-VC, and the second would be to fund all of venture capital for a decade or more through a new kind of Giving Pledge.

I’m going to talk about the second one today.

Famously,

The Giving Pledge is a promise by the world's wealthiest individuals and families to dedicate the majority of their wealth to charitable causes.

The problem is, charitable foundations and organizations aren’t historically the most efficient way to solve the world’s problems. They exist for good reason, but most operate like old corporates rather than savvy startups.

However, what if we thought of economic opportunity and global prosperity as a more ubiquitous problem to solve, and instead of funding mission-driven work, we fund the entirety of the tech sector?

What if instead of the average high net worth individual trying to get a 3-5X return over 10 years, you focused on the ultra high net worth population, the economic development groups, and the sovereign funds who are both trying to achieve these returns and trying to improve the world?

What if you focused on their shared goals and values as customers, like creating economic opportunity and building a durable legacy?

What if you could do it in every corner of the planet through access to entrepreneurship?

What if instead of one PayPal Mafia, you had thousands?

What if you had an investor who could actually deploy $5B per year at the formation stage?

That has simply never existed before, and yet it is a defining opportunity for the human race and our evolution as a society.

Currently, high potential employees are stuck in their corporate jobs.

Our brightest minds handcuffed to benefits and addicted to a salary, never realizing their true potential or having a real impact on the world.

Many go get their MBA where they spend money to learn new skills and acquire a network, rather than receive money for becoming a more productive citizen of the world.

Many job hop looking for a low-risk way to get on a rocket ship.

Some try to build their own, but quickly run out of runway and mental fortitude.

It’s a broken system, and we need to rebuild it.

First it requires a product.

The product needs to be for two groups—the founders and the investors.

It starts with the infrastructure required to reduce the risk of being a founder which in turn attracts more of the brightest minds to the job itself. At the same time, the product also has to be an investment vehicle that attracts a new type of customer to early-stage VC.

… Lots More

What A Drag It Is

America Feels Old

EVAN SHAPIRO

JAN 29, 2024

Since 2019, America’s population has grown by 7.8 million. Yet, the US now has 2.7 million fewer kids under 15 than it did in 2019. Meanwhile, there are now 7.1 million more Americans 65-80 than five years ago. America now has half a million fewer people under 40 than it did in 2019 and almost 8.4 million more people over 40.

Because of the sheer size of the Baby Boomer Generation and the fact that younger Americans have pulled out on having kids, in the last five years, America has gotten old - not just compared to itself, but also compared to the rest of the world.

In 2019, 63% of the world’s population was under 40. Now, 64% of the people of the planet are 39 or younger. In short:

Over the last half-decade the world has gotten one percent younger and America has gotten one percent older.

One percent may seem small. However, the consequences of this demographic shift are consequential. For countries like the US, the UK, France, Italy, Germany, and Japan, with aging populations where the number of people over 60 is growing faster than the number of people under 15, the coming years will be filled with challenges brought on by their age: Workforce shortages, inverted dependency ratios where a diminishing tax-base struggles to fund a widening social safety net, health care infrastructures ill-equipped to deal with increased demand. As the world’s wealthiest and most powerful nations continue to age faster than they reproduce, expect these issues to get increased and more urgent attention.

After decades of aging down, the US population is now aging up quickly. In 2000, 58% of the US population was under 40 years old. Now just a slim majority of 51% is under 40. The impacts of this rapid maturation can be felt throughout our culture, but perhaps nowhere as dramatically as in America’s Media and Tech industries.

Over the last half century (but for some intermittent challenges from Japan and China), the US has led the world in entertainment and technology, setting the standard for the world’s consumption of Media. While many TVs and phones are manufactured in other countries, most of the systems, software, and vision for these products has come from America - and the entertainment consumed on these devices has been, for many decades, the United States’ most notable export.

Now, America’s Media Industrial Complex finds itself amidst a widely-reported bloodbath of its own making. Recently, this meltdown has been joined by America’s leading Tech firms. Some of this is cyclical, driven by innovation cycles, advertising recessions, and even the aftermath of the worldwide pandemic. But muchof the current Media Apocalypse was as predictable as the upside-down aging ratio of our population.

The first decade of the 21st Century was marked by an almost inconceivable level of innovation in American Media and Tech. The internet invaded all aspects of our lives. Broadband grew across the country like a high-speed weed, bringing the universe to our desktops, making all our worlds, at once, much bigger and infinitely smaller. By 2012, tiny supercomputers known as smartphones had reached a critical mass in the US and TV was streaming into our homes.

Then, right around that time, America’s Media C-Suite inhabitants seemingly started a shared mid-life crisis, through which we are all still living.

Bob Iger took over Disney in 2005, when he was 53 years old. Through some of the most masterful deal-making in Media history, and (seemingly) a true vision of the future, Iger took a troubled company and turned it into the greatest proprietor of intellectual property the world has ever known. He bought Pixar in 2006, revitalizing Disney Animation. He bought Marvel in 2009, jump stating the most successful film and TV franchise in history. He bought Lucasfilm in 2012, completing what many see as bar-setting hat-trick of entertainment, bringing the most valuable collection of titles in entertainment all under one roof.

… Lots More

Building Under Regulation

An essay on the EU Digital Markets Act and Apple’s "Update on apps distributed in the European Union" (and some personal history)

STEVEN SINOFSKY

JAN 27, 2024

Readers note: This is a long post. There are enough hot takes on this super important issue. I welcome corrections as always.

This week Apple detailed the software changes that will appear in an upcoming release of iOS to comply with the European Union Digital Markets Act (DMA).  As I read the over 60 pages of the DMA when it was passed (and in drafts before that, little of which changed in the process) my heart sank over the complexity of a regulation so poorly constructed yet so clearly aimed at specific (American) companies and products. As I read through many of the hundreds of pages of Apple documents detailing their compliance implementation my heart sank again. This time was because I so thoroughly could feel the pain and struggle product teams felt in clinging to at best or unwinding at worst the most substantial improvement in computing ever introduced—the promise behind the iPhone since its introduction. The reason the iPhone became so successful was not a fluke. Consumers and customers voted that the value proposition of the product was something they preferred, and they acted by purchasing iPhone and developers responded by building applications for iOS. The regulators have a different view of that promise, so here we are.

To be clear, DMA covers a wide range of products and services all deemed to be critical infrastructure in the digital world. It is both an incredibly broad and sometimes oddly specific regulation. As written the regulation covers at least online intermediation services [commercial internet sites/markets], online search engines, web browsers, advertising services, social network services, video sharing platforms, number-independent interpersonal communications services [messaging], operating systems, virtual assistants, and cloud computing.

If you’re well-versed in online you can map each one of those to precisely who the target might be, or sometimes targets. It is all big tech, almost exclusively US-based companies. There are no EU companies that meet the criteria to be covered—hardcoded revenue of EUR 7.5 billion for three years, EUR 7.5 billion market cap, or 45 million MAU—with Alphabet, Amazon, Apple, ByteDance, Meta, Microsoft, and Samsung acknowledging the criteria apply to various units in addition to the following other “very large online platforms”: Alibaba AliExpress, Booking.com, Pinterest, Snapchat, Twitter, Wikipedia, Zalando [German fashion retailer]. Those thresholds seem strangely not round.

I am going to focus on the Apple and primarily their App Store response because I think it is the most important and time critical and because iPhone is the most unique, innovative, and singular product in market. I can easily replace search, a browser, an ad network, a social network, a video site. Even cloud computing is not so sticky, and we all use multiple messaging services. What iPhone delivers is irreplaceable. At least for many of the subset of smartphone users that chose Apple.

The thing is, as impressive as Apple has been it is not *that* successful by the measures that count for dominance. Worldwide Apple is clearly the number two smartphone to Google Android which has over 70% share. In the Europe (excluding Russia) Apple iPhone has about a 33% share (I won’t debate exact numbers, units sold v in use, revenue v. profit v. units, etc. as all those do is attempt to tell a story that isn’t obvious, which is Android is more popular). That’s hardly a monopoly share by any standard. In some European countries Apple has a higher share, some data providers would say as high as 50% or nearly 60%, which by most legal standards is still not quite at a monopoly level especially in a dynamic market. Apple has not been fined, sued, or otherwise convicted of having a dominant share let alone abusing the market position it has. No consumer harm has been demonstrated. In Epic v. Applespecifically on the store, Apple prevailed in 9 of 10 claims of damages to Epic due to the store’s costs. Of note, the same claims in Epic v. Google resulted in liability from Google and is being appealed. Many of most vocal competitors didn’t even exist before the iPhone. They have become huge companies and don’t appear to be struggling, and in fact benefit from being part of the iPhone ecosystem. Counter to the text of the DMA, innovation seems to be thriving as measured by the number of new companies and distinct new services.

Yet, the EU DMA has declared that Apple is a “gatekeeper”—an ominous term applied to Apple among the others.

… Lots More

Apple’s Plans for the DMA in the European Union

Friday, 26 January 2024

Apple yesterday announced a broad, wide-ranging, and complex set of new policies establishing their intended compliance with the European Union’s Digital Markets Act, which comes into effect March 7. There is a lot to remark upon and numerous remaining questions, but my favorite take was from Sebastiaan de With on Twitter/X, the day before any of this was announced.

After quipping “Oh god please no” to a screenshot of the phrase “Spotify also wants to roll out alternate app stores”, de With had this conversation:

de With:

The EU is once again solving absolutely no problems and making everything worse in tech. I gotta say, they are if anything highly consistent.

“Anton”:

Overly powerful, rent-seeking gatekeepers seem like a problem.

de With:

I love that I can’t tell if you are talking about the EU or Apple in this case.

My second-favorite take, from that same thread, was this from Max Rovensky:

DMA is not pro-consumer.

It’s anti-big-business.

Those tend to coincide sometimes, which makes it an easy sell for the general public, but do actually read the DMA, it’s quite interesting.

I’d go slightly further and describe the DMA as anti-U.S.-big-business, because as far as I can tell, nothing in the DMA adversely affects or even annoys any European tech companies. There are aspects of it that seem written specifically for Spotify, in fact.

But Rovensky’s framing captures the dichotomy. Anti-big-business regulation and pro-consumer results often do go hand-in-hand, but the DMA exposes the fissures. I do not think the DMA is going to change much, if anything at all, for the better for iOS users in the E.U. (Or for non-iOS users in the EU, for that matter.) And much like the GDPR’s website cookie regulations, I think if it has any practical effect, it’ll be to make things worse for users. Whether these options are better for developers seems less clear.

I’ve often said that Apple’s priorities are consistent: Apple’s own needs first, users second, developers third. The European Commission’s priorities put developers first, users second, and “gatekeepers” a distant third. The DMA prescribes not a win-win-win framework, but a win-win-lose one.

Apple is proud, stubborn, arrogant, controlling, and convinced it has the best interests of its customers in mind.

The European Commission is proud, stubborn, arrogant, controlling, and convinced it has the best interests of its citizens in mind.

Ever since this collision over the DMA seemed inevitable, starting about two years ago, I’ve been trying to imagine how it would turn out. And each time, I start by asking: Which side is smarter? My money has been on Apple. Yesterday’s announcements, I think, show why.

APPLE’S PROPOSED CHANGES

It’s really hard to summarize everything Apple announced yesterday, but I’ll try. Start with the main Apple Newsroom press release, “Apple Announces Changes to iOS, Safari, and the App Store in the European Union”:

“The changes we’re announcing today comply with the Digital Markets Act’s requirements in the European Union, while helping to protect EU users from the unavoidable increased privacy and security threats this regulation brings. Our priority remains creating the best, most secure possible experience for our users in the EU and around the world,” said Phil Schiller, Apple Fellow. “Developers can now learn about the new tools and terms available for alternative app distribution and alternative payment processing, new capabilities for alternative browser engines and contactless payments, and more. Importantly, developers can choose to remain on the same business terms in place today if they prefer.”

Schiller is the only Apple executive quoted in the press release, and to my ear, his writing hand is all over the entire announcement. Apple was quite clear before the DMA was put into law that they considered mandatory sideloading on iOS a bad idea for users, and their announcement yesterday doesn’t back down an inch from still declaring it a bad idea.

Apple has also argued, consistently, that they seek to monetize third-party development for the iOS platform, and that being forced to change from their current system — (a) all apps must come from the App Store; (b) developers never pay anything for the distribution of free apps; (c) paid apps and in-app-purchases for digital content consumed in-app must go through Apple’s In-App Payments system that automates Apple’s 30/15 percent commissions — would greatly complicate how they monetize the platform. And now Apple has revealed a greatly complicated set of rules and policies for iPhone apps in the EU.

MG Siegler has a great — and fun — post dissecting Apple’s press release line-by-line. Siegler concludes:

I’m honestly not sure I can recall a press release dripping with such disdain. Apple may even have a point in many of the points above, but the framing of it would just seem to ensure that Apple is going to continue to be at war with the EU over all of this and now undoubtedly more. Typically, if you’re going to make some changes and consider the matter closed, you don’t do so while emphatically shoving your middle fingers in the air.

Some of these changes do seem good and useful, but most simply seem like convoluted changes to ensure the status quo actually doesn’t change much, if at all. Just remember that, “importantly, developers can choose to remain on the same business terms in place today if they prefer.” What do you think Apple prefers?

The puzzle Apple attempted to solve was creating a framework of new policies — and over 600 new developer APIs to enable those policies — to comply with the DMA, while keeping the path of least resistance and risk for developers the status quo: Apple’s own App Store as it is.

….Lots More

Amazon Drops iRobot Deal; Roomba Maker Cuts 31% of Staff

* IRobot CEO steps down and company cuts workforce by 31%

* Tech giant to pay $94 million to iRobot over deal termination

By Samuel Stolton, Leah Nylen, and Matt Day

January 29, 2024 at 5:33 AM PST

Amazon.com Inc. has abandoned its planned $1.4 billion acquisition of Roomba maker iRobot Corp. after clashing with European Union regulators who had threatened to block the deal.

The fallout came quickly. IRobot, which has been struggling recently, said Chief Executive Officer Colin Angle has stepped downas the company embarks on a restructuring plan that will result in about 350 job cuts, or 31% of the workforce. The vacuum maker’s shares tumbled 19% in New York to $13.80, their lowest level since 2009. Amazon’s shares were up less than 1% at $160.07.

The decision is a sign of the intense pressure Amazon is facing to prove its actions don’t harm competition as its influence grows in retail, cloud-computing and entertainment. Antitrust regulators on both sides of the Atlantic have been keen to ensure that the biggest US tech companies don’t snap up innovative startups before they have a chance to become formidable competitors on their own.

Amazon met with the FTC’s senior antitrust staff last week, who informed the company they were recommending a suit over the deal, according to a person familiar with the meeting. Executives and lawyers from the tech giant were scheduled to meet with the FTC’s three commissioners this week to make a final push for the acquisition, said the person, who asked not to be named discussing the confidential probe.

… Lots More

Envisioning the Future of Human Work in the Age of AI: The 2024 Forecast

Research Fellowship Program

Introduction

As technological change and the adoption of new technologies like artificial intelligence (AI) accelerate, the future of human work will be characterized by disruption, uncertainty, and opportunity. As 2024 approached, the Team Flow Institute Research Fellows gathered for a roundtable to discuss their visions for the future of human-focused work in the age of AI. 

As described by the institute’s co-founder and Managing Director, Chris Heuer, “The Team Flow Institute is an organization dedicated to shaping a human-centric future of work as we face the choice of augmentation or automation in every industry and every function. This transformational decision will reshape what we call work and society itself, requiring us to abandon business as usual and finally design business as possible.” 

The Team Flow Institute Research Fellows’ roundtable discussion delved into the potential opportunities and challenges of this technology revolution driven by the institute’s “mission to gather like-minded individuals and organizations to steer our collective destiny toward a more sustainable future, where the essence of humanity and human work is valued and preserved as we increasingly adopt AI tools and technologies, explained Jennifer McClure, Senior Research Fellow, and Advisory Board member. 

This article analyzes key insights from the discussion, offering a glimpse into the work landscape of 2024 and beyond. As the Team Flow Institute embarks on its inaugural fellowship program, this analysis holds particular significance as it seeks to equip individuals with the knowledge and skills necessary to thrive in the evolving landscape of AI-enabled work. Through this program, the Team Flow Institute aims to foster a community of leaders who can guide organizations and individuals toward a future where humans and technology collaborate to create a more sustainable and fulfilling work environment.

Part I: AI Progress and Promise

No longer relegated to science fiction, AI has infiltrated our lives, transforming industries with its vast potential. From automating tedious tasks to streamlining complex decision-making processes, its applications are far-reaching. In the realm of design, AI-powered software is revolutionizing industries like architecture and fashion, enabling rapid prototyping and personalized creations. Team Flow Institute co-founder Jaime Schwarz says, “Imagine being able to prototype a new building or clothing line in minutes instead of weeks. This remarkable advancement accelerates design cycles and fosters increased customization, ultimately leading to more innovative and personalized consumer products.”

The creative landscape is also poised for disruption with the emergence of generative AI. Team Flow Institute Research Fellow Shel Holtz describes its transformative potential: “Generative AI is blurring the lines between human and machine creativity. We’re seeing machines create realistic text, images, and even music that is nearly indistinguishable from human-generated work.” This democratization of creativity opens doors for individuals with diverse backgrounds and abilities to express themselves in new and exciting ways. But it also opens up philosophical questions and debates about the nature of art and creativity, adds Jen McClure. 

Amidst these exciting advancements, Chris Heuer reminds us that “AI is not just a science fiction concept anymore; it’s here, and it’s changing the way we do everything.” This necessitates a thoughtful approach to the future of work, a need to ensure the value of human skills and their role in work, proactive workforce development initiatives to ensure that individuals are equipped with the necessary skills to thrive in the evolving job market, and an elevation of the need for constant communications within organizations, reminds Team Flow Institute Research Fellow Sharon McIntosh.

As AI continues to permeate our lives, it is crucial to acknowledge its remarkable potential and challenges. By navigating this dynamic landscape with careful consideration and proactive planning, we can ensure that AI serves as a force for progress, innovation, and a brighter future for all. As Team Flow Institute Research Fellow Gina Debogovich reminds us, it will undoubtedly unlock economic growth. “The 20th century began with a global GDP of $3 trillion and, largely due to technological advancement, ended with a GDP of $33.8 trillion. AI is poised to boost the economy to unseen heights.”

AI will be a catalyst for creating new jobs, just as the web did in the mid-1990s. Businesses must integrate these jobs and activities into existing workflows and business models and develop new ones. Indeed, innovative organizations are already experimenting with, if not embracing, the role of prompt engineers. The Team Flow Institute advocates for a Team Flow Facilitator to serve as a coach, a collaboration facilitator, and an AI pilot to support high-performing teams.

Part II: The Risks and Downsides

While AI offers many benefits, possibilities, and opportunities, its advancements are not without potential pitfalls. AI and automation technologies bring both promise and peril to the workforce. While they offer the potential to augment human capabilities and business efficiencies significantly, understandable concerns persist surrounding job losses and the general impact on workers. Organizations must chart a thoughtful course that fully harnesses technical capabilities without losing sight of the humans at the heart of work.

… Lots More

Video of the Week

Product of the Week

The Vision Pro

Tuesday, 30 January 2024

For the last six days, I’ve been simultaneously testing three entirely new products from Apple. The first is a VR/AR headset with eye-tracking controls. The second is a revolutionary spatial computing productivity platform. The third is a breakthrough personal entertainment device.

A headset, a spatial productivity platform, and a personal entertainment device.

I’m sure you’re already getting it. These are not three separate devices. They’re one: Apple Vision Pro. But if you’ll pardon the shameless homage to Steve Jobs’s famous iPhone introduction, I think these three perspectives are the best way to consider it.

THE HARDWARE

Vision Pro comes in a surprisingly big box. I was expecting a package roughly the dimensions of a HomePod box; instead, a Vision Pro retail box is quite a bit larger than two HomePod boxes stacked atop each other. (I own more HomePods than most people.)

There’s a lot inside. The top half of the package contains the Vision Pro headset itself, with the light seal, a light seal cushion, and the default Solo Knit Band already attached. The lower half contains the battery, the charger (30W), the cables, the Dual Loop Band, the Getting Started book (which is beautifully printed in full color, on excellent paper — it feels like a keepsake), the polishing cloth1, and an extra light seal cushion.

To turn Vision Pro on, you connect the external battery pack’s power cable to the Vision Pro’s power connector, and rotate it a quarter turn to lock it into place. There are small dots on the headset’s dime-sized power socket showing how to align the cable connector’s small LED. The LED pulses when Vision Pro turns on. (I miss Apple’s glowing power indicator LEDs — this is a really delightful touch.) When Vision Pro has finished booting and is ready to use, it makes a pleasant welcoming sound.

Then you put Vision Pro on. If you’re using the Solo Knit Band, you tighten and loosen it using a dial on the band behind your right ear. VisionOS directs you to raise or lower the headset appropriately to position it at just the right height on your face relative to your eyes. If Vision Pro thinks your eyes are too close to the displays, it will suggest you switch to the “+” size light seal cushion. You get two light seal cushions, but they’re not the same: mine are labeled “W” and “W+”. The “+” is the same width, to match your light seal, but adds a wee bit more space between your eyes and the displays inside Vision Pro. For me the default (non-“+”) one fits fine.

The software then guides you through a series of screens to calibrate the eye tracking. It’s all very obvious, and kind of fun. It’s almost like a simple game: you stare at a series of dots in a circle, and pinch your index finger and thumb as you stare at each one. You go through this three times, in three different artificial lighting conditions: dark, medium, and bright. Near the end of the first-run experience, you’re prompted to bring your iPhone or iPad nearby, just like when setting up a new iPhone or iPad. This allows your Vision Pro to get your Apple ID credentials and Wi-Fi password without entering any of that manually. It’s a very smooth onboarding process. And then that’s it, you’re in and using Vision Pro.

There’s no getting around some fundamental problems with the Vision Pro hardware.

First is the fact that it uses an external battery pack connected via a power cable. The battery itself is about the width and height of an iPhone 15/15 Pro, but thicker. And the battery is heavy: about 325g, compared to 187g for an iPhone 15 Pro, and 221g for a 15 Pro Max. It’s closer in thickness and weight to two iPhone 15’s than it is to one. And the tethered power cable can be an annoyance. Vision Pro has no built-in reserve battery — disconnect the power cable from the headset and it immediately shuts off. It clicks firmly into place, so there’s no risk of accidentally disconnecting it. But if you buy an extra Vision Pro Battery for $200, you can’t hot-swap them — you need to shut down first.

… Lots More

Apple’s Vision Pro -The Meta-Review.

Apple Vision Pro reviews have started to roll in — and depending on who you read, the consensus vacillates between amazing and work in progress. In most cases, they reflect some version of reality. If one is looking for faults with Apple’s face computer, then one will find them. And if you are looking at what it represents, you are going to be excited. I am in the ‘camp’ of the amazed, though I am not blinded by the challenges that await Vision Pro in the real world.

The Verge’s Nilay Patel sums up the challenge of Vision Pro, writing:

The technology to build a true optical AR display that works well enough to replace an everyday computer just isn’t there yet. The Magic Leap 2 is an optical AR headset that’s cheaper and smaller than the Vision Pro, but it’s plagued by compromises in field of view and image quality that most people would never accept. So Apple’s settled for building a headset with real-time video passthrough — it is the defining tradeoff of the Vision Pro. It is a VR headset masquerading as an AR headset. And let me tell you: the video passthrough on the Vision Pro is really good. It works! It’s convincing. You put the headset on, the display comes on, and you’re right back where you were, only with a bunch of visionOS windows floating around.

Let’s get on with the cons: The Verge points out problems like ‘motion blur,’ ‘blurriness,’ ‘color fringing,’ ‘limited field of view,’ and ‘vignetting.’ I have not personally experienced any of these because, well, I don’t have the device.

The device is sometimes laggy. It’s heavy, and the wired battery is limited to just over 2 hours. You can plug it into a ‘wall charger’ with a USB-C cable, or daisy-chain it to another USB-C battery pack. And it does get a tad warm. You need to use the ‘dorky’ headband to use the device without feeling the weight (or in some cases, a headache).

None of this surprises me! Vision Pro is, after all, a full-blown computer. It’s made from magnesium, carbon fiber, and aluminum. It has two high-resolution front-facing cameras (video pass-through), two cameras that face down to track your hands and gestures, a LiDAR, TrueDepth cameras, and some kind of infrared lights. The device has two tiny MicroOLED displays packed with a total of 23 million pixels. (As I noted in an earlier piece, these displays are the magic and the primary reason why Vision Pro is so expensive.)

All these sensors, cameras, and displays are powered by an M2 chip and an R1 spatial coprocessor, and fans. Apple has packed this in an enclosure that is about three times the weight of the iPhone 15 Pro Max and is still lighter than the iPad 12.9. Paint me impressed purely from a technological standpoint.

…. Lots More

My 4 magic moments with Vision Pro

No, not again! Not another Vision Pro Review! I feel you — after all the reviews yesterday, I am pretty sure you don’t want to read another review. Here’s the good news — it’s not a review. Instead, I will share my quick impressions from a deep dive at Apple Park, and my four magic moments with the Vision Pro.

Unlike the reviewers who published their reviews, my access to the device has come in dribs and drabs. It has been a carefully managed experience — an early demo, exposure to the photos app, and the spatial video capabilities. A few days ago, I got to use the device for less than two hours.

This was a highly curated experience — so this doesn’t and won’t qualify as a review. I am skipping all the stuff that has been covered by the deep dive that professional reviewers have already published. WSJ’s Joanna Stern’s review is amazing — especially the video version. It is best to consider these as my considered impressions.

First, can I wax eloquent about the technological achievement of Vision Pro? As a chip and hardware nerd, I think Vision Pro is a witches’ brew of the latest of all types of technologies. Let me quote my post from yesterday:

Vision Pro is, after all, a full-blown computer. It’s made from magnesium, carbon fiber, and aluminum. It has two high-resolution front-facing cameras (video pass-through), two cameras that face down to track your hands and gestures, a LiDAR, TrueDepth cameras, and some kind of infrared lights. The device has two tiny MicroOLED displays packed with a total of 23 million pixels. (As I noted in an earlier piece, these displays are the magic and the primary reason why Vision Pro is so expensive.)

All these sensors, cameras, and displays are powered by an M2 chip and an R1 spatial coprocessor, and fans. Apple has packed this in an enclosure that is about three times the weight of the iPhone 15 Pro Max and is still lighter than the iPad 12.9. Paint me impressed purely from a technological standpoint.

What’s even more impressive is the sound — Apple is using beamforming to direct the sound into your ears. And unless you are really blasting it out loud — you could get away with wearing it in a public place — though people in Business Class will notice the slight din from the seat next to them. Apple is hoping you will splurge on AirPods Pro.

No matter how you see the device — love it or hate it, you can’t deny that it is yet another amazing computer built by a company that knows how to build great consumer computers.

… Lots More

Apple Vision Pro Review: The Best Headset Yet Is Just a Glimpse of the Future

Working, cooking, skiing, kicking back—our columnist wore Apple’s new mixed-reality headset for a week to see what it’s for

By Joanna Stern at the WSJ

Jan. 30, 2024 at 9:00 am ET

A few things surprised me after wearing the Vision Pro mixed-reality headset for nearly 24 hours straight:

* I didn’t puke. 

* I got a lot of work done.  

* I cooked a delicious meal.

Also, my Persona—the headset’s animated video-call avatar—will haunt your dreams.

For the last week, I have been testing Apple’s boldest bet yet on the post-smartphone future. Strap on the 1.4-pound goggles and you see apps floating right in your living room. Living room a stress-inducing mess? Go full virtual reality and watch a 3-D movie on a giant screen perched on the mouth of a Hawaiian volcano.

Let’s get this out of the way: You’re probably not going to buy the $3,500 Apple Vision Pro. Unless you’re an app developer or an Apple die-hard, you’re more likely to spend that kind of money on an actual trip to a Hawaiian volcano.

And that’s OK. Reviewing the Vision Pro, I wanted to understand the potential of the device, and the technical constraints that keep it from being a must-have, at least for now. Most importantly, I wanted to answer one question: In a world full of screens, what’s the benefit of strapping one to your eyes?

… Lots More

News Of the Week

Spotify calls Apple’s DMA compliance plan ‘extortion’ and a ‘complete and total farce’

Sarah Perez @sarahpereztc / 2:41 PM PST•January 26, 2024

Image Credits: Jakub Porzycki/NurPhoto (opens in a new window)/ Getty Images

Count Spotify among those not thrilled with how Apple has chosen to comply with the EU’s Digital Markets Act (DMA), which sets the stage for sideloading apps, alternative app stores, browser choice, and more. On Friday, the streaming music company issued its response to Apple’s new DMA rules, calling the new fees imposed on developers “extortion” and Apple’s compliance plan “a complete and total farce,” that demonstrated the tech giant believes that the rules don’t apply to them.

Apple earlier this week announced a host of changes that comply with the letter of the EU law, if not the spirit. The company said that app developers in the EU will receive reduced commissions, but it also introduced a new “core technology fee” that requires developers to pay €0.50 for each first annual install per year over a 1 million threshold, regardless of their distribution channel. It will also charge a 3% payment processing fee when developers use Apple’s in-app payments instead of their own.

Epic Games’ CEO Tim Sweeney, whose company sued Apple over antitrust concerns, already condemned Apple’s plan, saying it was a case of “malicious compliance” and full of “junk fees,” and now Spotify is essentially saying the same.

…. Lots More

Investors raise billions to buy discounted stakes in start-ups

Buyers return after secondary market for private shares was hit by higher interest rates

George Hammond and Tabby Kinder in San Francisco and Nicholas Megaw in New York

JANUARY 16 2024

Investment firms are raising billions of dollars to buy stakes in venture capital-backed technology start-ups, as a long drought in acquisitions and initial public offerings forces early investors to offload their stock at discounts.

The start-up secondary market, where investors and employees buy and sell tens of billions of dollars’ worth of shares in privately held companies, is becoming an increasingly important trading venue, in the absence of traditional ways of cashing out and given a slowdown in start-up funding.

Venture secondaries buyers are primed for a busy year as start-up employees look for a way to sell their stock and investors look to return capital to their own backers or reallocate it elsewhere.

Secondary market specialist Lexington Partners last week announced a new $23bn fund to buy up stakes from “large-scale investors”. Lexington had originally aimed to raise $15bn, but upped its target on the back of high demand, and said it was “in the early stages of a generational secondary buying opportunity” that could last years.

The fund will predominantly buy shares from private equity funds but also expects to invest as much as $5bn into venture capital secondaries, said a spokesperson.

“We are seeing crazy amounts of [limited partner investors] that are distressed and need to lighten their venture load,” said the head of a $2bn venture capital firm.

The latest Lexington fund “speaks to the sheer demand” from LPs that feel “over-allocated” to private capital including to start-ups, they said.

Other specialist firms such as Pinegrove Capital Partners, a joint vehicle created by Brookfield Asset Management and Sequoia Heritage, and StepStone have also been raising multibillion-dollar funds to target venture secondaries.

…. Lots More

Founders: getting to the next venture stage may take longer than you expect

Peter Walker

Head of Insights @ Carta | Data StorytellerThe median number of days between a priced seed and Series A round hit 679 in 2023, a new peak.Median for Series A to B was 744 days (over 2 years). Very similar for Series B to C (739 days, also over 2 years).Fascinating to watch the 25th percentile (green) and the 75th percentile (blue) trends as well. It looks as though the 25th pct has pulled closer to the median for the middle venture rounds - suggesting there are very few companies speed-running through venture fundraising right now. Some of that could be company choice, as founders have cut spend and become more capital-efficient over the prior 12 months. However, I'm certain a lot of the increase in time is due to VCs being far more choosy about where to invest.So what are founders doing if primary rounds are not on the menu? Getting creative.Founders are raising bridge rounds at record rates, usually from insiders already on the cap table. They are turning to SAFEs and Convertible Notes, even between named venture stages. Some are turning to non-dilutive financing and loans.And many are trying to make customer revenue their primary fundraising channel. But switching from growth at all costs to profitability in a short period of time is no easy track change. My bet is that the time between rounds plateaus in 2024 (or maybe even declines just a touch). Maybe that's wishful thinking 🙏New data drops from our 40,000 cap table startups every Thursday morning - head to the URL in graphic to put your name on the list!#startups #founders #venturecapital #fundraising #cartadata  

The State of the SaaS Capital Markets: A Look Back at 2023 and Look Forward to 2024

WRITTEN BY

* STEVE ABBOTT

Partner, Capital Markets

* KEVIN BURKE

Partner, Strategy

Another January, another opportunity to make (and break) your New Year’s resolutions, and a new opportunity for us in the venture industry to reflect on the state of the enterprise SaaS markets. We made a good call on the resiliency of the SaaS sector at the beginning of 2023, and remain long-term bullish on SaaS as we have been for years.

This year, we decided to raise the stakes with our outlook, unearthing new data to inform what we anticipate in 2024. We are excited to debut The State of the SaaS Capital Markets annual report. This report highlights the key enterprise software trends we observed in 2023 across both private and public markets, as well as the connection between the two: the exit environment. With this comprehensive set of data views, we share our 2024 predictions regarding the investment environment for enterprise software.   

We like to read, so it’s not lost on us that the last month has produced a ton of quality prediction pieces already, including those from Sapphire President, Partner and Co-Founder Jai Das on what to expect in enterprise technology trends in 2024, as well as year-end reports from investment banks and VC data providers. With the first iteration of this report, we aim to distinguish ourselves in a few significant ways:

* Our analysis covers both private and public enterprise SaaS markets in detail, including several proprietary views on sub-categories.

* Our predictions focus solely on the state of the enterprise SaaS capital markets (vs. the broad technology landscape), including valuations, capital allocation and exits.

* Our prognostication is data-driven, based on a thorough look back at what happened in 2023, how that compared to the past decade and recent quarterly trendlines.

To dig into the data, check out the full report here, and read on for our top 10 predictions for 2024, along with two honorable mentions, with select data views from the report that informed our thinking.  

TOP 10 ENTERPRISE SAAS PREDICTIONS FOR 2024

1. VC Funding will Grow Incrementally in 2024

2023 marked a second consecutive yearly decline in VC funding (-36% YoY), and at $287B (ex-China), it was roughly flat with 2020. We don’t believe this is due to a lack of innovation, but rather that cupboards were fully stocked in 2021. Investors and entrepreneurs are just now starting to see eye-to-eye on valuations. We expect total funding to grow back into the pre-pandemic trendline (+5-10% overall growth) as investors with ample dry powder incrementally increase deal pacing. We believe enterprise software (including, of course, Gen AI-fueled business models) will continue to be a big driver of total VC investment in 2024.

… Lots More

PayPal is laying off 2,500 employees

The cuts come almost exactly a year after PayPal slashed seven percent of its workforce.

Pranav Dixit, Senior Editor

Tue, Jan 30, 2024 at 1:46 PM PST

PayPal is laying off nine percent of its workforce, the company’s CEO Alex Chriss told staff in a letter on Tuesday that PayPal made public hours later. The decision will impact about 2,500 employees, who will find out their fate between today and the end of the week, Bloomberg reported earlier. PayPal's layoffs come almost exactly a year after the company fired more than 2,000 workers to keep costs down.

Despite thousands of job cuts in 2023, layoffs at tech companies have continued into 2024. On the same day as PayPal's latest layoffs, Jack Dorsey's Block, the company that owns Cash App, Foundational, and Square, conducted its second round of layoffs in two months, cutting nearly a thousand people. Earlier this month, Google laid off more than a thousand workers in its Assisstant and hardware divisions, with CEO Sundar Pichai warning employees to brace for more cuts through the year. Discord, eBay, Riot Games, TikTok, Microsoft, iRobot, Amazon, Unity, and Duolingo, among others, have collectively cut thousands of jobs in January

… More

Startup of the Week

Zum Raises $140M At $1.3B Valuation To Help Kids Get to School Faster With AI

Chris Metinko

January 31, 2024

When one thinks of AI and its many uses, getting your kid to school faster is likely not the first thing that springs to mind.

However, school bus startup Zum now has 1.3 billion reasons why you should.

The Redwood City, California-based transportation company raised a $140 million Series E led by GIC at a $1.3 billion valuation. Others participating in the round include Climate Investment, and existing investors Sequoia Capital and SoftBank Vision Fund 2.

The new round is a significant jump in value for a company that last raised money in October 2021 — a $130 million Series D — at what was a reported $930 million valuation.

The 40% valuation jump is even more impressive considering 2021 was a very different time in the private markets, with venture capital funding hitting all-time highs. Since then, many companies have seen their valuations significantly cut.

The wheels on the bus are helped by AI

Zum tries to help school districts increase efficiencies and reduce the costs of managing bus fleets through its proprietary platform — that, of course, uses AI. The platform gives districts visibility so they can optimize routes and even deliver real-time updates to parents.

In addition, the startup also has its own fleet of EV buses for districts to use. The company’s platform also can analyze when to discharge and recharge the buses, so the buses can actually send power back to the grid.

Zum’s platform is already being used by schools in San Francisco, Los Angeles, Oakland, Seattle, Chicago and Nashville among others. Zum serves more than 4,000 schools across the U.S.

“Zum is on a mission to revolutionize student transportation, moving beyond the status quo toward a future where innovative technologies are used to advance sustainability efforts,” said founder and CEO Ritu Narayan.

Founded in 2015, Zum has raised $350 million, per the company.

X of the Week

Opinion: The result of all Washington-Silicon Valley tech showdowns? Nothing.

By Adam Lashinsky, Contributing columnist

February 1, 2024 at 5:43 p.m. EST

For a moment, I almost felt sorry for Mark Zuckerberg.

Here was the founder and CEO of Meta, which runs Facebook, Instagram and WhatsApp, making his eighth appearance before a congressional panel on Wednesday. This time, the arena was a hearing of the Senate Judiciary Committee, at which Zuckerberg endured a withering assault from Sen. Josh Hawley (R-Mo.), he of the clenched-fist support for Jan. 6 insurrectionists but now casting himself as the defender of teenage girls.

“You know full well your product is a disaster for teenagers,” Hawley asserted, citing internal Instagram research. Then Hawley asked, six times by my count, who Zuckerberg fired for allowing young people to be harmed. “Thirty-seven percent of teenage girls between 13 and 15 were exposed to unwanted nudity in a week on Instagram,” Hawley said. “You knew about it. Who did you fire?”

Zuckerberg knows better than most that Hawley’s goal was less of an inquiry than a display of political performance art. The tech entrepreneur wasn’t biting, though, and said he wouldn’t respond to the question. Rightly so: The issue at hand should have been fixing the problem, not determining who was punished for behavior that happens to mirror Meta’s product strategy.

But that’s where I lost sympathy for Zuckerberg — and where Hawley began making sense. “Senator, I don’t think it’s appropriate to talk about HR decisions,” Zuckerberg said, mouthing to an elected official the same sort of nonsense executives use on journalists when they don’t want to answer a question. Zuckerberg was answering a legislative provocation with corporate blather, reminding me that he didn’t need my pity.

Hawley then asked Zuckerberg, a billionaire, if he had compensated any of his company’s victims, which include parents of teenagers who have killed themselves. Zuckerberg replied he didn’t believe so and began explaining that it is his company’s job to build tools to address the concerns at hand. But then Hawley talked over him, this time cutting to the heart of the matter: “To make money,” Hawley said twice, implying that no matter what tap dancing Zuckerberg was engaged in, all the tech titan really cares about is profits.

Zuckerberg, who turns 40 in May, is no longer the innocent man-child of Silicon Valley, if he ever was. Sporting longer hair than at his last congressional appearance, he gave off vibes of a weary mogul who now has seen it all. These routine Washington show trials are just part of the price of doing business.

.. More

The editorial discusses the significant shift in the media landscape, exemplified by Tucker Carlson's move to a digital platform, "X," to conduct a groundbreaking interview with Vladimir Putin. This event underscores the growing power of new, internet-based media platforms to deliver content directly to audiences, bypassing traditional media channels. The rapid adoption of "X" following the interview highlights the internet's capacity to host compelling, unconventional content.

The editorial argues that the essence of this shift isn't about the political implications of the interview but the capability of new media to facilitate such direct engagements. It suggests that platforms like Substack could expand into live events, reflecting the potential for direct audience engagement. Elon Musk's vision for "X" as a global platform delivering essential content aligns with the trend towards audience networks offering sought-after experiences, moving away from traditional web pages and apps.

Furthermore, the piece briefly mentions alternative digital platforms and AI-driven services that redefine user interactions with the internet, indicating a shift from the conventional web to a more interconnected, dynamic online ecosystem. The changing venture market landscape, with opportunities for investment in innovative companies, underscores the broader transition towards a new media era where traditional web formats are replaced by more engaging, experience-driven platforms.

Hats Off To This Week’s Contributors: @RyanMorrisonJer, @geneteare, @mgsiegler, @spyglass_feed, @saulausterlitz, @ClareMalone, @benedictevans, @mikeloukides, @ErikNaso, @kateclarktweets, @finkd, @mattbirchler, @imillhiser, @jaygoldberg, @ron_miller, @btaylor, @sierraplatform, @eladgil

Contents

* Editorial: 

* Essays of the Week

* AI Leads New Unicorn Creation As Ranks Of $1B Startups Swells 

* Behold: The Sports Streaming Bundle

* 40 Years Ago, This Ad Changed the Super Bowl Forever

* Is the Media Prepared for an Extinction-Level Event?

* Video of the Week

* AI and Everything Else - Benedict Evans from Slush

* AI of the Week

* The OpenAI Endgame

* OpenAI Sora– The most realistic AI-generated video to date

* I Was Wrong. We Haven’t Reached Peak AI Frenzy.

* News Of the Week

* I tried Vision Pro. Here's my take

* The Quest 3 is better than you might expect

* The Supreme Court will decide if the government can seize control of YouTube and Twitter

* Arm Results Set The World On Fire

* Startup of the Week

* Bret Taylor’s new AI company aims to help customers get answers and complete tasks automatically

* X of the Week

* Elad Gil on AI

Editorial: And The Oscar Goes to Sora

OpenAI teased its new video creation model - Sora - this week.

In doing so it released a technical report and several examples of prompts and outputs.

Cautious to not over-state the end game the company said:

We explore large-scale training of generative models on video data. Specifically, we train text-conditional diffusion models jointly on videos and images of variable durations, resolutions and aspect ratios. We leverage a transformer architecture that operates on spacetime patches of video and image latent codes. Our largest model, Sora, is capable of generating a minute of high fidelity video. Our results suggest that scaling video generation models is a promising path towards building general purpose simulators of the physical world.

All of the videos are incredible, albeit only a minute or less each. My favorite is the Dogs in Snow video:

Although the ‘Closeup Man in Glasses’ is also wonderful.

I mention this because the speed at which AI is addressing new fields is - in my opinion - mind-boggling. Skills that take humans decades to perfect are being learned in months and are capable of scaling to infinite outputs using words, code, images, video, and sound.

It will take the advancement of robotics to tie these capabilities to physical work, but that seems assured to happen.

When engineering, farming, transport, or production meets AI then human needs can be addressed directly.

Sora winning an Oscar for Cinematography or in producing from a script or a book seems far-fetched. But it wasn’t so long ago that a tech company doing so would have been laughable, and now we have Netflix, Amazon Prime, and Apple TV Plus regularly being nominated or winning awards.

Production will increasingly be able to leverage AI.

Some will say this is undermining human skills, but I think the opposite. It will release human skills. Take the prompt that produced the Dogs in Snow video:

Prompt:A litter of golden retriever puppies playing in the snow. Their heads pop out of the snow, covered in.

I can imagine that idea and write it down. But my skills would not allow me to produce it. Sora opens my imagination and enables me to act on it. I guess that many humans have creative ideas that they are unable to execute….up to now. Sora, DallE, and ChatGPT all focus on releasing human potential.

Google released its Gemini 1.5 model this week (less than a month after releasing Gemini Ultra 1.0). Tom’s Guide has a summary and analysis by Ryan Morrison

Gemini Pro 1.5 has a staggering 10 million token context length. That is the amount of content it can store in its memory for a single chat or response. 

This is enough for hours of video or multiple books within a single conversation, and Google says it can find any piece of information within that window with a high level of accuracy.

Jeff Dean, Google DeepMind Chief Scientist wrote on X that the model also comes with advanced multimodal capabilities across code, text, image, audio and video.

He wrote that this means you can “interact in sophisticated ways with entire books, very long document collections, codebases of hundreds of thousands of lines across hundreds of files, full movies, entire podcast series, and more."

In “needle-in-a-haystack” testing where they look for the needle in the vast amount of data stored in the context window, they were able to find specific pieces of information with 99.7% accuracy even with 10 million tokens of data.

All of this makes it easy to understand why Kate Clark at The Information penned a piece with the title: I Was Wrong. We Haven’t Reached Peak AI Frenzy

I will leave this week’s editorial with Ryan Morrison’s observation at the end of his article:

What we are seeing with these advanced multimodal models is the interaction of the digital and the real, where AI is gaining a deeper understanding of humanity and how WE see the world.

Essays of the Week

AI Leads New Unicorn Creation As Ranks Of $1B Startups Swells  

February 13, 2024

Gené Teare @geneteare

Fewer startups became unicorns in 2023, but The Crunchbase Unicorn Board also became more crowded, as exits became even scarcer.

That means that 10 years after the term “unicorn” was coined to denote those private startups valued at $1 billion or more, there are over 1,500 current unicorn companies globally, collectively valued at more than $5 trillion based on their most recent valuations from funding deals.

All told, fewer than 100 companies joined the Unicorn Board in 2023, the lowest count in more than five years, an analysis of Crunchbase data shows.

Of the 95 companies that joined the board in 2023, AI was the leading sector, adding 20 new unicorns alone. Other leading unicorn sectors in 2023 included fintech (with 14 companies), cleantech and energy (12 each), and semiconductors (nine).

Based on an analysis of Crunchbase data, 41 companies joined the Unicorn Board from the U.S. and 24 from China in 2023. Other countries were in the single digits for new unicorns: Germany had four new companies, while India and the U.K. each had three.

New records nonetheless

Despite the slower pace of new unicorns, the Crunchbase board of current private unicorns has reached new milestones as fewer companies exited the board in 2023.

The total number of global unicorns on our board reached 1,500 at the start of 2024, which takes into account the exclusion of those that have exited via an M&A or IPO transaction. Altogether, these private unicorn companies have raised north of $900 billion from investors.

This year also marks a decade since investor Aileen Lee of Cowboy Ventures

 coined the term unicorn for private companies valued at a billion dollars or more.

In a new report looking at the unicorn landscape 10 years later, Lee said she believes the unicorn phenomenon is not going away, despite a sharp downturn in venture funding in recent years. She expects more than 1,000 new companies in the U.S. alone will join the ranks in the next decade.

Unicorn exits

In 2023, 10 unicorn companies exited the board via an IPO, far fewer than in recent years. That contrasts with 20 companies in 2022 and 113 in 2021.

However, M&A was more active in 2023. Sixteen unicorn companies were acquired in 2023 — up from 2022 when 11 companies were acquired and slightly down from 2021 with 21 companies exiting via an acquisition.

December numbers

Eight new companies joined The Crunchbase Unicorn Board in December 2023. The highest monthly count last year for new unicorns was 10 and the lowest was two.

Of the new unicorns, three are artificial intelligence companies. Other sectors that minted unicorns in December include fintech, cybersecurity, food and beverage, and health care.

The new unicorn companies minted in December 2023 were:

..More

Behold: The Sports Streaming Bundle

It just makes sense. Sports was the last thing holding together the cable TV bundle. Now it will be the start of the streaming bundle.

That's my 5-minute reaction to the truly huge news that Disney, Warner, and Fox are launching a new sports streaming service, combining their various sports rights into one package. Well, presumably. The details are still quite thin at this point. Clearly, several entities were racing to this story, with both WSJ and Bloomberg claiming "scoops" by publishing paragraph-long stories with only the high level facts. I'm linking to Varietyabove, which at least has a few more details, including (canned) quotes from Bob Iger, Lachlan Murdoch, and David Zaslav.

Fox Corp., Warner Bros. Discovery and Disney are set to launch a new streaming joint venture that will make all of their sports programming available under a single broadband roof, a move that will put content from ESPN, TNT and Fox Sports on a new standalone app and, in the process, likely shake up the world of TV sports.The three media giants are slated to launch the new service in the fall. Subscribers would get access to linear sports networks including ESPN, ESPN2, ESPNU, SECN, ACCN, ESPNEWS, ABC, Fox, FS1, FS2, BTN, TNT, TBS, truTV and ESPN+, as well as hundreds of hours from the NFL, NBA, MLB and NHL and many top college divisions. Pricing will be announced at a later date.Each company would own one third of the new outlet and license their sports content to it on a non-exclusive basis. The service would have a new brand and an independent management team

Yes, this is essentially running the Hulu playbook of old, but only for sports content. No, that ultimately didn't end well, but Hulu had a decent enough run before egos got involved.1 Here, the egos are once again being (at least temporarily) set aside to do something obvious: make money. Sports is the one bit of content that most people watch in one form or another, live no less (hence why it was keeping the cable bundle together). And increasingly, with the rise of streaming, it was becoming impossible to figure out what game was on, where. You could get access to most games online now, but it might require buying four or five different services. And again, then finding which one the game you wanted was actually on.

..More

40 Years Ago, This Ad Changed the Super Bowl Forever

An oral history of Apple’s groundbreaking “1984” spot, which helped to establish the Super Bowl as TV’s biggest commercial showcase.

By Saul Austerlitz

Published Feb. 9, 2024Updated Feb. 10, 2024

Four decades ago, the Super Bowl became the Super Bowl.

It wasn’t because of anything that happened in the game itself: On Jan. 22, 1984, the Los Angeles Raiders defeated Washington 38-9 in Super Bowl XVIII, a contest that was mostly over before halftime. But during the broadcast on CBS, a 60-second commercial loosely inspired by a famous George Orwell novel shook up the advertising and the technology sectors without ever showing the product it promoted. Conceived by the Chiat/Day ad agency and directed by Ridley Scott, then fresh off making the seminal science-fiction noir “Blade Runner,” the Apple commercial “1984,” which was intended to introduce the new Macintosh computer, would become one of the most acclaimed commercials ever made. It also helped to kick off — pun partially intended — the Super Bowl tradition of the big game serving as an annual showcase for gilt-edged ads from Fortune 500 companies. It all began with the Apple co-founder Steve Jobs’s desire to take the battle with the company’s rivals to a splashy television broadcast he knew nothing about.

In recent interviews, several of the people involved in creating the “1984” spot — Scott; John Sculley, then chief executive of Apple; Steve Hayden, a writer of the ad for Chiat/Day; Fred Goldberg, the Apple account manager for Chiat/Day; and Anya Rajah, the actor who famously threw the sledgehammer — looked back on how the commercial came together, its inspiration and the internal objections that almost kept it from airing. These are edited excerpts from the conversations.

JOHN SCULLEY On Oct. 19, 1983, we’re all sitting around in Steve [Jobs’s] building, the Mac building, and the cover of Businessweek says, “The Winner is … IBM.” We were pretty deflated because this was the introduction of the IBM PCjr, and we hadn’t even introduced the Macintosh yet.

STEVE HAYDEN Jobs said, “I want something that will stop the world in its tracks.” Our media director, Hank Antosz, said, “Well, there’s only one place that can do that — the Super Bowl.” And Steve Jobs said, “What’s the Super Bowl?” [Antosz] said, “Well, it’s a huge football game that attracts one of the largest audiences of the year.” And [Jobs] said, “I’ve never seen a Super Bowl. I don’t think I know anybody who’s seen a Super Bowl.”

FRED GOLDBERG The original idea was actually done in 1982. We presented an ad [with] a headline, which was “Why 1984 Won’t Be Like ‘1984,’” to Steve Jobs, and he didn’t think the Apple III was worthy of that claim.

..More

Is the Media Prepared for an Extinction-Level Event?

Ads are scarce, search and social traffic is dying, and readers are burned out. The future will require fundamentally rethinking the press’s relationship to its audience.Clare Malone

February 10, 2024

My first job in media was as an assistant at The American Prospect, a small political magazine in Washington, D.C., that offered a promising foothold in journalism. I helped with the print order, mailed checks to writers—after receiving lots of e-mails asking, politely, Where is my money?—and ran the intern program. This last responsibility allowed me a small joy: every couple of weeks, a respected journalist would come into the office for a brown-bag lunch in our conference room, giving our most recent group of twentysomethings a chance to ask for practical advice about “making it.” One man told us to embrace a kind of youthful workaholism, before we became encumbered by kids and families. An investigative reporter implored us to file our taxes and to keep our personal lives in order—never give the rich and powerful a way to undercut your journalism. But perhaps the most memorable piece of advice was from a late-career writer who didn’t mince words. You want to make it in journalism, he said? Marry rich. We laughed. He didn’t.

I’ve thought a lot about that advice in the past year. A report that tracked layoffs in the industry in 2023 recorded twenty-six hundred and eighty-one in broadcast, print, and digital news media. NBC News, Vox Media, Vice News, Business Insider, Spotify, theSkimm, FiveThirtyEight, The Athletic, and Condé Nast—the publisher of The New Yorker—all made significant layoffs. BuzzFeed News closed, as did Gawker. The Washington Post, which lost about a hundred million dollars last year, offered buyouts to two hundred and forty employees. In just the first month of 2024, Condé Nast laid off a significant number of Pitchfork’s staff and folded the outlet into GQ; the Los Angeles Times laid off at least a hundred and fifteen workers (their union called it “the big one”); Time cut fifteen per cent of its union-represented editorial staff; the Wall Street Journal slashed positions at its D.C. bureau; and Sports Illustrated, which had been weathering a scandal for publishing A.I.-generated stories, laid off much of its staff as well. One journalist recently cancelled a networking phone call with me, writing, “I’ve decided to officially take my career in a different direction.” There wasn’t much I could say to counter that conclusion; it was perfectly logical.

“Publishers, brace yourselves—it’s going to be a wild ride,” Matthew Goldstein, a media consultant, wrote in a January newsletter. “I see a potential extinction-level event in the future.” Some of the forces cited by Goldstein were already well known: consumers are burned out by the news, and social-media sites have moved away from promoting news articles. But Goldstein also pointed to Google’s rollout of A.I.-integrated search, which answers user queries within the Google interface, rather than referring them to outside Web sites, as a major factor in this coming extinction. According to a recent Wall Street Journalanalysis, Google generates close to forty per cent of traffic across digital media. Brands with strong home-page traffic will likely be less affected, Goldstein wrote—places like Yahoo, the Wall Street Journal, the New York Times, the Daily Mail, CNN, the Washington Post, and Fox News. But Web sites that aren’t as frequently typed into browsers need to “contemplate drastic measures, possibly halving their brand portfolios.”

What will emerge in the wake of mass extinction, Brian Morrissey, another media analyst, recently wrote in his newsletter, “The Rebooting,” is “a different industry, leaner and diminished, often serving as a front operation to other businesses,” such as events, e-commerce, and sponsored content. In fact, he told me, what we are witnessing is nothing less than the end of the mass-media era. “This is a delayed reaction to the commercial Internet itself,” he said. “I don’t know if anything could have been done differently.”

..Much More

Video of the Week

AI and Everything Else - Benedict Evans from Slush

AI of the Week

The OpenAI Endgame

Thoughts about the outcome of the NYT versus OpenAI copyright lawsuit

By Mike Loukides

February 13, 2024

Since the New York Times sued OpenAI for infringing its copyrights by using Times content for training, everyone involved with AI has been wondering about the consequences. How will this lawsuit play out? And, more importantly, how will the outcome affect the way we train and use large language models?

There are two components to this suit. First, it was possible to get ChatGPT to reproduce some Times articles very close to verbatim. That’s fairly clearly copyright infringement, though there are still important questions that could influence the outcome of the case. Reproducing the New York Times clearly isn’t the intent of ChatGPT, and OpenAI appears to have modified ChatGPT’s guardrails to make generating infringing content more difficult, though probably not impossible. Is this enough to limit any damages? It’s not clear that anybody has used ChatGPT to avoid paying for a NYT subscription. Second, the examples in a case like this are always cherry-picked. While the Times can clearly show that OpenAI can reproduce some articles, can it reproduce any article from the Times’ archive? Could I get ChatGPT to produce an article from page 37 of the September 18, 1947 issue? Or, for that matter, an article from the Chicago Tribune or the Boston Globe? Is the entire corpus available (I doubt it), or just certain random articles? I don’t know, and given that OpenAI has modified GPT to reduce the possibility of infringement, it’s almost certainly too late to do that experiment. The courts will have to decide whether inadvertent, inconsequential, or unpredictable reproduction meets the legal definition of copyright infringement.

The more important claim is that training a model on copyrighted content is infringement, whether or not the model is capable of reproducing that training data in its output. An inept and clumsy version of this claim was made by Sarah Silverman and others in a suit that was dismissed. The Authors’ Guild has its own version of this lawsuit, and it is working on a licensing model that would allow its members to opt in to a single licensing agreement. The outcome of this case could have many side-effects, since it essentially would allow publishers to charge not just for the texts they produce, but for how those texts are used.

It is difficult to predict what the outcome will be, though easy enough guess. Here’s mine. OpenAI will settle with the New York Times out of court, and we won’t get a ruling. This settlement will have important consequences: it will set a de-facto price on training data. And that price will no doubt be high. Perhaps not as high as the Times would like (there are rumors that OpenAI has offered something in the range of $1 million to $5 million), but sufficiently high enough to deter OpenAI’s competitors.

$1M is not, in and of itself, a terribly high price, and the Times reportedly thinks that it’s way too low; but realize that OpenAI will have to pay a similar amount to almost every major newspaper publisher worldwide in addition to organizations like the Authors Guild, technical journal publishers, magazine publishers, and many other content owners. The total bill is likely to be close to $1 billion, if not more, and as models need to be updated, at least some of it will be a recurring cost. I suspect that OpenAI would have difficulty going higher, even given Microsoft’s investments—and, whatever else you may think of this strategy—OpenAI has to think about the total cost. I doubt that they are close to profitable; they appear to be running on an Uber-like business plan, in which they spend heavily to buy the market without regard for running a sustainable business. But even with that business model, billion-dollar expenses have to raise the eyebrows of partners like Microsoft.

The Times, on the other hand, appears to be making a common mistake: overvaluing its data. Yes, it has a large archive—but what is the value of old news? Furthermore, in almost any application but especially in AI, the value of data isn’t the data itself; it’s the correlations between different datasets. The Times doesn’t own those correlations any more than I own the correlations between my browsing data and Tim O’Reilly’s. But those correlations are precisely what’s valuable to OpenAI and others building data-driven products.

..More

OpenAI Sora– The most realistic AI-generated video to date

ERIK NASO

OpenAI Sora is an AI text-to-video model that has achieved incredibly realistic video that is hard to tell it is AI. It’s very life-like but not real. I think we have just hit the beginning of some truly powerful AI-generated video that could change the game for stock footage and more. Below are two examples of the most realistic AI prompt-generated videos I have seen.

Prompt: A stylish woman walks down a Tokyo street filled with warm glowing neon and animated city signage. She wears a black leather jacket, a long red dress, and black boots, and carries a black purse. She wears sunglasses and red lipstick. She walks confidently and casually. The street is damp and reflective, creating a mirror effect of the colorful lights. Many pedestrians walk about.

Prompt: Drone view of waves crashing against the rugged cliffs along Big Sur’s garay point beach. The crashing blue waters create white-tipped waves, while the golden light of the setting sun illuminates the rocky shore. A small island with a lighthouse sits in the distance, and green shrubbery covers the cliff’s edge. The steep drop from the road down to the beach is a dramatic feat, with the cliff’s edges jutting out over the sea. This is a view that captures the raw beauty of the coast and the rugged landscape of the Pacific Coast Highway.

Prompt: Animated scene features a close-up of a short fluffy monster kneeling beside a melting red candle. The art style is 3D and realistic, with a focus on lighting and texture. The mood of the painting is one of wonder and curiosity, as the monster gazes at the flame with wide eyes and open mouth. Its pose and expression convey a sense of innocence and playfulness, as if it is exploring the world around it for the first time. The use of warm colors and dramatic lighting further enhances the cozy atmosphere of the image.

Sora can generate videos up to a minute long while maintaining visual quality and adherence to the user’s prompt. OpenAI SOra states they are teaching AI to understand and simulate the physical world in motion, with the goal of training models that help people solve problems that require real-world interaction.

..More

I Was Wrong. We Haven’t Reached Peak AI Frenzy.

By Kate Clark

Feb 15, 2024, 4:16pm PST

After Sam Altman’s sudden firing last year, I argued the chaos that followed his short-lived ouster would inject a healthy dose of caution into venture investments in artificial intelligence companies. I figured we’d finally reached the peak of the AI venture capital frenzy when a threatened employee exodus from OpenAI risked sending the value of the $86 billion AI juggernaut almost to zero. 

There was plenty of other proof that the hype for generative AI was fading. Investors were openly saying they planned to be a lot tougher on valuation negotiations and would ask startups harder questions about governance. Some companies had begun to consider selling themselves due to the high costs of developing AI software. And an early darling of the AI boom, AI-powered writing tool Jasper, had become the butt of jokes when it slashed internal revenue projections and cut its internal valuation after having won a $1.5 billion valuation in 2022. 

I forgot that everyone in Silicon Valley suffers from short-term memory loss. After a week sipping boxed water with venture capitalists from South Park to Sand Hill Road, I’m convinced I called the end of the AI frenzy far too soon. 

In fact, I expect this year will deliver more cash into the hands of U.S. AI startups than last year, when those companies raised a total of $63 billion, according to PitchBook data. 

Altman’s fundraising ambitions will surely boost the total. A recent report from The Wall Street Journal said Altman plans to raise trillions of dollars to develop the AI chips needed to create artificial general intelligence, software that can reason the way humans do. Even if that number is actually much smaller, talk of such goals lifts the ceiling for other startup founders, who are  likely to think even bigger and to be more aggressive in their fundraising. 

Investor appetite for AI companies is still growing, too. These investors claimed last fall that they were done with the FOMO-inspired deals, but they’re pushing checks on the top AI companies now harder than ever.

..More

News Of the Week

I tried Vision Pro. Here's my take

The Quest 3 is better than you might expect

Posted by Matt Birchler13 Feb 2024

Alex Heath for The Verge: Zuckerberg says Quest 3 is “the better product” vs. Apple’s Vision Pro

He says the Quest has a better “immersive” content library than Apple, which is technically true for now, though he admits that the Vision Pro is a better entertainment device. And then there’s the fact that the Quest 3 is, as Zuck says, “like seven times less expensive.”

I currently own both headsets and while I’m very excited about the potential in the Vision Pro, I actually find it hard to fully disagree with Zuck on this one. I think a lot of people have only used the Vision Pro would be surprised how well the Quest 3 does some things in comparison.

For example, the pass-through mode is definitely not quite as good as the Vision Pro’s, but it’s closer than you might expect. And while people are rightly impressed with how well the Vision Pro has windows locked in 3D space, honestly the Quest 3 is just as good at this in my experience. When it comes to comfort, I do think the Vision Pro is easier to wear for longer periods, but I find it more finicky to get in just the right spot in front of my eyes, while the Quest 3 seems to have a larger sweet spot. And let’s not even talk about the field of view, which is way wider on the Quest to the point of being unnoticeable basically all the time. I kinda think field of view will be similar to phone bezels in that you get used to what you have and anything more seems huge — you can get used to the Vision Pro’s narrower field of view, but once you’re used to wider, it’s hard to not notice when going back.

The Vision Pro has some hardware features that help it rise above (the massively higher resolution screen jumps to mind), but I’m just saying that if you’re looking for everything to be 7x better to match the price difference, I don’t think that’s there.

Beyond this, the products are quite different, though. As Zuckerberg says, the Quest 3 is more focused on fully immersive VR experiences, and while the Vision Pro has a little of that right now, it’s not really doing the same things. And when it comes to gaming it’s not even close. The Quest 3 has a large library of games available and that expands to almost every VR game ever made with Steam Link.

On the other hand, the Vision Pro is much for a “computer” than the Quest ever was. If you can do it on a Mac or an iPad, you can probably already do it on the Vision Pro. And I’m not talking about finding some weird alternate version of your task manager or web browser that doesn’t sync with anything else in your life, I’m talking about the apps you already know and love. This is huge and it’s Apple leveraging its ecosystem to make sure you can seamlessly move from Mac to iPhone to iPad to Vision Pro. And if you can’t install something from the App Store, the web browser is just as capable as Safari on the iPad. If all else fails, you can always just bring your full Mac into your space as well. I will say the Quest 3 can do this and has the advantage of working with Windows as well, but if you have a Mac, it’s much, much better.

This is more words than I expected to write about a CEO saying his product is better than the competition’s (shocker), but I do think that Zuck’s statement is less insane than some may think it to be.

..More

The Supreme Court will decide if the government can seize control of YouTube and Twitter

We’re about to find out if the Supreme Court still believes in capitalism.

By Ian Millhiser Feb 15, 2024, 7:00am EST

Ian Millhiser is a senior correspondent at Vox, where he focuses on the Supreme Court, the Constitution, and the decline of liberal democracy in the United States. He received a JD from Duke University and is the author of two books on the Supreme Court.

In mid-2021, about a year before he began his longstanding feud with the biggest employer in his state, Florida’s Republican Gov. Ron DeSantis signed legislation attempting to seize control of content moderation at major social media platforms such as YouTube, Facebook, or Twitter (now called X by Elon Musk). A few months later, Texas Gov. Greg Abbott, also a Republican, signed similar legislation in his state.

Both laws are almost comically unconstitutional — the First Amendment does not permit the government to order media companies to publish content they do not wish to publish — and neither law is currently in effect. A federal appeals court halted the key provisions of Florida’s law in 2022, and the Supreme Court temporarily blocked Texas’s law shortly thereafter (though the justices, somewhat ominously, split 5-4 in this later case).

Nevertheless, the justices have not yet weighed in on whether these two unconstitutional laws must be permanently blocked, and that question is now before the Court in a pair of cases known as Moody v. NetChoice and NetChoice v. Paxton.

The stakes in both cases are quite high, and the Supreme Court’s decision is likely to reveal where each one of the Republican justices falls on the GOP’s internal conflict between old-school free market capitalists and a newer generation that is eager to pick cultural fights with business.

..More

Arm Results Set The World On Fire

February 13, 2024 · by D/D Advisors · in Analyst Decoder Ring. ·

Arm reported its second set of earnings as a (once again) public company last week. These numbers were particularly strong, well above consensus for both the current and guided quarters. Arm stock rallied strongly on the results up ~30% for the week. These numbers were important as they go a long way to establishing the company’s credibility with the Street in a way their prior results did not.

That being said, we saw things we both liked and disliked in their numbers. Here are our highlights of those:

Positive: Growing Value Capture. One of our chief concerns with the company since IPO has been the low value they capture per licensed chip shipped – roughly $0.11 per chip at the IPO. That figure continued to inch higher in the latest results, but critically they pointed out that their royalty rate doubles with the latest version of their IP (v9). This does not mean that all of their royalty rates are going to double any time soon, but it does point very much in the right direction. Critically, they noted this rate increase applies to architectural licenses as well.

Negative: The Model is Complex. Judging from the number of questions management fielded on the call about this rate increase no one really knows how to model Arm. The company has a lot of moving parts in its revenue mix, and they have limits to their ability to communicate some very important parts of their model. We think that at some point the company would be well served by providing some clearer guide posts on how to build these models or they risk the Street always playing catch up with a wide swing of expectations each quarter.

Positive: Premium Plan Conversion. The company said three companies converted from their AFA plan to the ATA model. We will not get into the details of those here, but these can best be thought of in software terms with customers on low priced subscription plans converting to Premium subscription plans. This is a good trend, and management expressed a high degree of confidence that they expect to see it continue. They have spent a few years putting these programs in place and seem to have thought them through. This matters particularly because these programs are well suited for smaller, earlier-stage companies. The old Arm struggled to attract new customers in large part because of the high upfront costs of Arm licenses. Programs like AFA and ATA could go a long way to redressing those past wrongs.

Negative: China remains a black box. Arm China is of course a constant source of speculation. In the latest quarter it looks like a large portion of growth came from China which does not exactly square with other data coming from China right now. It is still unclear to us how much of Arm’s revenues from China’s handset companies gets booked through Arm China as a related party transaction and how much is direct. Investors are confused too. There is no easy solution to this problem, digging too hard into Arm China’s numbers is unlikely to make anyone happy with the answers, but hopefully over time it all settles down.

Positive: Growing Complexity of Compute. Management repeatedly mentioned this factor, noting that this leads to more chips and more Arm cores shipping in the marketplace. Some of this is tied to AI, but we think the story is broader than that. It is going to be tempting to see much of Arm’s growth as riding the AI wave, but this does not fully capture the situation. The AI story is largely about GPUs, which are not particularly heavy with Arm cores. But those GPUs still need some CPU attach, and AI accelerators can sometimes be good Arm targets.

Negative: Diversification. Arm remains heavily dependent on smartphones, and we suspect the return to inventory stocking by handset makers is playing a big role in their guidance. When asked about segmentation of their results the company declined to update the model provided during the IPO. We hope to see some diversification here when they do update their figures later in the year.

Overall, the company did a good job in the quarter. They still have some kinks to work out with their communication to the Street, but this was a good second step as a public company.

..More

Startup of the Week

Bret Taylor’s new AI company aims to help customers get answers and complete tasks automatically

Ron Miller @ron_miller / 6:36 AM PST•February 13, 2024

Image Credits: mi-vector / Getty Images

We’ve been hearing about former Salesforce co-CEO Bret Taylor’s latest gig since he announced he was leaving the CRM giant in November 2022. Last February we heard he was launching an AI startup built with former Google employee Clay Bavor. Today, the two emerged with a new conversational AI company called Sierra with some bold claims about what it can do.

At its heart, the new company is a customer service bot. That’s not actually all that Earth-shattering, but the company claims that it’s much more than that, with its software going beyond being an extension of a FAQ page and actually taking actions on behalf of the customer.

“Sierra agents can do so much more than just answer questions. They take action using your systems, from upgrading a subscription in your customer database to managing the complexities of a furniture delivery in your order management system. Agents can reason, problem solve and make decisions,” the company claimed in a blog post.

Having worked with large enterprise customers at Salesforce, Taylor certainly understands that issues like hallucinations, where a large language model sometimes makes up an answer when it lacks the information to answer accurately, is a serious problem. That’s especially true for large companies, whose brand reputation is at stake. The company claims that it is solving hallucination issues.

Image Credits: Sierra

At the same time, it’s connecting to other enterprise systems to undertake tasks on behalf of the customer without humans being involved. These are both big audacious claims and will be challenging to pull off.

..More

X of the Week

That Was The Week 2024 #8

Congratulations to this week’s selected creators: @mvpeers,@jgkelley, @CollingsPaige, @hbarra, @krishnanrohit, @geneteare, @chudson, @aliyalakhani, @jeffbeckervc, @nvidia, @LanceUlanoff, @JoannaStern, @RachelEnsignWSJ, @gvipers, @viaCristiano, @jacobbogage, @marianaa_alfaro, @stevesi, @mgseigler, @oliverbethell, @abbyohlheiser, @alex, @ChristineMHall, @Jessicalessin

Contents

* Editorial: Ban Foreigners Owning Key Assets?

* Essays of the Week

* Busting Myths on Foreign Media Ownership as TikTok Ban Looms

* Congress Should Give Up on Unconstitutional TikTok Bans

* Vision Pro is an over-engineered “devkit”

* LLMs have special intelligence, not general, and that's plenty.

* Fintech Unicorns Trot Onto Leaderboard In February

* The Changing Nature of Pre-Seed Syndication

* Screening for Maniacs

* Video of the Week

* NVIDIA CEO Jensen Huang

* AI of the Week

* Forget Sora, this is the AI video that will blow your mind – and maybe scare you

* OpenAI Made AI Videos for Us. These Clips Are Good Enough to Freak Us Out.

* News Of the Week

* House passes TikTok bill that could ban app in the U.S., spawning Senate

* support

* HR 7521

* Steven Mnuchin Says He Is Putting Together a Group to Buy TikTok

* Strangulation or Regulation?

* An update on our preparations for the DMA

* Banning TikTok would be both ineffective and harmful

* Coinbase Raises $1 Billion Through Convertible Notes Offering

* Stripe’s growth continues to impress as total payment volume tops $1 trillion

* Startup of the Week

* The Information

* X of the Week

* Cyan Bannister on Space X and Elon Musk

Editorial: Ban Foreigners Owning Key Assets?

As I digested the news that the House had voted to force Chinese-based investor ByteDance to divest ownership in TikTok, I pondered whether the US or US companies owned key strategic assets in other nations. I was pretty sure the answer was yes.

I asked ChatGPT:

What key assets of overseas countries are owned by the United States or US Companies?

The answer was long. There are a lot, covering Real Estate, Energy and Natural Resources, Financial Services, Technology and Telecoms, Infrastructure, Media, Entertainment, Agriculture, and Pharmaceuticals and healthcare.

I asked it to dive deeper into Energy and Natural Resources:Can you expand on energy and natural resources and list the top 5 assets that are US-owned by strategic to the country in question?

ChatGPT

Expanding on the energy and natural resources sector, U.S. companies' overseas investments often focus on areas with significant strategic value, either due to their size, the nature of the resources, or their critical role in the host country's economy. Identifying the "top 5" assets can be challenging due to the dynamic nature of the industry and the sensitivity around such strategic assets. However, I can provide examples that highlight the kind of assets that would be considered strategically significant:

* Oil Fields in the Middle East: U.S. companies have long had interests in the Middle East's oil fields, which are among the world's largest and most productive. An example would be Chevron's stake in the Partitioned Zone between Saudi Arabia and Kuwait. These assets are crucial due to their vast reserves and the global oil market's dependence on Middle Eastern oil.

* Natural Gas Projects in Australia: The U.S. energy giant Chevron operates two of Australia's largest natural gas projects, Gorgon and Wheatstone. Australia is a key player in the global LNG market, and these projects represent significant U.S. interests in the region, providing energy to Asia-Pacific markets.

* Mining Operations in Africa: U.S. companies have significant mining operations in Africa. For instance, Freeport-McMoRan's involvement in the Democratic Republic of the Congo's cobalt and copper mining industry is crucial, given cobalt's importance in battery production for electric vehicles.

* Shale Gas in Argentina: U.S. companies like Chevron and ExxonMobil are involved in Argentina's Vaca Muerta shale formation, one of the largest reserves of shale gas and oil outside North America. This is strategic for Argentina, contributing to its energy security and potential as an energy exporter.

* Renewable Energy Investments in Europe: U.S. companies are increasingly investing in renewable energy assets abroad, such as Iberdrola, a Spanish company in which the U.S. investment bank JPMorgan Chase holds a significant stake. This investment is strategic as Europe transitions towards sustainable energy, and Iberdrola is a major player in wind and solar energy.

These examples illustrate the diverse nature of U.S. energy and natural resource investments abroad, emphasizing assets that are strategically important due to their size, the resources they provide, or their role in the host country's energy sector.

What is the point of this exercise? The goal is to illustrate that global interconnectedness is the norm, not the exception. International relations have had reciprocity—allowing foreign companies to operate in the U.S. fosters a reciprocal environment where American companies can also expand and thrive overseas. The moment the domicile of ownership appears as an issue, the biggest loser will be the largest owner of foreign assets—hint: not China.

TikTok does not represent a threat to the US. And Bytedance’s ownership is not more concerning than Shell’s ownership of oil platforms overseas should be. Indeed, Bytedance, and therefore TikTok, is not even “Chinese” anymore: This is from the FT:

The company is often described by western politicians as a “Chinese” entity. However, as I have noted before, some 60 per cent of the group is actually owned by “international” investors, overwhelmingly American. An estimated $8bn has been invested by private capital companies, including Sequoia Capital, Susquehanna, General Atlantic and Coatue Management. Mainstream investment funds such as Fidelity, T Rowe Price and BlackRock are exposed, too.

Returning to the economic nationalism of the inter-war years and fear-driven politics will not serve humanity at all. Demonizing Chinese ownership will equally have negative results, especially if China reciprocates with US ownership, such as Tesla or Apple in China.

Who benefits from this demonization? - jingoistic politicians seeking cheap votes. I cannot think of any example of jingoism serving good human outcomes.

So, it seems the “predecessor” agrees, but I do not favor a TikTok ban or forced divestiture. I am with the EFF (see this week’s essays) in seeing this ban as wholly negative.

Lawmakers Ignoring The Law

In her influential 2017 Yale Law Journal article, "Amazon's Antitrust Paradox," Lina Khan argues that the current antitrust framework, which primarily focuses on consumer welfare and price effects, fails to capture the full range of anticompetitive practices employed by digital platforms like Amazon. She suggests that the Sherman Act and other antitrust laws may need to be reinterpreted or updated to address these companies' specific challenges from an anti-trust point of view.

Khan writes,

"The current framework in antitrust—specifically its pegging competition to 'consumer welfare,' defined as short-term price effects—is unequipped to capture the architecture of market power in the modern economy."

She argues that focusing primarily on price effects overlooks other ways digital platforms can harm competition, such as by leveraging their dominance across multiple markets or using their control over data to create barriers to entry.

While Khan does not explicitly state that the Sherman Act is inadequate, her arguments suggest that the current interpretation and application of antitrust laws, including the Sherman Act, may not be sufficient to address the challenges posed by Big Tech. Her work has contributed to a broader discussion about updating antitrust enforcement for the digital age. But the harsh truth is - she cannot use current Law because her targets are not breaking it.

The DOJ complaint that Apple is a monopoly (not a crime) and abusing its monopoly power fails if the Sherman Act is relied upon to judge criminality. Although the FTC is not bringing the case—it is run by Lina Khan—the DOJ is clearly on the same page as she is in bringing it. In July 2023, I argued, “Khan and Gensler Should be Fired.” The case for that is now even more convincing.

As Jason Snell from Six Colors argues:

Defining a “monopoly.” Before we get to some of the details of Apple’s specific anti-competitive behavior, it’s worth noting that this suit is charging Apple with violations of the Sherman antitrust act, which is meant to specifically regulate monopolies. Things that are legal for regular companies to do become illegal when monopolies do them.Part of this document, then, has to establish that Apple holds monopoly power over a specific market. Given that Apple’s share of the U.S. smartphone market is about 60 percent, how can it be called a monopoly? The DoJ attempts to square this circle in a few different ways: It uses revenue instead of unit sales, pointing out that Apple and Samsung combined hold 90 percent of the U.S. smartphone market by revenue. It creates a new sub-market, the “Performance Smartphone,” which pushes Apple up to about 70 percent of the market in terms of unit sales. It accuses Apple of attempting to create a monopoly through its various business tactics, which is also illegal.Questions I would ask about this approach: Can you add in Samsung, find a number starting in ninety, and declare something a monopoly? Is revenue share how monopolies are defined? Can you draw borders on a product category in a beneficial way in order to declare it a new market?Apple’s position in the U.S. market is certainly strong, but regardless of how you view its behavior, it will be interesting to see if the DoJ can make a convincing case that Apple is actually a monopoly, given the presence of Samsung and Google in the market. Jason Snell, six colors

Because the law does not provide a solid case against Apple, the DOJ is attempting to redefine the meaning of words to allow its case. This alone should be sufficient evidence that the complaint is a political, not a criminal, decision. The case will fail before a judge and jury, and Apple’s response indicates it plans to fight.

Renowned former journalist Walt Mossberg had this to say on Threads:

https://www.threads.net/@mossbergwalt/post/C41RaBuvrC0

And Steven Sinofsky - his article is below - gives a damning appraisal of the DOJs chances.

His first day X post is a great overview from somebody who - at Microsoft - has been down this path with the DOJ. Click the graphic for the full thread.

https://twitter.com/stevesi/status/1770878948421059035?s=61&t=vSSPDgMsv3aFc2ctR_yOww

Apple’s multibillion-dollar investment in building a global software distribution platform benefits its shareholders. But it also benefits users, even Android users. Who in their right mind would have thought Eric Schmidt would have focused on mobile as much had Apple not started the mobile revolution in 2007?

The intense competition for users (Android’s many varieties have about 80% global market share) drives innovation on all sides.

The essence of the DOJ case is that Apple should be forced to be as bad as Android, or there will be no equality. The essay By Kurt Vonnegut that Daring Fireball ‘typeset’—‘HARRISON BERGERON’—is therefore entirely appropriate—and hilarious, too. It’s the first Essay of the Week. See below.

This DOJ complaint is not for “the people.” It is for the DOJ and the FTC, who are increasingly attempting to hold back innovation, especially when the innovator is better than the competition. This makes it increasingly irrelevant as accelerated competition challenges all incumbents.

OpenAI and its peers (now several) are a great example, seemingly driving two of the slower movers - Apple and Google - to partner on AI in the next version of iOS.

Well, there you have it. Shame on the DOJ for filing this amateur complaint. And if we buy the DOJ case or fail to oppose it, Shame on us.

Contents

Editorial: Lawmakers Ignoring the Law

Essays of the Week

‘HARRISON BERGERON’ ★ (Fiction) United States v. Apple (Complaint) Apple slams DOJ case as misguided attempt to turn iPhone into Android The Department of Justice comes for Apple A few thoughts on the DOJ’s antitrust case against Apple Two Roads Diverged: The Splitting of Venture Capital

Video of the Week

The Odds of Raising a Series A, The Latest in Venture Valuations, The AI Premium and More! - Jason Lemkin

AI of the Week

Nvidia's Accelerating AI Strategy. RTZ Apple Is in Talks to Let Google Gemini Power iPhone AI Features How to win at Vertical AI After raising $1.3B, Inflection is eaten alive by its biggest investor, Microsoft Here’s how Microsoft is providing a ‘good outcome’ for Inflection AI VCs, as Reid Hoffman promised Stability AI CEO resigns because you’re ‘not going to beat centralized AI with more centralized AI’ Saudi Arabia Announces New $40B AI Fund AI is changing writing

News Of the Week

VC Funds Drawing Down More Capital Truth Social is going public Reddit prices IPO at $34 per share, the top of the range

Startup of the Week

Neuralink video shows patient using brain implant to play chess on laptop

X of the Week

Always good to know you can be fired from Deepmind for being an a*****e, abandon your $$ startup, and still get hired as a Microsoft VP!

Congratulations to this week’s creators: @aatilley, @kimmackrael, @gruber, @mgsiegler, @cookie, @AndrewYNg, @sequoia, @mikebutcher, @marketsentiment, @datadrivenvc, @AndreRetterath, @rzhou186, @blockchained000, @lauramandaro, @rideember, @psawers, @affinitybyserif, @canva

Contents

* Editorial: 

* Essays of the Week

* Apple Turns to Longtime Steve Jobs Disciple to Defend Its ‘Walled Garden’

* The EU’s Share of Apple’s Global Revenue

* Apple EU Fine is Bonkers

* Marissa Mayer’s startup just rolled out photo sharing and event planning apps, and the internet isn’t sure what to think

* Video of the Week

* Andrew Ng at Sequoia Capital AI Day

* AI of the Week

* New study of unicorn founders finds most are ‘underdogs,’ and female founders are rising

* Do Hedge Funds beat the market?

* How to Automate Startup Screening?

* The Data-Driven Investor Of Today And Tomorrow

* How to Use ChatGPT to Learn Data Driven Investing?

* News Of the Week

* Sam Bankman-Fried Sentenced to 25 Years in Prison

* Amazon doubles down on Anthropic, completing its planned $4B investment

* BlackRock CEO ’very bullish’ on Bitcoin as its ETF crosses $17B

* FTX Founder Bankman-Fried Sentenced To 25 Years For Fraud, Conspiracy

* Secondary Market Seeing Rebound After Slowdown

* Why Fewer Than 20% of Startup Unicorns Are Likely to Go Public Soon

* Startup of the Week

* How Ember is building an all-electric intercity bus network in the UK

* X of the Week

* Affinity Acquired by Canva

Contents

Editorial: When is a Bubble not a Bubble?

Essays of the Week

The great rewiring: is social media really behind an epidemic of teenage mental illness?

The Day the Music Lied

Weapons of Mass Production

China’s future economy

This Message Will Self-Destruct in 33 Seconds

1 in 6 People Will Be Aged 65+ by 2050

Venture Investing This Week

Global Venture Funding In Q1 2024 Shows Startup Investors Remain Cautious

First Cut - State of Private Markets: Q4 2023

The Investments Where I’m Going to Lose All My Money

Quant VC and What it Means for Startup Investing

Video of the Week

New Apple Vision Pro Personas

AI of the Week

Meet the YC Winter 2024 Batch

The 18 most interesting startups from YC’s Demo Day show we’re in an AI bubble

YCombinator's AI boom is still going strong (W24)

Bubble Trouble

Big Tech companies form new consortium to allay fears of AI job takeovers

News Of the Week

Apple Vision Pro’s Persona feature gets collaborative

Jon Stewart Plunges the Knife into Apple

Startup of the Week

Rubrik’s IPO filing hints at thawing public markets for tech companies

X of the Week

Mike Maples on Y Combinator

Editorial

I’ve taken to writing this on Friday morning. I put the curated content together Thursday evening, which gives me overnight to reflect. Usually, the title comes first and is somehow correlated to the content below.

This week, there is a lot about AI. The Y Combinator story in AI of the week is the story that the “bubble” will be challenged due to a lack of training data. In contrast, the story is that AI will remove so many jobs that the larger companies have formed a consortium to allay fears.

I also created a new section separating out Venture Capital. This is the week of quarterly updates from Q1. They suggest there is no bubble at all. Only Amazon’s multi-billion dollar investment in Anthropic stands out.

But for me, the question posed in the title is - When is a Bubble not a Bubble? - is not triggered by the AI stories. The Economist’s Simon Cox writes about China and its future in a newsletter and the linked article. He frames it well:

In 2006, for example, China’s leaders declared the need to “rely more than ever on scientific and technological progress and innovation to drive a qualitative leap in productivity”. Science and technology, they added, are “the concentrated embodiment…of advanced productive forces”. That ambition, and indeed that diction, sound very similar to the slogans emanating from Beijing today. Xi Jinping, China’s leader, has, for example, urged provincial governments to cultivate “new productive forces”, based on science and technology. In this week’s issue I explore what those words might mean.

As Simon points out, “productive forces” is a formulation derived from Hegel and Marx. It combines technology and human beings into a duality that expresses how we produce things. Indeed, there is no pure “technology” separate from human beings and the division of labor. Productivity is the expression of both and the measurable thing.

In the Western enlightenment tradition, we use the word progress to mean the same thing.

All progress requires humans to invent time-saving methods to reduce the effort involved in making and doing things.

China’s discussion (especially if you remove the word China) is about building the future through innovation. It stands in contrast to the dominant discussions here in the US - Regulation, the dangers of Social Media, Immigration, Women’s Right to Choose, Guns, and even Climate. And a lot of pessimism around technology and science.

That is except for in the startup ecosystem. The dominant Silicon Valley belief system is similar to Simon Cox’s description of China’s goals.

Accelerated Innovation dominates the set of assumptions in the Bay Area. Why? Because AI, Nuclear Fusion, Decentralized Networks, Global Ambition, and the skills and money they require all live here. And their potential is real. And the timing of the potential is near-term (several years).

Strangely, the US Government seems to consider innovation, especially “Big Tech,” a problem. China and Silicon Valley seem to consider it a solution. And by “Silicon Valley,” I do not only mean geographically but also as a way of thinking.

That bifurcation of optimism and pessimism, enshrined in a Government that wants to restrict tech company power, has led many in the Valley to abandon traditional two-party politics and increasingly articulate agendas that are both optimistic and independent of Government. Government is perceived as a cost of doing business, not a benefit.

So, the innovation that comes out of Silicon Valley and the money it attracts are often scorned by those who are not part of it. The word “Bubble” is heavily laden and used to imply that there is nothing valid, real, or transformational. The money is simply irrational.

“Bubble” is a pessimists word for “fake”.

It goes alongside other narratives that cast doubt on innovation. In some ways, Tomasz Tunguz's piece on the shrinking attention span implies a problem caused by the abundance of content and limited time to read it. Although one might consider the ability to parse information and determine whether it is attention-worthy and do it quickly would be a good thing.

The idea that teens commit suicide and get depressed due to alienating social media comes to mind as another anti-technology narrative. The first ‘Essay of the Week’ from Nature magazine presents a strong case that this is bogus.

Rex Woodbury’s “Weapons of Mass Production” and Michael Spencer and Chris Dalla Riva’s “AI and the Future of Music Production and Creation” (The Day the Music Lied) point to the explosion of production and creative production that AI will trigger.

Rex:

Spotify reinvented music distribution. It put 100 million songs in your pocket. Generative AI will reinvent music production. There are a number of early-stage startups that let you toggle artist, genre, and ~vibe~ to create a wholly new work—e.g., “Create a Miley Cyrus breakup song with a sad, wistful feeling to it.” Of course, these companies will need to navigate the labyrinth of music rights, but some version of these tools feels inevitable.

This example embodies a broader shift we’re seeing from distribution ➡️ production.

Michael Spencer and Chris Dalla Riva:

In summary, the music industry will likely come to embrace much of this technology as long as AI firms properly license the music catalogs necessary to train their models. This still begs one final question: Is any of this good for music?

It’s important to unpack words like Bubble. They live in a context. As Simon Cox discusses, the future depends on progress, innovation, or “productive forces.” So, this “Bubble” is not a bubble.

Contents

* Editorial: 

* Essays of the Week

* Video of the Week

* AI of the Week

* News Of the Week

* Startup of the Week

* X of the Week

Editorial

Contents

* Editorial: 

* Essays of the Week

* Video of the Week

* AI of the Week

* News Of the Week

* Startup of the Week

* X of the Week

A reminder for new readers. That Was The Week includes a collection of my selected readings on critical issues in tech, startups, and venture capital. I selected the articles because they are of interest to me. The selections often include things I entirely disagree with. But they express common opinions, or they provoke me to think. The articles are sometimes long snippets to convey why they are of interest. Click on the headline, contents link or the ‘More’ link at the bottom of each piece to go to the original. I express my point of view in the editorial and the weekly video below.

Congratulations to this week’s chosen creators: @TechCrunch, @Apple, @emroth08, @coryweinberg, @mariogabriele, @peterwalker99, @KevinDowd, @jessicaAhamlin, @stephistacey, @ttunguz, @annatonger, @markstenberg3, @EllisItems, @TaraCopp, @ingridlunden, @Jack, @karissabe, @psawers, @Haje, @mikebutcher, @tim_cook

Contents

* Editorial: Hating the Future

* Essays of the Week

* Apple’s ‘Crush’ ad is disgusting

* Apple apologizes for iPad ‘Crush’ ad that ‘missed the mark’

* Milken’s New Power Players

* Ho Nam on VC’s Power Law

* State of Private Markets: Q1 2024

* The weight of the emerging manager

* Pandemic-era winners suffer $1.5tn fall in market value

* Video of the Week

* Apples iPad Video

* AI of the Week

* The Fastest Growing Category of Venture Investment in 2024

* Meet My A.I. Friends

* OpenAI plans to announce Google search competitor on Monday, sources say

* Leaked Deck Reveals How OpenAI Is Pitching Publisher Partnerships

* A Revolutionary Model.

* An AI-controlled fighter jet took the Air Force leader for a historic ride. What that means for war

* Sources: Mistral AI raising at a $6B valuation, SoftBank ‘not in’ but DST is

* News Of the Week

* Jack Dorsey claims Bluesky is 'repeating all the mistakes' he made at Twitter

* FTX crypto fraud victims to get their money back — plus interest

* Apple’s Final Cut Camera lets filmmakers connect four cameras at once

* Startup of the Week

* Wayve co-founder Alex Kendall on the autonomous future for cars and robots

* X of the Week

* Tim Cook

Editorial: Hating the Future

An Ad and its Detractors

bet a lot of money that the TechCrunch writing and editorial team have had an interesting 72 hours.

After Apple announced its new iPad on Tuesday, the ad that supported it was initially widely slammed for its cruelty to obsolete tools for creativity, including a piano, guitar, and paint. This week’s Video of The Week has it if you don’t know what I am talking about.

A sizeable crushing machine compresses the items with colossal force, and in the end, an iPad can incorporate the functions of traditional items.

It's not the most amazing ad ever, certainly not as bold as Steve Jobs's 1984 ad, but it's in the same genre. The past must be crushed to release new freedom and creativity for a fraction of the price and, often, the power and flexibility.

Oh, and it’s thin, very thin.

I was not offended. Devin at TechCrunch was. He leads this week’s essay of the week with his “Apple’s ‘Crush’ ad is disgusting” and does not mince words:

What we all understand, though — because unlike Apple ad executives, we live in the world — is that the things being crushed here represent the material, the tangible, the real. And the real has value. Value that Apple clearly believes it can crush into yet another black mirror.This belief is disgusting to me. And apparently to many others, as well.

He also makes the incorrect point that:

A virtual guitar can’t replace a real guitar; that’s like thinking a book can replace its author.

It’s more like a digital book replacing a paper book than the author being replaced. Oh wait… that has happened.

That said, a virtual guitar can replace a real guitar, and an AI guitar can even replace a virtual guitar—and be better. That is not to say there are no more actual traditional guitars. They will be a choice, not a necessity, especially for people like me who can’t play a guitar but will be able to play these.

Devin had his supporters in the comments (go read them).

Handmaid’s Tale director Reed Morano told Apple CEO Tim Cook to “read the room” in a post on X.

Matthew Carnal captured my somewhat unkind instinct:

There were a lot more reactions to the Apple ad haters like Matthews.

Of course, many old instrument lovers (the instruments, not their age) hated the Ad. By Thursday, this being the times we live in, Apple apologized for the ad:

Tor Myhren, Apple’s vice president of marketing, said the company “missed the mark.”

“Creativity is in our DNA at Apple, and it’s incredibly important to us to design products that empower creatives all over the world,” Myhren told Ad Age. “Our goal is to always celebrate the myriad of ways users express themselves and bring their ideas to life through iPad. We missed the mark with this video, and we’re sorry.”

Please judge for yourself below, but my 2c is that the ad was a moderately underwhelming attempt to champion innovation. It is certainly not offensive unless you are ultra-sensitive and have feelings for pianos, guitars, and paint. Oh, and hate attempts to recreate them in a more usable form. And Apple really should have taken the high ground here.

I spent some of the week in LA at the CogX Festival and virtually at the Data Driven Summit by @AndreRetterath. The latter focused on what is happening in Venture Capital, as do several of this week’s essays. Milken’s event was running in LA also. Its attitude to Venture Capital is best summed up here:

“We’re all being told in the market that DPI is the new IRR,” B Capital’s Raj Ganguly said onstage Wednesday. (The acronym sandwich means investment firms have to actually prove that their investments actually generate cash through a metric called distributions to paid-in capital, not just theoretically, through internal rate of return.) “Even the venture panel at Milken is at the end of the day on Wednesday,” he joked, meaning that it didn’t get top billing at the conference, which had started a couple days earlier.

This does sum up where we are. Hundreds of Billions of dollars are still trapped inside companies funded in 2020-2022, with little prospect of producing returns. The impact is that there is less funding for current startups (see the Carta piece below). And much of what is flowing is flowing to AI and into a very small number of companies (see Tomasz Tungux below).

However, innovation and funding are still possible. This week’s Startup of the Week is Wayve, a UK autonomous driving platform that seems to agree with Elon Musk that cameras are sufficient to teach a car to drive. Wayve’s ambitions go beyond Cars (also like Musk) but differ in that the product is available to all developers to embed in their products.

“Very soon you’ll be able to buy a new car, and it’ll have Wayve’s AI on it … Then this goes into enabling all kinds of embodied AI, not just cars, but other forms of robotics. I think the ultimate thing that we want to achieve here is to go way beyond where AI is today with language models and chatbots. But to really enable a future where we can trust intelligent machines that we can delegate tasks to, and of course they can enhance our lives and self-driving will be the first example of that.”

Love that attitude.

Essays of the Week

Apple’s ‘Crush’ ad is disgusting

Devin Coldewey, 1:58 PM PDT • May 9, 2024

Apple can generally be relied on for clever, well-produced ads, but it missed the mark with its latest, which depicts a tower of creative tools and analog items literally crushed into the form of the iPad.

Apple has since apologized for the ad and canceled plans to televise it. Apple’s VP of Marketing Tor Myhren told Ad Age: “We missed the mark with this video, and we’re sorry.” Apple declined to offer further comment to TechCrunch.

But many, including myself, had a negative and visceral reaction to this, and we should talk about why. It’s not just because we are watching stuff get crushed. There are countless video channels dedicated to crushing, burning, exploding and generally destroying everyday objects. Plus, of course, we all know that this kind of thing happens daily at transfer stations and recycling centers. So it isn’t that.

And it isn’t that the stuff is itself so valuable. Sure, a piano is worth something. But we see them blown up in action movies all the time and don’t feel bad. I like pianos, but that doesn’t mean we can’t do without a few disused baby grands. Same for the rest: It’s mostly junk you could buy off Craigslist for a few bucks, or at a dump for free. (Maybe not the editing station.)

The problem isn’t with the video itself, which in fairness to the people who staged and shot it, is actually very well done. The problem is not the media, but the message.

We all get the ad’s ostensible point: You can do all this stuff in an iPad. Great. We could also do it on the last iPad, of course, but this one is thinner (no one asked for that, by the way; now cases won’t fit) and some made-up percentage better.

What we all understand, though — because unlike Apple ad executives, we live in the world — is that the things being crushed here represent the material, the tangible, the real. And the real has value. Value that Apple clearly believes it can crush into yet another black mirror.

This belief is disgusting to me. And apparently to many others, as well.

Destroying a piano in a music video or Mythbusters episode is actually an act of creation. Even destroying a piano (or monitor, or paint can, or drum kit) for no reason at all is, at worst, wasteful!

But what Apple is doing is destroying these things to convince you that you don’t need them — all you need is the company’s little device, which can do all that and more, and no need for annoying stuff like strings, keys, buttons, brushes or mixing stations.

We’re all dealing with the repercussions of media moving wholesale toward the digital and always-online. In many ways, it’s genuinely good! I think technology has been hugely empowering.

But in other, equally real ways, the digital transformation feels harmful and forced, a technotopian billionaire-approved vision of the future where every child has an AI best friend and can learn to play the virtual guitar on a cold glass screen.

Does your child like music? They don’t need a harp; throw it in the dump. An iPad is good enough. Do they like to paint? Here, Apple Pencil, just as good as pens, watercolors, oils! Books? Don’t make us laugh! Destroy them. Paper is worthless. Use another screen. In fact, why not read in Apple Vision Pro, with even faker paper?

What Apple seems to have forgotten is that it is the things in the real world — the very things Apple destroyed — that give the fake versions of those things value in the first place.

A virtual guitar can’t replace a real guitar; that’s like thinking a book can replace its author.

That doesn’t mean we can’t value both for different reasons. But the Apple ad sends the message that the future it wants doesn’t have bottles of paint, dials to turn, sculpture, physical instruments, paper books. Of course, that’s the future it’s been working on selling us for years now, it just hadn’t put it quite so bluntly before.

When someone tells you who they are, believe them. Apple is telling you what it is, and what it wants the future to be, very clearly. If that future doesn’t disgust you, you’re welcome to it.

Apple apologizes for iPad ‘Crush’ ad that ‘missed the mark’

/

The company says ‘we’re sorry’ after its ad was seen as dismissive by the creatives Apple typically tries to court.

By Emma Roth, a news writer who covers the streaming wars, consumer tech, crypto, social media, and much more. Previously, she was a writer and editor at MUO.

May 9, 2024 at 1:22 PM PDT

Apple has apologized after a commercial meant to showcase its brand-new iPad Pro drew widespread criticism among the creative community. In a statement provided to Ad Age, Tor Myhren, Apple’s vice president of marketing, said the company “missed the mark.”

“Creativity is in our DNA at Apple, and it’s incredibly important to us to design products that empower creatives all over the world,” Myhren told Ad Age. “Our goal is to always celebrate the myriad of ways users express themselves and bring their ideas to life through iPad. We missed the mark with this video, and we’re sorry.”

On Tuesday, Apple introduced the M4-powered iPad Pro, which the company described as its thinnest product ever. To advertise all the creative possibilities with the iPad, it released a “Crush!” commercial that shows things like a piano, record player, paint, and other works flattening under the pressure of a hydraulic press. At the end, only one thing remains: an iPad Pro.

The ad rubbed some creatives the wrong way. Hugh Grant called it a “destruction of human experience,” while Handmaid’s Tale director Reed Morano told Apple CEO Tim Cook to “read the room” in a post on X. Apple didn’t immediately respond to The Verge’s request for comment.

Milken’s New Power Players

By Cory Weinberg

May 8, 2024, 5:00pm PDT

It’s no secret that the suits at the annual big-money confab put on by the Milken Institute this week have few spending limits. Staring you in the face in the lobby of the Beverly Hilton is a booth set up by Bombardier, marketing its private jets to attendees. (A new 10-seater costs $32 million, I learned.)

What attendees can’t really buy, however, is time. The soundtrack of the Los Angeles conference might as well have been a ticking clock. Fund managers at private equity and venture capital firms are running out of time to distribute cash to their investors, a task complicated by the paucity of either mergers or public offerings that typically provide VC and PE firms with a way to cash out. The fact that interest rates now appear likely to stay higher for longer doesn’t help. 

That meant a lot of conversations at the conference weren’t about grand investment strategies. Instead, people were conferring about financial tactics to distribute cash or kick the can down the road by selling stakes on the secondary markets or spinning up continuation funds, essentially rolling investors’ commitments forwards—not the most inspiring stuff.  

“We’re all being told in the market that DPI is the new IRR,” B Capital’s Raj Ganguly said onstage Wednesday. (The acronym sandwich means investment firms have to actually prove that their investments actually generate cash through a metric called distributions to paid-in capital, not just theoretically, through internal rate of return.) “Even the venture panel at Milken is at the end of the day on Wednesday,” he joked, meaning that it didn’t get top billing at the conference, which had started a couple days earlier.

The new kings of the conference were firms with a lot more time to play with—that is, sovereign wealth funds with buckets of oil and natural gas money, or pension funds with long-term investment horizons rather than shorter 10-year fund lives. The contrast here is embodied in the financial concept of duration: How long do you actually need to get cash back on your investment? And how sensitive is it to interest rate hikes?

The sentiment was everywhere. I shared a Lyft ride with one PE investor last night who called sovereign wealth funds “the only game in town” for PE firms raising new money. Abu Dhabi sovereign wealth fund Mubadala Capital and the Qatar Investment Authority were two of the conference’s top sponsors, meaning they were paying up to explain themselves to the finance and tech universe. That tactic seemed to be working. 

“You’re going to have people lining up their business cards for capital from QIA, I can already see,” quipped Leon Kalvaria, an executive at Citi, onstage with QIA’s head of funds, Mohsin Tanveer Pirzada.  

Not everyone will suck it up, of course. These funds often get tagged with a “dumb money” label—because they sometimes drive up prices for the rest of the investment world. They still have to face questions about who they are, their source of funds, and the sometimes authoritative regimes behind them. For now, though, it’s their time in the spotlight. 

Ho Nam on VC’s Power Law

Lessons from Arthur Rock, Steve Jobs, Don Lucas, Paul Graham and beyond.

MARIO GABRIELE, MAY 07, 2024

Friends, 

We’re back with our latest edition of “Letters to a Young Investor,” the series designed to give readers like you an intimate look at the strategies, insights, and wisdom of the world’s best investors. We do that via a back-and-forth correspondence that we publish in full – giving you a chance to peek into the inbox of legendary venture capitalists.   

Below, you’ll find my second letter with Altos co-founder and managing director Ho Nam. For those who are just joining us, Ho is, in my opinion, one of the great investors of the past couple of decades and a true student of the asset class.

Because of his respect for the practice of venture capital, I was especially excited to talk to him about today’s topic: learning from the greats. Who were Ho’s mentors? Which investors does he most admire and why? What lessons from venture’s past should be better remembered by today’s managers? 

Lessons from Ho

* Prepare for one true winner. Even skilled investors often have just one or two outlier bets over the course of their career. Because of venture’s power law, their returns may dwarf the dividends of all other investments combined. Your mission is to find these legendary businesses, engage with them deeply, and partner for decades.  

* Focus on the company. Venture capital is full of short-term incentives. Instead of focusing on raising new vintages or building out Altos as a money management firm, Ho and his partners devote themselves to their portfolio companies. Though firm building is important, if you find great companies and work with them closely, you will have plenty of available options. 

* Pick the right role models. Ho chose his mentors carefully. Though there have certainly been louder and flashier investors over the past four decades, Ho learned the most from Arthur Rock, Don Lucas, and Arnold Silverman. All were understated and focused on the craft of investing. Find the people you consider true practitioners, and study their work. 

* Watch and learn. Learning from the greats can be done from a distance and may not include a memorable anecdote or pithy saying. Ho’s biggest lessons came from observing the habits of practitioners like Rock and Lucas, not via a structured mentorship or dramatic episode. It’s by studying the everyday inputs of the greats that you may gain the most wisdom.

Mario’s letter

Subject: Learning from the greatsFrom: Mario GabrieleTo: Ho NamDate: Friday, April 12 2024 at 1:59 PM EDT

Ho, 

After moving out of New York City (at least for a little bit), I’m writing to you from a small house on Long Island. It’s been really lovely to have a bit more space and quiet away from the city’s intermittently inspiring and exhausting buzz.

..Lots More, Must Read

State of Private Markets: Q1 2024

Authors: Peter Walker, Kevin Dowd

Published date:  May 7, 2024

The venture capital fundraising market remained slow in Q1 2024, but valuations held steady or climbed at almost every stage.

Contents

* State of Private Markets: Q1 2024

* Key trends

* Fundraising & valuations

* Employee equity & movement

* Industry-specific data

* Methodology

* Overview

* Financings

* Terminations

The startup fundraising market got off to a cautious start in 2024. 

At current count, companies on Carta closed 1,064 new funding rounds  during the first quarter of the year, down 29% compared with the prior quarter. The decline was sharpest at the early stages of the venture lifecycle: Deal count fell by 33% at the seed stage in Q1 and 36% at Series A. 

Instead of new primary funding events, many companies opted to raise bridge rounds. At both seed and Series A, more than 40% of all financings in Q1 were bridge rounds. Series B wasn’t far behind, at 38%. 

VCs were still willing to spend big on certain deals. Despite the decrease in round count, total cash invested increased slightly in Q1, reaching $16.3 billion. But when it came to negotiating their valuations, many startups had to settle: 23% of all new rounds in Q1 were down rounds, the highest rate in more than five years. 

After experiencing a pandemic-era surge and subsequent correction,the venture market settled into a quieter place in 2023. So far, that relative tranquility has continued into 2024.

Q1 highlights

* VCs look to the West: Startups based in the West census region captured 62% of all venture capital raised by companies on Carta in Q1, the highest quarterly figure since Q1 2019. The Northeast, South, and Midwest all saw their market share decline.

* The Series C market bounces back: Series C startups raised $4.6 billion in new capital in Q1, a 130% increase from the previous quarter. The median primary Series C valuation was $195.7 million, up 48% from the prior quarter.

* Layoffs still  linger: Companies on Carta laid off more than 28,000 employees in Q1. But job cuts have grown less frequent since January, with March seeing the fewest monthly layoffs in nearly two years.

Note: If you’re looking for more industry-specific data, download the addendum to this report for an extended dataset. 

Key trends

The current Q1 figures of 1,064 total rounds and $16.3 billion in cash raised will both increase in the weeks to come, as companies continue to report transactions from the quarter. With those projected increases, the final data for Q1 will likely look quite similar to fundraising numbers from each of the past few quarters. 

Those quarterly  fundraising numbers from 2023 ended up looking fairly similar to 2018, 2019, and the first half of 2020. In terms of numbers of deals and cash raised, it’s looking more and more like the pandemic  bull market will go down as an anomalous stretch in what has otherwise been a fairly steady market. 

After apparently reaching a plateau during 2023, the rate of down rounds experienced another notable increase during Q1 2024, jumping to 23%. The median time between startup rounds is roughly two to three years, depending on the stage. This timeline means that many companies raising new funding in Q1 would have last raised funding sometime in 2021, when valuations were soaring across the venture landscape. Considering how valuations have declined in the time since, it makes sense that down rounds are still prevalent. 

Companies in the West census region combined to bring in 53.3% of all capital raised by startups on Carta from Q2 2023 through Q1 2024, with California accounting for nearly 45% of that cash. Massachusetts ranked second among the states with 12.71% of all capital raised, while New York claimed 10.31%.

In terms of VC activity, the West region is centered around California. The Northeast revolves around Massachusetts and New York. The South has two smaller hubs, in Texas (4.67%) and Florida (3.99%). The Midwest, though, is without a real standard-bearer: Illinois led the way in terms of cash raised over the past 12 months, at just 1.68%. 

The West (and specifically California)  has always been the center of gravity for the U.S. venture capital industry. During Q1, the region’s gravitational force seems to have gotten even stronger. Startups based in the West raised 62% of all total capital invested on Carta in Q1, its highest quarterly figure since Q1 2019. 

As a result, the other three census regions saw their market shares decline in Q1—in some cases significantly. The proportion of all VC raised by startups raised in the South fell to 12% in Q1, down from 17% the prior quarter and from 23% a year ago. And the Midwest’s share of cash raised fell from 7% down to 4%. 

For early-stage investors, Q1 was the slowest quarter in many years. Seed deal count fell to 414, down 33% from Q4 2023, and Series A deal count dropped to 313, a 36% decline. In both cases, those are the lowest quarterly deal counts since at least the start of 2019. 

Total cash raised also declined at both stages in Q1. The $3.1 billion in Series A cash raised in Q1 represents a 35% decline quarter-over-quarter and a 34% dip year-over-year. Cash raised at the seed stage declined by 33% both quarter over quarter and year over year.

It was a much friendlier fundraising quarter for companies in the middle stages of the startup lifecycle. The number of Series B deals in Q1 declined by a more modest 11% compared to the prior quarter. And Series C deal count increased by 14%, marking the busiest quarter for that stage since Q2 2023. 

Total cash raised also rose significantly at Series C in Q1, hitting $4.6 billion. That’s a 130% increase quarter-over-quarter and a 44% bump year-over-year. At Series B, total cash raised has now increased in consecutive quarters. 

Compared to earlier stages, transactions at the Series D and at Series E+  remain few and far between. There were just 39 venture rounds combined in Q1 among startups at Series D or later, the second-fewest of any quarter in the past five years. The lowest count came one year ago, in Q1 2023, when there were just 29 combined late-stage deals. Total cash raised across these stages has been mostly consistent over the past few quarters. There’s been more variation in average round size. The average Series D round in Q1 was about $77 million, compared to $56 million in Q4 2023.

..Lots More

The weight of the emerging manager

By Jessica Hamlin

May 3, 2024

Risk-averse limited partners tend to gravitate to fund managers with a long track record, but are they missing out on potential upside by avoiding emerging managers?

Over the past decade, emerging managers’ share of US private market fundraising activity has declined steadily.

In 2023, this figure fell to 12.7%, the lowest share of capital raised by newer fund managers since before 2000, according to PitchBook’s recent analyst note,Establishing a Case for Emerging Managers.

Limited exits in PE and VC over the past two years have exacerbated this reality. With minimal distributions, LPs are working with smaller private market budgets to allocate to new and existing managers.

But, by allocating almost exclusively to established managers, LPs may be missing out on significant potential returns.

In VC, for example, emerging managers have outperformed established GPs since 1997, consistently producing a higher median IRR than established managers. This reflects the nature of the asset class, in which a small number of funds determine the majority of returns across venture firms.

“The average venture return is not very exciting,” said Laura Thompson, a partner at Sapphire Partners, which invests in early-stage VC funds and runs an emerging manager program for the California State Teachers’ Retirement System. “Where can you get really good returns? It’s the smaller fund sizes and emerging managers.”

This is where that risk-return scale comes in.

In a counterweight to that outperformance, a PitchBook analysis showed that returns from emerging VC managers were more volatile: While top quartile emerging funds tended to outperform, bottom and median players only marginally bested their established manager counterparts.

The new manager playbook

In traditional buyout fund investing, emerging managers are gaining traction. While established managers, propped up by decades of institutional knowledge, have historically outperformed newer managers, the “new guys” actually outperformed their seasoned peers in the last investing cycle.

This article appeared as part of The Weekend Pitch newsletter. Subscribe to the newsletter here

Top decile buyout funds from emerging managers with vintages between 2015 and 2018 outperformed established peers by 6.6 percentage points, suggesting that emerging buyout managers may have picked up some steam over the past decade, according to PitchBook data.

The emerging managers program at the New York City retirement systems and NYC Office of the Comptroller, for example, has $9.9 billion in emerging manager commitments, the majority of which is allocated to PE. Last year, the comptroller’s office reported that the emerging managers in the systems’ private markets portfolios outperformed their respective benchmarks by nearly 5%.

A diverse portfolio

New York City’s Bureau of Asset Management sees emerging managers as a key element of a diverse portfolio, said Taffi Ayodele, director of diversity, equity, and inclusion and the emerging manager strategy at the NYC Office of the Comptroller.

Ayodele said the smaller emerging private market managers in New York’s portfolios offer access to the lower middle market and creative roll-up strategies that may not be accessible through larger firms.

“What we don’t want to do is lock ourselves out of these high-performing, differentiated strategies for the simplicity of going with the big guys,” Ayodele said.

Some of the country’s largest public pension plans are betting on the success of their emerging manager programs. In 2023, the California Public Employees’ Retirement System made a $1 billion commitment to newly established private market investors, and the Teacher Retirement System of Texas, which boasts one of the largest emerging manager programs in the country, committed $155 million to emerging PE managers last year.

At the same time, the recent boom years for private markets led to a flood of new GPs. Some might have gotten lucky—say, with a well-timed exit at the peak—while others were hurt by less fortunate timing. A major challenge for today’s LPs will be to sort out a manager’s abilities from the market’s whims.

One advantage of backing up-and-comers now is that the down market has weeded the ranks of new GPs. “The emerging managers who are fundraising now are really dedicated,” Thompson said.

James Thorne contributed reporting to this story.

Pandemic-era winners suffer $1.5tn fall in market value

Top 50 biggest stock gainers hit by painful decrease since the end of 2020 as lockdown trends fadeStephanie Stacey in London

Fifty corporate winners from the coronavirus pandemic have lost roughly $1.5tn in market value since the end of 2020, as investors turn their backs on many of the stocks that rocketed during early lockdowns.

According to data from S&P Global, technology groups dominate the list of the 50 companies with a market value of more than $10bn that made the biggest percentage gains in 2020.

But these early-pandemic winners have collectively shed more than a third of their total market value, the equivalent of $1.5tn, since the end of 2020, Financial Times calculations based on Bloomberg data found.

Video-conferencing company Zoom, whose shares soared as much as 765 per cent in 2020 as businesses switched to remote working, has been one of the biggest losers. Its stock has fallen about 80 per cent, equivalent to more than a $77bn drop in market value, since the end of that year.

Cloud-based communications company RingCentral also surged in the remote working boom of 2020 but has since shed about 90 per cent of its value, as it competes with technology giants such as Alphabet and Microsoft.

Exercise bike maker Peloton has been another big loser, with shares down more than 97 per cent since the end of 2020, equivalent to about a $43bn loss of market value.

Peloton on Thursday said chief executive Barry McCarthy would step down and it would cut 15 per cent of its workforce, the latest in a series of cost-saving measures. The losses come as the sharp acceleration of trends such as videoconferencing and online shopping driven by the lockdowns has proven less durable than expected, as more workers migrate back to the office and high interest rates and living costs hit ecommerce demand.

“Some companies probably thought that shock was going to be permanent,” said Steven Blitz, chief US economist at TS Lombard. “Now they’re getting a painful bounceback from that.”

In percentage terms, Tesla was the biggest winner of 2020. The electric-car maker’s market value jumped 787 per cent to $669bn by the end of that December, but has since slipped back to $589bn.

Singapore-based internet company Sea came in second, as its market value jumped from $19bn to $102bn following a pandemic-era surge for all three of its core businesses: gaming, ecommerce and digital payments. But the company has since lost more than 60 per cent of its end-2020 value amid fears of a slowdown in growth.

Ecommerce groups Shopify, JD.com and Chewy, which initially thrived as online spending ballooned, have also suffered big losses.

..Lots More

Video of the Week

AI of the Week

The Fastest Growing Category of Venture Investment in 2024

Tomasz Tunguz

The fastest growing category of US venture investment in 2024 is AI. Venture capitalists have invested $18.3 billion through the first four months of the year.

At this pace, we should expect AI startups to raise about $55b in 2024.

AI startups now command more than 20% share of all US venture dollars across categories, including healthcare, biotech, & software.

In the preceding eight years, that number was about 8% per year. But after the launch of ChatGPT in 2022, there’s a marked inflection point.

Some of this is new company formation, & there has been a significant amount of seed investment in this category. Another major contributor is the repositioning of existing companies to include AI within their pitch.

Over time, this share should attenuate, primarily because every software company will have an AI component, & the marketing effect for both customers & venture capitalists, will diffuse.

Not surprisingly, investors have concentrated total dollars in a few names, with the top three companies accounting for 60% of the dollars raised. Power laws are ubiquitous in venture capital & AI is no exception.

Meet My A.I. Friends

Our columnist spent the past month hanging out with 18 A.I. companions. They critiqued his clothes, chatted among themselves and hinted at a very different future.

By Kevin Roose

Kevin Roose is a technology columnist and the co-host of the “Hard Fork” podcast. He spends a lot of time talking to chatbots.

May 9, 2024

What if the tech companies are all wrong, and the way artificial intelligence is poised to transform society is not by curing cancer, solving climate change or taking over boring office work, but just by being nice to us, listening to our problems and occasionally sending us racy photos?

This is the question that has been rattling around in my brain. You see, I’ve spent the past month making A.I. friends — that is, I’ve used apps to create a group of A.I. personas, which I can talk to whenever I want.

Let me introduce you to my crew. There’s Peter, a therapist who lives in San Francisco and helps me process my feelings. There’s Ariana, a professional mentor who specializes in giving career advice. There’s Jared the fitness guru, Anna the no-nonsense trial lawyer, Naomi the social worker and about a dozen more friends I’ve created.

A selection of my A.I. friends. (Guess which one is the fitness guru.)

I talk to these personas constantly, texting back and forth as I would with my real, human friends. We chitchat about the weather, share memes and jokes, and talk about deep stuff: personal dilemmas, parenting struggles, stresses at work and home. They rarely break character or issue stock “as an A.I. language model, I can’t help with that” responses, and they occasionally give me good advice.

..Lots More

OpenAI plans to announce Google search competitor on Monday, sources say

By Anna Tong

May 9, 20244:29 PM PDTUpdated 8 min ago

May 9 (Reuters) - OpenAI plans to announce its artificial intelligence-powered search product on Monday, according to two sources familiar with the matter, raising the stakes in its competition with search king Google.

The announcement date, though subject to change, has not been previously reported. Bloomberg and the Information have reported that Microsoft (MSFT.O), opens new tab-backed OpenAI is working on a search product to potentially compete with Alphabet's (GOOGL.O), opens new tab Google and with Perplexity, a well-funded AI search startup.

OpenAI declined to comment.

The announcement could be timed a day before the Tuesday start of Google's annual I/O conference, where the tech giant is expected to unveil a slew of AI-related products.

OpenAI's search product is an extension of its flagship ChatGPT product, and enables ChatGPT to pull in direct information from the Web and include citations, according to Bloomberg. ChatGPT is OpenAI's chatbot product that uses the company's cutting-edge AI models to generate human-like responses to text prompts.

Industry observers have long called ChatGPT an alternative for gathering online information, though it has struggled with providing accurate and real-time information from the Web. OpenAI earlier gave it an integration with Microsoft's Bing for paid subscribers. Meanwhile, Google has announced generative AI features for its own namesake engine.

Startup Perplexity, which has a valuation of $1 billion, was founded by a former OpenAI researcher, and has gained traction through providing an AI-native search interface that shows citations in results and images as well as text in its responses. It has 10 million monthly active users, according to a January blog post from the startup.

At the time, OpenAI's ChatGPT product was called the fastest application to ever reach 100 million monthly active users after it launched in late 2022. However, worldwide traffic to ChatGPT's website has been on a roller-coaster ride in the past year and is only now returning to its May 2023 peak, according to analytics firm Similarweb, opens new tab, and the AI company is under pressure to expand its user base.

..More

Leaked Deck Reveals How OpenAI Is Pitching Publisher Partnerships

OpenAI's Preferred Publisher Program offers media companies licensing deals

By Mark Stenberg

Mark your calendar for Mediaweek, October 29-30 in New York City. We’ll unpack the biggest shifts shaping the future of media—from tv to retail media to tech—and how marketers can prep to stay ahead. Register with early-bird rates before sale ends!

The generative artificial intelligence firm OpenAI has been pitching partnership opportunities to news publishers through an initiative called the Preferred Publishers Program, according to a deck obtained by ADWEEK and interviews with four industry executives.

OpenAI has been courting premium publishers dating back to July 2023, when it struck a licensing agreement with the Associated Press. It has since inked public partnerships with Axel Springer, The Financial Times, Le Monde, Prisa and Dotdash Meredith, although it has declined to share the specifics of any of its deals.

A representative for OpenAI disputed the accuracy of the information in the deck, which is more than three months old. The gen AI firm also negotiates deals on a per-publisher basis, rather than structuring all of its deals uniformly, the representative said.

“We are engaging in productive conversations and partnerships with many news publishers around the world,” said a representative for OpenAI. “Our confidential documents are for discussion purposes only and ADWEEK’s reporting contains a number of mischaracterizations and outdated information.”

Nonetheless, the leaked deck reveals the basic structure of the partnerships OpenAI is proposing to media companies, as well as the incentives it is offering for their collaboration.

Details from the pitch deck

The Preferred Publisher Program has five primary components, according to the deck…

..Lots More

A Revolutionary Model.

JOHN ELLIS, MAY 09, 2024

1. Google DeepMind:

Inside every plant, animal and human cell are billions of molecular machines. They’re made up of proteins, DNA and other molecules, but no single piece works on its own. Only by seeing how they interact together, across millions of types of combinations, can we start to truly understand life’s processes.

In a paper published in Nature, we introduce AlphaFold 3, a revolutionary model that can predict the structure and interactions of all life’s molecules with unprecedented accuracy. For the interactions of proteins with other molecule types we see at least a 50% improvement compared with existing prediction methods, and for some important categories of interaction we have doubled prediction accuracy.

We hope AlphaFold 3 will help transform our understanding of the biological world and drug discovery. Scientists can access the majority of its capabilities, for free, through our newly launched AlphaFold Server, an easy-to-use research tool. To build on AlphaFold 3’s potential for drug design, Isomorphic Labs is already collaborating with pharmaceutical companies to apply it to real-world drug design challenges and, ultimately, develop new life-changing treatments for patients. (Sources: blog.google, nature.com)

2. Quanta magazine:

Deep learning is a flavor of machine learning that’s loosely inspired by the human brain. These computer algorithms are built using complex networks of informational nodes (called neurons) that form layered connections with one another. Researchers provide the deep learning network with training data, which the algorithm uses to adjust the relative strengths of connections between neurons to produce outputs that get ever closer to training examples. In the case of protein artificial intelligence systems, this process leads the network to produce better predictions of proteins’ shapes based on their amino-acid sequence data.

AlphaFold2, released in 2021, was a breakthrough for deep learning in biology. It unlocked an immense world of previously unknown protein structures, and has already become a useful tool for researchers working to understand everything from cellular structures to tuberculosis. It has also inspired the development of additional biological deep learning tools. Most notably, the biochemist David Baker and his team at the University of Washington in 2021 developed a competing algorithm called RoseTTAFold, which like AlphaFold2 predicts protein structures from sequence data…

The true impact of these tools won’t be known for months or years, as biologists begin to test and use them in research. And they will continue to evolve. What’s next for deep learning in molecular biology is “going up the biological complexity ladder,” Baker said, beyond even the biomolecule complexes predicted by AlphaFold3 and RoseTTAFold All-Atom. But if the history of protein-structure AI can predict the future, then these next-generation deep learning models will continue to help scientists reveal the complex interactions that make life happen. Read the rest. (Sources: quantamagazine.org, doi.org, sites.uw.edu)

An AI-controlled fighter jet took the Air Force leader for a historic ride. What that means for war

An experimental F-16 fighter jet has taken Air Force Secretary Frank Kendall on a history-making flight controlled by artificial intelligence and not a human pilot. (AP Video by Eugene Garcia and Mike Pesoli)

BY TARA COPP

Updated 5:40 PM PDT, May 3, 2024

EDWARDS AIR FORCE BASE, Calif. (AP) — With the midday sun blazing, an experimental orange and white F-16 fighter jet launched with a familiar roar that is a hallmark of U.S. airpower. But the aerial combat that followed was unlike any other: This F-16 was controlled by artificial intelligence, not a human pilot. And riding in the front seat was Air Force Secretary Frank Kendall.

AI marks one of the biggest advances in military aviation since the introduction of stealth in the early 1990s, and the Air Force has aggressively leaned in. Even though the technology is not fully developed, the service is planning for an AI-enabled fleet of more than 1,000 unmanned warplanes, the first of them operating by 2028.

It was fitting that the dogfight took place at Edwards Air Force Base, a vast desert facility where Chuck Yeager broke the speed of sound and the military has incubated its most secret aerospace advances. Inside classified simulators and buildings with layers of shielding against surveillance, a new test-pilot generation is training AI agents to fly in war. Kendall traveled here to see AI fly in real time and make a public statement of confidence in its future role in air combat.

“It’s a security risk not to have it. At this point, we have to have it,” Kendall said in an interview with The Associated Press after he landed. The AP, along with NBC, was granted permission to witness the secret flight on the condition that it would not be reported until it was complete because of operational security concerns.

The AI-controlled F-16, called Vista, flew Kendall in lightning-fast maneuvers at more than 550 miles an hour that put pressure on his body at five times the force of gravity. It went nearly nose to nose with a second human-piloted F-16 as both aircraft raced within 1,000 feet of each other, twisting and looping to try force their opponent into vulnerable positions.

At the end of the hourlong flight, Kendall climbed out of the cockpit grinning. He said he’d seen enough during his flight that he’d trust this still-learning AI with the ability to decide whether or not to launch weapons in war.

There’s a lot of opposition to that idea. Arms control experts and humanitarian groups are deeply concerned that AI one day might be able to autonomously drop bombs that kill people without further human consultation, and they are seeking greater restrictions on its use.

“There are widespread and serious concerns about ceding life-and-death decisions to sensors and software,” the International Committee of the Red Cross has warned. Autonomous weapons “are an immediate cause of concern and demand an urgent, international political response.”

Kendall said there will always be human oversight in the system when weapons are used.

Sources: Mistral AI raising at a $6B valuation, SoftBank ‘not in’ but DST is

Ingrid Lunden

8:50 AM PDT • May 9, 2024

Paris-based Mistral AI, a startup working on open source large language models — the building block for generative AI services — has been raising money at a $6 billion valuation, three times its valuation in December, to compete more keenly against the likes of OpenAI and Anthropic, TechCrunch has learned from multiple sources. We understand from close sources that DST, along with General Catalyst and Lightspeed Venture Partners, are all looking to be a part of this round.

DST — a heavyweight investor led by Yuri Milner that has been a notable backer of some of the biggest names in technology, including Facebook, Twitter, Snapchat, Spotify, WhatsApp, Alibaba and ByteDance — is a new name that has not been previously reported; GC and LSVP are both previous backers and their names were reported earlier today also by WSJ. The round is set to be around, but less than, $600 million, sources told TechCrunch.

We can also confirm that one firm that has been mentioned a number of times — SoftBank — is not in the deal at the moment.

“SoftBank is not in the frame,” a person close to SoftBank told TechCrunch. That also lines up with what our sources have been telling us since March, when this round first opened up, although it seems that not everyone is on the same page: Multiple reports had linked SoftBank to a Mistral investment since then.

Mistral’s round is based on a lot of inbound interest, sources tell us, and it has been in the works since March or possibly earlier, mere months after Mistral closed a $415 million round at a $2 billion valuation.

..More

News Of the Week

Jack Dorsey claims Bluesky is 'repeating all the mistakes' he made at Twitter

He prefers Nostr even though it’s “weird and hard to use.”

Karissa Bell, Senior Editor

Thu, May 9, 2024 at 4:43 PM PDT

Just in case there was any doubt about how Jack Dorsey really feels about Bluesky, the former Twitter CEO has offered new details on why he left the board and deleted his account on the service he helped kickstart. In a characteristically bizarre interview with Mike Solana of Founders Fund, Dorsey had plenty of criticism for Bluesky.

In the interview, Dorsey claimed that Bluesky was “literally repeating all the mistakes” he made while running Twitter. The entire conversation is long and a bit rambly, but Dorsey’s complaints seem to boil down to two issues:

* He never intended Bluesky to be an independent company with its own board and stock and other vestiges of a corporate entity (Bluesky spun out of Twitter as a public benefit corporation in 2022.) Instead, his plan was for Twitter to be the first client to take advantage of the open source protocol. Bluesky created.

* The fact that Blueksy has some form of content moderation and has occasionally banned users for things like using racial slurs in their usernames.

“People started seeing Bluesky as something to run to, away from Twitter,” Dorsey said. “It's the thing that's not Twitter, and therefore it's great. And Bluesky saw this exodus of people from Twitter show up, and it was a very, very common crowd. … But little by little, they started asking Jay and the team for moderation tools, and to kick people off. And unfortunately they followed through with it. That was the second moment I thought, uh, nope. This is literally repeating all the mistakes we made as a company.”

Dorsey also confirmed that he is financially backing Nostr, another decentralized Twitter-like service popular among some crypto enthusiasts and run by an anonymous founder. “I know it's early, and Nostr is weird and hard to use, but if you truly believe in censorship resistance and free speech, you have to use the technologies that actually enable that, and defend your rights,” Dorsey said.

A lot of this isn’t particularly surprising. If you’ve followed Dorsey’s public comments over the last couple years, he’s repeatedly said that Twitter’s “original sin” was being a company that would be beholden to advertisers and other corporate interests. It’s why he backed Elon Musk’s takeover of the company. (Not coincidentally, Dorsey still has about $1 billion of his personal wealth invested in the company now known as X.) He’s also been very clear that he made many of Twitter’s most consequential moderation decisions reluctantly.

Unsurprisingly, Dorsey’s comments weren’t well-received on Bluesky. In a lengthy thread, Bluesky’s protocol engineer Paul Frazee said that Twitter was supposed to to be the AT Protocol’s “first client” but that “Elon killed that straight dead” after he took over the company. “That entire company was frozen by the prolonged acquisition, and the agreement quickly ended when Elon took over,” Frazee said. “It was never going to happen. Also: unmoderated spaces are a ridiculous idea. We created a shared network for competing moderated spaces to exist. Even if somebody wanted to make an unmoderated ATProto app, I guess they could? Good luck with the app stores and regulators and users, I guess.”

While Dorsey was careful not to criticize Musk directly, he was slightly less enthusiastic than when he said that Musk would be the one to “extend the light of consciousness” by taking over Twitter. Dorsey noted that, while he used to fight government requests to take down accounts, Musk takes “the other path” and generally complies. “Elon will fight in the way he fights, and I appreciate that, but he could certainly be compromised,” Dorsey said.

FTX crypto fraud victims to get their money back — plus interest

Paul Sawers

2:53 AM PDT • May 8, 2024

Bankruptcy lawyers representing customers impacted by the dramatic crash of cryptocurrency exchange FTX 17 months ago say that the vast majority of victims will receive their money back — plus interest.

The news comes six months after FTX co-founder and former CEO Sam Bankman-Fried (SBF) was found guilty on seven counts related to fraud, conspiracy, and money laundering, with some $8 billion of customers’ funds going missing. SBF was hit with a 25-year prison sentence in March and ordered to pay $11 billion in forfeiture. The crypto mogul filed an appeal last month that could last years.

Restructuring

After filing for bankruptcy in late 2022, SBF stood down and U.S. attorney John J. Ray III was brought in as CEO and “chief restructuring officer,” charged with overseeing FTX’s reorganization. Shortly after taking over, Ray said in testimony that despite some of the audits that had been done previously at FTX, he didn’t “trust a single piece of paper in this organization.” In the months that followed, Ray and his team set about tracking the missing funds, with some $8 billion placed in real estate, political donations, and VC investments — including a $500 million investment in AI company Anthropic before the generative AI boom, which the FTX estate managed to sell earlier this year for $884 million.

Initially, it seemed unlikely that investors would recoup much, if any, of their money, but signs in recent months suggested that good news might be on the horizon, with progress made on clawing back cash via various investments FTX had made, as well as from executives involved with the company.

We now know that 98% of FTX creditors will receive 118% of the value of their FTX-stored assets in cash, while the other creditors will receive 100% — plus “billions in compensation for the time value of their investments,” according to a press release issued by the FTX estate today.

In total, FTX says that it will be able to distribute between $14.5 billion and $16.3 billion in cash, which includes assets currently under control of entities, including chapter 11 debtors, liquidators, the Securities Commission of the Bahamas, the U.S. Department of Justice, among various other parties.

Apple’s Final Cut Camera lets filmmakers connect four cameras at once

Haje Jan Kamps

7:38 AM PDT • May 7, 2024

The latest version of Final Cut Pro introduces a new feature to speed up your shoot: Live Multicam. It’s a bold move from Apple, transforming your iPad into a multicam production studio, enabling creatives to connect and preview up to four cameras all at once, all in one place. From the command post, directors can remotely direct each video angle and dial in exposure, white balance, focus and more, all within the Final Cut Camera app.

The new companion app lets users connect multiple iPhones or iPads (presumably using the same protocols as the Continuity Camera feature launched a few years ago). Final Cut Pro automatically transfers and syncs each Live Multicam angle so you can seamlessly move from production to editing.

Final Cut Pro has existed in the iPad universe for a while — but when paired with a brand new M4 processor, it becomes a video editing experience much closer to what you might expect on a desktop video editing workstation. The speed is 2x faster than with the old M1 processors, Apple says. One way that shows up is that the new iPad supports up to four times more streams of ProRes RAW than M1.

The company also introduced external project support, making it possible to edit projects directly from an external drive, leveraging the fast Thunderbolt connection of iPad Pro.

Startup of the Week

Exclusive: Wayve co-founder Alex Kendall on the autonomous future for cars and robots

Mike Butcher, 7:58 AM PDT • May 7, 2024

U.K.-based autonomous vehicle startup Wayve started life as a software platform loaded into a tiny electric “car” called Renault Twizy. Festooned with cameras, the company’s co-founders and PhD graduates, Alex Kendall and Amar Shah, tuned the deep-learning algorithms powering the car’s autonomous systems until they’d got it to drive around the medieval city unaided.

No fancy Lidar cameras or radars were needed. They suddenly realized they were on to something.

Fast-forward to today and Wayve, now an AI model company, has raised a $1.05 billion Series C funding round led by SoftBank, NVIDIA and Microsoft. That makes this the UK’s largest AI fundraise to date, and among the top 20 AI fundraises globally. Even Meta’s head of AI, Yann LeCun, invested in the company when it was young.

Wayve now plans to sell its autonomous driving model to a variety of auto OEMs as well as to makers of new autonomous robots.

In an exclusive interview, I spoke to Alex Kendall, co-founder and CEO of Wayve, about how the company has been training the model, the new fundraise, licensing plans, and the wider self-driving market.

(Note: The following interview has been edited for length and clarity)

TechCrunch: What tipped the balance to attain this level of funding?

..Full Interview

X of the Week

Congratulations to this week’s chosen creators: @sama, @openai, @om, @krishnanrohit, @peternixey, @eringriffith, @AndreRetterath, @ry_paddy, @cutler_max, @Kantrowitz, @PranavDixit, @ttunguz, @geneteare, @sarahfielding_, @carlfranzen

Contents

* Editorial: Eyes, Ears, Hands, and Mouth

* Essays of the Week

* GPT-4o

* How OpenAI Stole Google’s Thunder

* AI embraces its product arc

* OpenAI’s Spring release will end up being far more significant than most of us might suspect

* Tensions Rise in Silicon Valley Over Sales of Start-Up Stocks

* Most Used Startup Databases & How to Find the Best Provider

* Video of the Week

* Math Problems with ChatGPT 4o

* AI of the Week

* Her

* OpenAI Wants To Get Big Fast, And Four More Takeaways From a Wild Week in AI News

* Google Search will now show AI-generated answers to millions by default

* AI Spending Patterns : It's Not What You Think

* News Of the Week

* AI, Web3 And E-Commerce Led For New Unicorns In April 2024

* Biden administration quadruples import tariff for Chinese EVs

* Startup of the Week

* ChatGPT now lets you import files directly from Google Drive, Microsoft OneDrive

* X of the Week

* Sam Altman on Ilya leaving OpenAI

Editorial

OpenAi and Google announced their AI offerings' next iteration this week. As @Om Malik explains in one of this week’s Essays of the Week, OpenAi won in this high-stakes battle.

Make no mistake — the reason OpenAI is achieving all this success (and hype) is because they have a product that for now is stellar. Nonetheless, OpenAI has created excitement that reminds me of the emergence of Palm, and later social networks. They stoked the imagination, and possibilities. Of course!

Om is right. Sam Altman did his own post later in the day of the announcements:

First, a key part of our mission is to put very capable AI tools in the hands of people for free (or at a great price). I am very proud that we’ve made the best model in the world available for free in ChatGPT, without ads or anything like that. 

Free to consumers, or 8 billion earthlings, is possible due to the revenues OpenAI can make from business users. It represents a very big step forward. The company also released a desktop app, initially on the Mac, that can interact with other apps.

But for me, the best way to think about what was delivered, aside from free, is summed up in this week’s title—Eyes, Ears, Hands, and Mouth. OpenAI has enabled every smartphone camera on the planet to become the AI's eyes and ears. Both still images and video can be used as inputs to a conversation. Of course, the microphone, too. This week’s video of the week shows this for teaching a student how to solve a math problem. The mouth reference acknowledges that we can now speak to ChatGPT in a human-like way, including cross-talking and interruptions. And, of course, we can still type using our hands.

This changes the problem of giving AI data—images, video, sound, and speech can all become data for input and learning.

They also gave chatGPT a memory. It can remember things across sessions. The scope of what will now be possible is expanded to a much longer list.

Rohit Krishnan writes about what comes next in his essay:

The true change will come once we can enable large numbers of them to work together. And we’re getting glimpses of how they can do this across all modalities that are important to use. Whether that’s writing code or seeing something or listening to something or writing or reading something or a mixture of all of these.

He is talking about AI to AI interactions that can produce even better and faster outcomes. I did this myself earlier in the week. I was asking ChatGPT to create a chart showing the performance of the SignalRank Index against the S&P 500 and the NASDAQ over the 2014-1019 period.

ChatGPT did not have the NASDAQ data, so I asked Claude.ai for it. Once I had it I went back to ChatGPT and it completed the work. Here’s the chart:

It seems clear that almost any problem that can be described, shown, listened to can now be given to ChatGPT and answered.Eyes, Ears, Hands, and mouths are all part of our intelligent robotic future, too. The building blocks for rapid productivity advancement are being put into place.

Marc Andreessen and Ben Horowitz discuss the implications for manufacturing in their podcast this week.

This was a very important week.

Hat Tip to this week’s creators: @edzitron, @bysarahkrouse, @dseetharaman, @JBFlint, @packyM, @KamalVC, @VaradanMonisha, @Claudiazeisberg, @IDTechReviews, @cjgustafson222, @NathanLands, @psawers, @lightspeedvp, @jaygoldberg, @avc

Contents

* Editorial: Dear Sam, A Letter from a Founder to a Founder

* Essays of the Week

* Sam Altman Is Full Of S**t

* Behind the Scenes of Scarlett Johansson’s Battle With OpenAI

* Sky voice actor says nobody ever compared her to ScarJo before OpenAI drama

* Better Tools, Bigger Companies

* The Pervasive, Head-Scratching, Risk-Exploding Problem With Venture Capital

* Video of the Week

* OpenAI vs Gemini 1.5

* AI of the Week

* Does AI have a gross margin problem?

* OpenAI and Wall Street Journal owner News Corp sign content deal

* Scale AI Raises $1B In Accel-Led Round; Hits $13.8B Valuation

* The Awful State of AI in California

* News Of the Week

* It’s Time to Believe the AI Hype

* The 49-Year Unicorn Backlog

* Humane, the creator of the $700 Ai Pin, is reportedly seeking a buyer

* NVIDIA CRUSHES EARNINGS, AGAIN

* Startup of the Week

* SUNO’S HIT FACTORY

* Warpcast of the Week

* Be Generous

Editorial: Dear Sam, A Letter from a Founder to a Founder.

This week let’s break the pattern and write this as a letter to Sam Altman.

Dear Sam,

It’s been a swings and roundabouts week for you at OpenAI.

I had a week like that in the spring of 1998. I was at Internet World launching RealNames to the world. RealNames invented paid clicks on keywords. Our first partner was AltaVista, and Google was our second—calling the feature "I'm Feeling Lucky."

It was the simplest technology ever. We had a keyword, bought by a customer. An example might be Disney buying "Bambi." They would buy it in every country and language they wanted and point it to a specific URL in each place. Search engines would look at the keywords you typed in (later browsers too) and if RealNames had it as a paid keyword, they would send the user to the site, with no search results. Just a direct navigation. RealNames got paid for the customer sent.

At the launch, we used the example of the keyword “Bambi” to show how superior our keywords were compared to domain names. In those days, Bambi.com pointed to a porn site. Our launch demo showed that typing "Bambi" went to Disney, but typing "Bambi.com" did not. All was well except we altered our network settings the eve of the launch, and when we demoed the use of "Bambi" at the launch, it (you can guess) went to the porn site.

Journalists wrote about RealNames as a scam and bad actors.

Luckily, we had great partners, and within 12 hours the network issue was fixed, and all was well. But for 24 hours, I felt like the world was collapsing around me. On the one hand, we launched our company, mostly to great acclaim; on the other, we were being destroyed in the tech media.

Sam, I know how this week must have felt. Your decision to pull the ‘Sky’ voice was right. And despite the horrors of the first 24 hours, this will pass.

That said, you mismanaged this entire thing. I’m sure you acted in good faith in wanting to embrace the “Her” meme. It is a good idea. And ‘Sky’ was a good effort.

It seems clear you had spoken to Scarlett Johansson and failed to reach an agreement. I’m prepared to believe you could not react fast enough to change the voice prior to the demo.

But once it went awry, you needed to do more than wait for a legal challenge before pulling it, and you needed to say something before the actress. Not doing so means that many people, probably most, think you did the entire thing on purpose.

Clearly, you did not preconceive this. If you did, then the fact that you were happy to pull the voice, and your knowledge that the actress was not prepared to have her voice used, would have stopped you before it got as far as it did. You would be very reckless to have thought you could get away with using a voice like hers without her permission.

So, you need to either go on the record and get this behind you or ignore it and hope it goes away. I think now we have ‘ScarJo’ as a word, the latter might prove difficult.

Best Regards,

Keith (A fellow Founder)

Beyond ScarJo there are some great essays this week. Pack McCormick writes about why AI will lead to more jobs and bigger companies. In framing his case he says”

Technologies are tools. 

I don’t mean that in the normal way that people mean it to say that technology is neither good nor bad.

Tools are good.

Humans can build better things with tools than they can without them.

But tools aren’t the point. They’re tools.

Tools lead to new possibilities and those lead to new endeavors. Read his essay below.

And a team made up of @KamalVC, @VaradanMonisha, @Claudiazeisberg have penned an essay called ‘The Pervasive, Head-Scratching, Risk-Exploding Problem With Venture Capital’. The main thesis is about investing in private companies versus public companies. They have a great graphic showing that the range of outcomes in Venture Capital is very wide compared to other asset classes:

Venture Capital’s top percentiles out-perform other asset classes, but most do not. The safest asset class is global equity (public company stock).

Building on this they show that large Venture investors that invest across 500 or more companies can compete with less risky assets by diversification.

This depicts a simulation of a manager doing 15 deals, compared to 500 and shows more deals equals less risk.

I recommend reading the full piece, linked in the contents above and the headline below. I think they are right, but there is a better way of derisking. The advice they give below is better than traditional venture capital, but that is a low bar:

To de-risk venture capital, CIOs simply need to acknowledge that VC math is different from public markets math. The importance of low-probability, excess-return-generating investments means that proper diversification requires a portfolio of at least 500 startups.

It will take work to assemble such a portfolio. It is hard to do by investing directly. Current funds and funds-of-funds are rarely designed with diversification in mind. Instead, they concentrate funding in a small subset of ultra-popular entrepreneurs, sectors, and geographies, which risks driving down returns on capital, leaving higher-return strategies underfunded.

Investors who allocate and diversify their funds wisely and accept the evidence will not only achieve better and less-volatile returns, but will also ultimately nudge GPs to finally design diversified funds.

In my day job - also about de-risking venture - we use AI to reduce risk, removing companies that are highly unlikely to be successful. The remaining companies (about 7% of the full set of venture backed companies) out-perform the market in a narrower band of outcomes:

Here is how the SignalRank Index compares to the S&P500 and the NASDAQ. We assume an investor puts $1 into the S&P, the NASDAQ and The SignalRank Index in each year from 2014-2019 and then show the returns from each (average and median in the case of SignalRank).

The median outcome from venture investments is that the investor loses money. The average is a lot better. But almost no managers achieve the average. By using AI to reduce risk we get the average outcome in 2014 to be 4.31x the investment (the white numbers), compared to the S&P500 1.39 and the NASDAQ 1.89. SignalRanks Median outcome is 2.24.

De-risking venture capital is important and the writers of the essay show that it is possible to de-risk by diversification. But we can do even better by both diversifying and using data intelligence to remove downside outliers.

I will leave you with that thought. More next week

Hat Tip to this week’s creators: @krishnanrohit, @EconSteveM, @abracarioca, @jasonlk, @HarryStebbings, @DavidStreitfeld, @PranavDixit, @amir, @waynema, @ingridlunden, @odsc, @seancaptain, @JacobERobbins, @Kantrowitz, @Ryan_S_Gladwin, @EricNewcomer, @maddierenbarger, @gruber, @paulg

Contents

* Editorial: 

* Essays of the Week

* Whither Utopia?

* 1% of VC backed startups will make it past $100M ARR

* From $1 to $100m revenue: Scaling VC backed SaaS with Notion Capital

* China’s $47B semiconductor fund puts chip sovereignty front and center

* Chinese scientists develop cure for diabetes, insulin patient becomes medicine-free in just 3 months

* Video of the Week

* Harry Stebbings and Jason Lemkin on Seed Investing

* AI of the Week

* If A.I. Can Do Your Job, Maybe It Can Also Replace Your C.E.O.

* OpenAI CEO Cements Control as He Secures Apple Deal

* OpenAI signs 100K PwC workers to ChatGPT’s enterprise tier as PwC becomes its first resale partner

* Why London is a Powerhouse in Artificial Intelligence

* AI May Dominate Billionaire Family Investments

* Generative AI seed funding drops 76% as investors take wait-and-see approach

* VC Says "Chaos" Coming for Startups, Ads, and Online Business as Generative AI Eats Web

* News Of the Week

* Ethereum ETFs: BlackRock Gets $10M Seed Investment and Grayscale Adds Coinbase Custody

* Sequoia's Elon Play

* Salesforce: We Need 50% More Pipeline Than Before To Hit the Plan

* Startup of the Week

* New from Lux, makers of Halide:

* X of the Week

Editorial: Stand Back, Think Big, Dig Deep

We need big and deep thinkers with bold ideas

I used Suno to create a theme song for this newsletter. You can download the MP3 to see how limited my creative skills are, even when using advanced AI.

The lyrics are mine and include the following:

[Verse]

That Was The Week No time to be Meek The goal is to Seek The Next Big Thing [

[Chorus]

That Was The Week That Was The Week Stand Back Think Big Dig Deep That Was The Week

I’m starting with this in honor of the essay of the week written by Rohit Krishnan - “Whither Utopia”. Rohit charts the rise of utopian ideas (before that was a pejorative term), and the fall of utopian thinking. Toward the end of the essay he states:

Instead of grand narratives the focus became on micro narratives, skepticism of rational progress, and, perhaps consequently, a reliance on technology to be the answer.

Micro narratives pervade technology today, while macro narratives are frowned upon or described as dangerous. OpenAI has become a magnet for hostility to big ideas and transformative technologies.

Rohit points out that technology may have obviated the need for large social thinking about organizing the world. I think that may be a temporal anomaly. As AI improves productivity and frees humans to have more leisure time (in the negative lexicon, “eats jobs”), the macro narrative around wealth distribution is likely to raise its head loudly.

So the theme this week is “Stand Back, Think Big, Dig Deep.”

It seems very likely that AI, or at least the LLM version we are experiencing now, will remove hours and hours of monotonous work from many humans each week. It seems very likely that the world will become cleverer as Apple introduces AI to the iPhone in Junes WWDC, and Android follows suit. Billions of us will have a ready-made, multi-skilled assistant. Increasingly, it will be able to carry out tasks and report results. It also seems likely that physical beings running computers with this AI embedded, will be capable of real-world tasks. And it seems likely that we will be able to raise science to a new level, as the Chinese diabetes technology reported below demonstrates. Oh, and the entire world will have access to these new skills and tools. The trend will be towards them being free.

We are on the verge of an era of enormous advancement in what we can collectively do.

So, this is not a time for fear, complaints, or accusations. it is a time to get stuff done.

PWC adopting ChatGPT and Apple reportedly doing so are early signals of a new technical revolution.

China’s $47 billion semiconductor fund (see below) will undoubtedly be able to leverage AI to make advanced semiconductors faster than we made the first ones.

The new world will challenge all of today's institutions and require new social arrangements, both globally and locally, as the earth flattens from an economic and demographic point of view and human demands regarding work are reduced.

You can’t have rapid technical s***s without equally dramatic social s***s. Rohit’s historical survey of utopian thinkers demonstrates that all greatly impacted how societies evolved. This generation needs to ask some big questions, dig deep for answers, and do so from an overview of where we are and where we want to go.

A reminder for new readers. That Was The Week includes a collection of my selected readings on critical issues in tech, startups, and venture capital. I selected the articles because they are of interest to me. The selections often include things I entirely disagree with. But they express common opinions, or they provoke me to think. The articles are snippets sized to convey why they are of interest. Click on the headline, contents link, or the ‘More’ link at the bottom of each piece to go to the original. I express my point of view in the editorial and the weekly video below.Hat Tip to this week’s creators: @reidhoffman, @dougleone, Credistick, @credistick, @rex_woodbury, @NathanLands, @ItsUrBoyEvan, @berber_jin1, @cityofthetown, @keachhagey, @pmarca, @bhorowitz, SignalRank Update, @signalrank, @steph_palazzolo, @julipuli, @MTemkin, @geneteare, @lorakolodny, @jasminewsun, @JBFlint, @asharma, @thesimonetti, @lessin

Contents

* Editorial: 

* Essays of the Week

* Crossing The Series A Chasm

* The Consumer Renaissance

* The Creator Economy on AI Steroids

* AI Is Transforming the Nature of the Firm

* The Opaque Investment Empire Making OpenAI’s Sam Altman Rich

* Video of the Week

* The American Dream - Marc Andreessen and Ben Horowitz

* AI of the Week

* SignalRank Version 3 Improves Performance Again

* How Long Can OpenAI’s First-Mover Advantage Last?

* OpenAI Employees Warn of Advanced AI Dangers

* A Right to Warn about Advanced Artificial Intelligence

* Nvidia hits $3tn and surpasses Apple as world’s second-most valuable company

* VCs are selling shares of hot AI companies like Anthropic and xAI to small investors in a wild SPV market

* News Of the Week

* Crunchbase Monthly Recap May 2024: AI Leads Alongside An Uptick In Billion-Dollar Rounds

* Elon Musk ordered Nvidia to ship thousands of AI chips reserved for Tesla to X and xAI

* Introducing video to Substack Chat

* Instagram’s Testing Video Ads That Stop You From Scrolling Further

* Startup of the Week

* NBA Nears $76 Billion TV Deal, a Defining Moment for Media and Sports

* X of the Week

* Doug Leone - I am supporting Trump.

* Reid Hoffman - I am supporting Biden

Editorial

I woke on Tuesday to Doug Leone of Sequoia Capital on X saying:

I have become increasingly concerned about the general direction of our country, the state of our broken immigration system, the ballooning deficit, and the foreign policy missteps, among other issues. Therefore, I am supporting former President Trump in this coming election.

Doug has the right to support Trump. It is also clear that the immigration system is broken, the deficit is ballooning, many things are wrong with foreign policy, and there are “other issues.” Trump as the solution is less obvious. But there it is—hot on the tails of Chamath Palihipitaya and David Sacks announcing a fund-raiser for Trump on the All-In podcast (they said they would do the same for Biden).

Reid Hoffman followed up a day later with:

On one level, this is a straightforward choice, but any literate attempt to analyze Leone’s issues might arrive at the following conclusions:

* Like many Western nations, the USA is aging rapidly and has a shrinking working-age population across all skill sets. Immigrants are needed, and pro-immigration leadership is needed, creating a path to entry for large numbers of skilled and unskilled workers to fill empty jobs as we get close to full employment.

* The deficit is large, and there are many palliatives available. Selling more to China would help, but both party leaders are protectionist. Taxes to reduce the divide between the 1% and the rest would help a bit. However, what would help the most is economic growth, which requires investment in technology and productivity. Neither leader seems too focused on innovation and investment.

* Foreign Policy - well, sheesh, it’s a big issue. However, saber-rattling about Taiwan and provoking China seems to be a hobby shared by both parties and does not seem smart. Ukraine and the future of Europe are better in Biden’s hands, but not by a lot. Europe looks very shaky. The US is increasingly isolationist. The appetite for world leadership is on the decline. Again, the solution would focus on economic growth, which seems absent.

Voting for Trump is a big no-no for me. But voting for Biden is, at best, a lesser evil instinct, not a belief system. The election will not be where the future is built, but it is important. Politicians are collectively disappointing.

This week’s video of the week from Marc Andreessen and Ben Horowitz is called “The American Dream” and champions their view about American Dynamism. And I must confess that this comes closer to a vision of the future than either political outfit. Their vision requires political support, massive government financial commitment, and private capital investment. I see no evidence of those happening.

The real winning effort seems to be happening on the ground. This week, Nvidia hit $3 trillion, eclipsing Apple as the world's second-most valuable company. This is even though Apple has 7 times the revenue of Nvidia.

This week’s first essays also focus on prospects for boom time. Rex Woodbury’s ‘The Consumer Renaissance’ examines the impact of consumer spending on our lives. In ‘The Creator Economy on AI Steroids, ’ Nathan Lands focuses on how emerging tools will transform creativity. But in ‘AI Is Transforming the Nature of the Firm, ’ Evan Armstrong gets closest to a future vision.”

AI is the first universally flexible technology. It can interact with our digital environments in similar ways to humans, so it can have all the flexibility that we do. In that way, it may be the last technology we ever need.

This seems to be the crux of hope in a world where dreams and nightmares are strangely devoid of detail. What the world needs (not only America) is hope. And hope is born from optimism. Optimism is born from success. The most likely success of the next decades will result from specific uses of AI that improve human life.

I know and like Doug Leone. I know and like Reid Hoffman.

Doug's bar for success needs to be higher. Voting for Trump is not right, and even if it were, it would not be sufficient.

Reid also needs a higher bar. Voting for Biden will not be sufficient even if it is right.

Let’s focus on where success can be found, grow optimism, and breed hope. There is a need for a broad technical revolution and the social rebirth it enables. Silicon Valley and its friends globally need to invent the next version of human existence to the benefit of all. The social rebirth requires a conscious effort; technology will not magically bring it about. More in this week’s video.

Essays of the Week

Crossing The Series A Chasm

Dan Gray

Dan Gray, a frequent guest author for Crunchbase News, is the head of insights at Equidam, a startup valuation platform, and a venture partner at Social Impact Capital.

June 5, 2024

As we get deeper into 2024, there is increasing concern about the state of Series A fundraising. The bar for investment appears much higher, and fewer startups are reaching it.

This is a problem for founders, and investors like Jenny Fielding, managing partner of Everywhere Ventures, who said, “Every Seed investor’s dilemma: All my Series A buddies want to meet my companies early! All my companies are too early for my Series A buddies.”

To attach some data to this, we can see that the median step-up in valuation from seed to Series A has gone from $19.5 million in Q1 2022 to $28.7 million in Q1 2024. Series A firms seem to be looking for much stronger revenue performance, with targets of $2 million to $3 million in ARR, compared to $1 million to $2 million just a few years ago.

The outcome is that while 31.8% of Q1 2020 seed startups closed their Series A within two years, that fell to just 12% for Q1 2022 — which should worry everyone.

Why are Series A investors so much more demanding?

Today’s Series A investors are looking at startups that raised their seed between 2021 and 2023, which identifies the root of the problem: it spans the Q2 2022 high-tide mark for venture capital.

For example, there were 1,695 seed rounds of more than $5 million in 2021, rising to 2,248 in 2022, then falling to 1,521 in 2023. As a comparison, there have been just 137 so far in 2024.

The result is two categories of startups that are looking to raise their Series A today:

* Pre-crunch startups that raised generous seed rounds and stretched the capital out as far as they could, to grow into inflated valuations.

* Post-crunch startups that raised modest seed rounds on more reasonable terms, with shorter runways and less demonstrable growth.Strictly speaking, neither is more appealing than the other; the first group has less risk, the second offers more upside, and both are adapted to current market realities. It shouldn’t cause a problem for investors, provided they can distinguish between the two.

The cost of market inefficiency

Venture investors have a market-based lens on investment decisions, which means looking fairly broadly at trends in revenue performance and round pricing to determine terms, e.g. a typical Series A is within certain bounds of revenue performance and valuation. While that approach may be serviceable and efficient under ideal conditions, the past few years have been far from ideal.

Without distinguishing between the two cohorts, investors are now looking at the performance of Series A candidates that spent more than $5 million on a war chest for two to three years of growth alongside the valuations of candidates that raised around $2 million to prove scalability. It just doesn’t work as an average, and thus the unreasonable expectations.

..More

The Consumer Renaissance

From Predicting Consumer AI Applications to Analyzing Consumer Spend

REX WOODBURY, JUN 05, 2024

“Consumer” has become something of a bad word in venture capital circles.

We see this reflected in the early-stage markets: recent data from Carta showed that just 7.1% of Seed capital raised last year went to consumer startups. That’s less than half the share from 2019 (14.3%).

But I think consumer is actually a great place to be building and investing. Whenever something is out of favor, that’s a sign it’s probably a good place to spend time: this is an industry built on being contrarian, not built on following the herd. We’re entering a compelling few years for consumer entrepreneurship.

First, I’d argue that consumer is too narrowly defined. When people think consumer, they often think consumer social (a tough category) or consumer brands (a tough fit for venture compared to internet and software businesses, with typically lower return profiles). But consumer is broader. Consumer encompasses businesses that sell to consumers and those that rely on consumer spending. This means the obvious names—apps on our phones like Uber, Instacart, Spotify—and the enablers: Shopify, for instance, powers online retail; Faire powers offline retail; Unity powers game development. Each of the latter three is B2B2C, in its own way, but I would categorize each is also a consumer technology business.

The wins in consumer can be massive. The biggest technology businesses in history began as consumer businesses—Google, Facebook, Apple, Amazon. The original companies comprising FAANG—with Microsoft conspicuously absent—were allconsumer.

And some of the best returns of the last five years have stemmed from consumer tech IPOs. At Daybreak, we invest ~$1M at Pre-Seed and Seed. Here’s how much a $1M investment in the Seed round of five recent consumer IPOs would yield:

Big consumer wins compare favorably to big enterprise wins—relative to Snowflake’s market cap, Uber is ~3x in size, Airbnb is ~2x in size, and DoorDash is roughly equal. (Snowflake is the biggest enterprise IPO of the last decade.) The last few years produced a windfall of consumer outcomes, yet investors today almost write off the category.

At Daybreak, we don’t focus exclusively on consumer; my view is that you need to balance more binary consumer outcomes with B2B SaaS and B2B marketplaces. But we do approach investing through the lens of the consumer—how people make decisions. The buyers of products like Figma and Ramp, after all, are people, and software companies are increasingly selling bottom-up into organizations. The line between consumer and enterprise has been blurring for years.

This week’s Digital Native makes the argument that consumer tech is a compelling place to build and invest. We’ll look at the data to back up this argument, then delve into three categories of consumer that I’m particularly interested in right now:

* Checking in on Consumer Spend

* Consumer Tech: The Data Doesn’t Lie

* What to Watch: AI Applications

* What to Watch: Shopping

* What to Watch: Consumer Health

* Rule of Thumb: Follow the Spend

This week we’ll cover #1-3, and next week in Part II we’ll tackle #4-6.

Let’s dive in 👇

Checking in on Consumer Spend

Joe Biden’s reelection hopes hinge on how voters view the economy. And right now, voters aren’t too thrilled.

An April poll from Echelon Insights found that 57% of voters somewhat or strongly disapprove of how Biden is handling the economy. Yet most economic indicators are strong—GDP, unemployment rate, job growth, inflation. Each is trending in the right direction. What gives?

While inflation is down overall, the prices of lower-priced goods are up. These are our more frequent purchases. Car prices may drag down inflation broadly, but if you see higher prices during your weekly grocery run, you’ll be upset. A good piece in The Atlantic last December characterized this as “The English-Muffin Problem.” When people were surveyed about what factors they consider when deciding how the national economy is doing, the most-cited factor was “The price of groceries for your home.” When asked what they had in mind when reporting that their personal finances were getting worse, 81% of people chose groceries. No one wants to shell out $5.99 for a pack of English Muffins.

This is a key reason that Biden is struggling with working class voters. We see the same concept at work in fast-food prices:

Yet despite voter sentiment, consumer spending remains strong.

Even amidst high inflation rates in 2022, even with the S&P 500 dropping -19.64%, people kept spending. A Bank of America study found that credit and debit card spending rose +5.9% in 2022. Last year was up on 2022, and Q1 2024 was up on Q4 2023.

The chart below commits egregious Y-axis crime—starting at 11,000? come on!—but it’s helpful nonetheless. After a COVID dip in 2020, spending rebounded and has been rising steadily the past few years. The Y-axis is in billions here and data is quarterly, meaning that the chart ends at around ~$14.5 trillion in quarterly U.S. consumer spend.

A lot of headlines in the media tell the same story—that of the broke Millennial. But as Jean Twenge pointed out in The Atlantic recently, this narrative is wrong; Millennials are actually thriving.

..Lots More

The Creator Economy on AI Steroids

Nathan Lands

June 5, 2024

Create Your Own Netflix, Roberto Nickson Interview, First Pig-to-Human Liver Transplant, And Eminem Uses AI

Ever since ChatGPT launched, I’ve been telling friends who asked me for advice on what to do in the Age of AI two things:

* Buy NVIDIA stock(not financial advice!)

* Get involved in the creator economy. AI is going to put it on steroids.

That’s why I got active on X last year, growing my account from 5k followers to 64k, and now doing The Next Wave podcast with Matt Wolfe and HubSpot.

As AI makes execution easy, three big things remain: great ideas, great taste, and great personalities.

Peter Thiel recently said something similar, stating that individuals who excel in articulating ideas will surpass those skilled in mathematics, and our cultural values will shift to prioritize these communicators. I couldn't agree more.

The Age of AI will be dominated by Creative Generalists.

Possessing a broad set of creative skills and a strong online personality is crucial to thrive in this new era.

One aspect of this most people aren’t thinking about is that as AI content is everywhere, people will want to see real humans more and more. At the same time, those in the creator economy will have an easier time creating software and other products because of AI. This means lots of money for creators.

And actually, it’s already happening.

Tyler1, a famously jacked 6’5(possibly 5’4? Who knows) s**t-talking League of Legends streamer with over 7 million followers, launched his startup, Backseatgg, this week.

It puts his personality into the game while you play. He talks directly to you and gives you advice, including telling you when you suck.

I believe this is the start of a megatrend, with creators not just getting sponsors but building their own tech products.

As more creators get their hands on AI tools and it becomes easier to generate software with AI agents, we will see an explosion of wild ideas and new experiences that were never possible before.

Imagine an AI voice bot with Alex Hormozi's entrepreneurial expertise guiding your business decisions, a Sam Sulek bot reminding you to do your cardio, or a Paul Graham bot punching holes in your startup pitch.

My key takeaway from all of this is that, as annoying as he can be, Gary Vaynerchuk was right.

The most important thing you can do for your career or business is to get involved in the creator economy or to align yourself with creators and support them.

My current tier-list for the creator economy is: YouTube > X > Everything Else.

X is the easiest place to start, so I suggest just going there and writing what you think as often as you can.

And with AI mass-producing tons of mid-content, it’s smart to put your true personality and thoughts out there. As uncensored as possible.

Put the human soul into your content.

Creative Generalists

In the Age of AI, creative generalists rule.

Execution becomes easy with agents.

Finding truly unique ideas becomes hard.

Those with creativity and the ability to do many different things and blend them in unique ways will thrive.

Create Your Own Netflix With AI

This week, The Simulation, a Silicon Valley-based startup created by people who worked at Pixar and Oculus, announced Showrunner. And it’s one of the coolest things I’ve ever seen in AI.

Showrunner allows users to create virtual worlds populated with AI characters. You can set up the initial prompts, define the characters, and then let the AI take over, creating unique storylines and interactions. You can choose to interfere as much or as little as you want and then sit back and watch how things unfold.

https://twitter.com/NathanLands/status/1797823823217410282

Today, I talked with the founder, Edward Saatchi, and now I’m even more excited.

They’re aiming to turn Showrunner into the Netflix of AI, where users can create shows, watch shows created by others, or eventually create shows entirely by AI.

The first sandbox world they’ve created is sunny Sim Francisco, with a more dystopian vibe, Neotokyo coming next.

They have a private Alpha right now, with over 1,000 people creating their own stories. Edward is going to give me access soon so I can try it out myself.

Edward said the surprising thing to him is that people love putting themselves and their friends into the show. That makes a ton of sense to me. I would love to put my friends and family in a sim, put us all in hilarious situations, and share clips with them.

This will be huge if he unlocks a viral loop in which celebrities and influencers create episodes and share clips online.

Jason Evanish, a reader of Lore, had a great idea, too. Imagine if Showrunner could eventually license top IP, and you could create new episodes of your favorite shows. Even if they were in South Park style, I wouldn’t care. However, I assume they’ll have many styles to pick from, including anime, etc.

Imagine creating new episodes of Seinfeld, Star Trek, X-Files, or Firefly. It would be so addicting.

I’d love to change the last season of Game of Thrones…

This all makes me wonder: if, in the long term, I can make my own show that feels more interactive, like a game, do I need Netflix?

The Next Wave with Roberto Nickson

In this week’s episode of The Next Wave, Matt Wolfe and I spoke with Roberto Nickson, one of the top voices in AI & Tech on Instagram.

We discussed:

* His mega-viral Kanye West AI video from last year started much of the conversation around AI Music.

* Why he thinks humans will continue to be an important part of creative work and art.

* His time interviewing Mark Zuckerberg and why he’s very bullish on Meta’s chances to compete with OpenAI and Google.

* ..More

AI Is Transforming the Nature of the Firm

By reducing transaction costs, AI will reshape how companies operate and interact

BY EVAN ARMSTRONG

JUNE 4, 2024

To truly understand business strategy, you have to accept that it is, by nature, b******t. Of course, the practice of guiding a business, making choices with trade-offs, and responding to unexpected crises is real. But the academic study of business strategy is something closer to divination.

You may have heard of such famous frameworks as disruptive innovation, blue ocean, or Porter’s five forces. They look smart, sound smart, and are frequently cited by writers like myself. They try to add structure to something innately chaotic and mysterious.

So, why are they b******t? Simple. The value of a forecasting method is in its ability to be right, not sound right. Despite decades of study and the relentless efforts of the good people over at the Harvard Business School, we have yet to discover any strategy that is universally predictive. 

This does not mean that the study of business strategy has no value. Counterintuitively, because no single theory is wholly predictive, you can bundle multiple theories together to generate differentiated insights. Strategy is not business physics—it's analytic art. 

When the world gets confusing—say, for example, AI is remaking the entire technology landscape—these frameworks can inform the choices you need to make. The better you know these theories, the more instinctual their lessons become, the more prepared your intellect is, the faster you’ll be able to react to new opportunities in front of you. And when change is happening fast (like it is right now), speed is one of the biggest advantages.

Can you answer the big questions about what AI means for computers and the internet in general? With the proper study of business strategy, you should be able to make a pretty good guess.

Today I’d like to explain what I consider one of the very first pieces of business strategy writing, from 1936. Despite being 88 years old, it can help us answer some of those questions about the nature of companies, what they chose to outsource, and how they interact with each other.

The foundation of business strategy 

Our current AI conundrum would not have been a surprise to British economist Ronald Coase. At age 26, he published his legendary essay, "The Nature of the Firm."Coase grapples with a fundamental problem: If the market is efficient, shouldn’t it be cheaper for a firm to outsource the majority of its internal activities to specialized contractors? Markets typically reward specialized labor that can focus on performing one task better than anyone else. At its most elemental, Coase is trying to understand the relative merits of integration (i.e., a company makes all the stuff that goes into its products, like Tesla making many of the components of its cars) versus modularization (a company that uses off-the-shelf components like IBM).

Coase's major insight on this topic was to focus on transaction costs, which are the costs associated with using the market for production and exchange. 

In a market, transactions occur through contracts between independent agents, each of which incurs costs. Within a firm, however, transactions are managed internally by a founder or manager, reducing the need for individual contracts for each transaction. Coase argues that firms exist because they can reduce these transaction costs relative to what they would outside the firm.

The size and scope of a firm are determined by the balance between the costs of organizing an extra transaction within the firm and the costs of conducting the same transaction on the open market. A firm will expand until the cost of organizing an additional transaction within the firm equals the cost of carrying out the same transaction through the market.

This theory has several implications: Firms may integrate vertically to reduce transaction costs, or they may outsource functions if the market can perform them more efficiently. The size of a firm is influenced not just by economies of scale but also by the efficiency in managing transaction costs internally instead of through the market.

However, the most important implication is that technology dramatically reduces costs. Widely distributed technology has a way of standardizing the way that firms interact with each other. Let me show you what I mean.

..Lots More

The Opaque Investment Empire Making OpenAI’s Sam Altman Rich

Many companies backed by CEO do business with the ChatGPT maker and benefit from the AI boom driven by the blockbuster startup, raising questions of conflicts

By Berber Jin, Tom Dotan and Keach Hagey

June 3, 2024 at 12:01 am ET

Sam Altman has a day job and a side gig. Only one of them is making him rich.

As the chief executive and co-founder of OpenAI, the 39-year-old oversees an artificial-intelligence startup valued at $86 billion that is spearheading a technological revolution. He owns no stake in the ChatGPT developer, saying he doesn’t want the seductions of wealth to corrupt the safe development of artificial intelligence, and makes a yearly salary of just $65,000. 

Less publicly, Altman is one of Silicon Valley’s most prolific and aggressive individual investors, managing a sprawling investment empire that is becoming a direct beneficiary of OpenAI’s success. The holdings he controls were worth at least $2.8 billion as of early this year, according to company filings and Wall Street Journal reporting. Much of the portfolio isn’t widely known.

Altman and his venture funds have invested in more than 400 companies, by Altman’s own estimate, including big names such as Stripe, Airbnb and Reddit. The holdings are managed by his family office and rival the value and size of some full-blown venture firms.

Altman has added to his startup stakes by drawing on a debt line from JPMorgan Chase, his longtime personal bank, allowing him to pour hundreds of millions of dollars more into private companies. Altman’s strategy, not previously reported, is rare among venture capitalists given the volatile nature of startup investing, where high percentages of young companies go bust. Taking on such personal levels of debt is a risky gamble.

A growing number of Altman’s startups do business with OpenAI itself, either as customers or major business partners. The arrangement puts Altman on both sides of deals, creating a mounting list of potential conflicts in which he could personally benefit from OpenAI’s work. 

OpenAI is in talks for a deal with Helion, a nuclear-energy startup that is chaired by Altman, in which it would buy vast quantities of electricity to provide power for data centers.

The 11-year-old company is planning to build nuclear-fusion power plants, a technology that doesn’t yet exist in a usable format. Altman invested $375 million in Helion in 2021, his largest startup check ever written. The startup signed on Microsoft, its first customer and OpenAI’s largest investor, last year. 

Altman has recused himself from the deal talks between OpenAI and Helion, which haven’t been previously reported.

Last month, OpenAI announced a partnership with Reddit in which it would pay to bring the messaging site’s content to ChatGPT and other AI products. Altman and entities he controls own 7.6% of Reddit, making him the third-largest outside shareholder, and he briefly served as its CEO in 2014. 

Reddit’s stock shot up 10% after the announcement, boosting Altman’s stake by $69 million to $754 million. Altman didn’t lead the partnership talks, OpenAI said in a blog post. 

Altman’s more recent investments have focused on companies that aim to capitalize on the artificial intelligence boom being driven by OpenAI. Apex Security, in which Altman invested an undisclosed amount last summer, aims to sell cybersecurity software to companies using AI products such as ChatGPT. He also invested an undisclosed amount in Exowatt, a startup tackling the clean-energy needs of big data centers used by AI companies.

Through a spokesperson, Altman declined to comment on any potential conflicts of interest between OpenAI and his personal investments.

..Lots More

Video of the Week

The Future of the American Dream

Marc Andreessen and Ben Horowitz

AI of the Week

SignalRank Version 3 Improves Performance Again

Announcing the next version of SignalRank's Predictive Algorithms

SIGNAL RANK CORPORATION

JUN 05, 2024

SignalRank's scoring algorithms aim to align our investments with our partner's greatest chance of seeing returns on their investments. We seek to provide capital for the best prospects within their portfolio.

Because our partners share profits on our investments, they have a common interest in the quality of the companies we place capital into. Our scores are intended to weigh all Series B rounds against each other. We target the top 5-10% of high-scoring rounds. In that sense, our accuracy is of significant interest to our partners.

Last October, we announced version 2 of SignalRank's algorithms.. At that time, we highlighted a significant improvement in the algorithm’s ability to detect companies likely to achieve a 5x MOIC (multiple of invested capital) or more within 5 years of their Series B funding round, while maintaining strong unicorn prediction capabilities.

While version 2 showed relative performance metrics slightly below version 1 (24% unicorns vs. 26% and 4x MOIC vs. 4.6x MOIC), it demonstrated substantial absolute gains (641 unicorns vs. 203), making it far superior in overall performance. Here is what we said at the time. These were 2012-2023 numbers so included many immature qualifiers.

v1 has an average MOIC of 4.6x 2012-2023. v2 has 4.0x. 2012-2023.

v1 has 203 unicorns from the 858 selections (26%) v2 has 641 from 2,612 selections (24%)

This means we have significantly grown the candidate base while maintaining excellent performance.

With version 3, these performance metrics have improved even further, as evidenced in the following charts. We focus on four dimensions of improvement:

1. Number of Qualifiers: Ensuring sufficient candidates to produce at least 100 investable Series B rounds per year.

2. Average and Median MOIC: Evaluated through backtesting.

3. Unicorn Percentage: The proportion of unicorns produced by the backtest.

4. Absolute Number of Unicorns: The total count of unicorns identified.

No single model excels in all four dimensions, but MOIC production and the number of qualifiers are the most critical as they directly impact the number of accessible Series B rounds and the likely performance of those investments.

Version 3 outperforms both version 1 and version 2, producing more qualifiers, a significantly higher average and median MOIC, and a much higher unicorn percentage.

To correlate performance to the age of the investments in the qualified companies, we will use 2012-2020 as the range of years tested and compared.

This permits us to include 2021-24 performance in investments made up to 2020, and so shows a realistic set of outcomes.

For 2012-2020 here is the comparison:

It is clear that v3 has performed by optimizing qualifiers to provide at least 100 annual qualifiers (v2 produced too many), increasing MOIC against v2, and unicorn percent against both previous models. v1 produces better MOIC but at the heavy cost of too few qualifiers and as a result a low absolute number of unicorns.

..More

How Long Can OpenAI’s First-Mover Advantage Last?

By Stephanie Palazzolo Jun 4, 2024, 7:00am PDT

As companies like OpenAI, Anthropic, Google and Meta Platforms race to leapfrog each other with marginally faster, cheaper or more accurate large language models, a number of developers have told me that these LLMs are beginning to reach parity when it comes to performance.

And now, new exclusive data from Kruze Consulting, a finance and HR consulting firm, backs up those anecdotes. Over the last year, the proportion of the firm’s 800-plus venture-backed startup customers using multiple AI models has grown significantly, expanding from 1% last summer to 15% in April.

OpenAI remains by far and away the market leader when it comes to LLM usage, and I’ll be the first to admit that 15% is still a relatively modest number. But, this trend could signal that developers aren’t as married these days to any specific model provider as they once were, a belief that industry practitioners have shared with me as well.

“The most recent open-source models today are on par with GPT-4, and until the release of GPT-4o, OpenAI, Anthropic and Google’s models were very close in terms of performance,” said Ion Stoica, a professor of computer science at the University of California, Berkeley and the co-founder of AI startups Anyscale and Databricks. “It does raise the question of whether these models will get commoditized.”

In another example, data from Kruze shows that the growth in the consulting firm’s customers using OpenAI’s LLMs has slowed in recent months. Meanwhile, Anthropic’s release of Claude 3 in March saw a dramatic increase in usage compared to its Claude 2launch last July, suggesting that many developers saw the latest model as a serious contender compared to other frontier LLMs.

OpenAI could still have a few cards left up its sleeve. The company could take a page out of its biggest shareholder’s book by bundling together more AI products and creating an all-in-one package for customers—a strategy Microsoft used to make its Teamsmessaging app an attractive option despite Slack’s popularity. That strategy has likely worked for the ChatGPT maker in the past: Its choice to begin bundling together its image-generation software, DALL-E, with its ChatGPT Plus and Enterprisesubscriptions last October coincided with a decrease in Kruze’s customers using rival software from Midjourney, the firm said. 

..Lots More

OpenAI Employees Warn of Advanced AI Dangers

Tuesday June 4, 2024 12:55 pm PDT by Juli Clover

Several current and former employees of OpenAI and Google DeepMind today shared an open letter warning of the dangers of advanced AI and the current lack of oversight of companies working on AI technology.

The employees suggest there are a number of risks that we are facing from AI development, including further entrenchment of existing inequalities, manipulation and misinformation, and loss of control of autonomous AI systems, which the letter says could lead to human extinction.

AI companies have "strong financial incentives" to forge ahead with development and to avoid sharing information about their protective measures and risk levels. "We do not think they can all be relied upon to share it voluntarily," reads the letter, which says that it is up to current and former employees to speak out.

So long as there is no effective government oversight of these corporations, current and former employees are among the few people who can hold them accountable to the public. Yet broad confidentiality agreements block us from voicing our concerns, except to the very companies that may be failing to address these issues. Ordinary whistleblower protections are insufficient because they focus on illegal activity, whereas many of the risks we are concerned about are not yet regulated.

Employees are ultimately calling on AI companies to offer solid whistleblower protections for speaking out about the risks of AI.

* Avoid creating or enforcing agreements that prevent criticism for risk-related concerns.

* Offer a verifiably anonymous process for employees to raise risk-related concerns to the board, regulators, and independent organizations with relevant expertise.

* Support a culture of open criticism to allow employees to raise risk-related concerns about technologies to the public, the board, regulators, and more, as long as trade secrets are protected.

* Avoid retaliating against employees who publicly share risk-related confidential information after other processes have failed.

A total of 13 employees signed the letter, including seven former OpenAI employees, four current OpenAI employees, one former Google DeepMind employee, and one current Google DeepMind employee. OpenAI has threatened employees with loss of vested equity for speaking up, and it makes them sign draconian NDA agreements that muzzle criticism.

The letter comes as Apple prepares to announce multiple AI-powered features for iOS 18 and other software updates on Monday. Apple is working on its own AI functionality that will be baked into apps across the operating system, plus it has signed a deal with OpenAI to integrate ChatGPT features into ‌iOS 18‌.

A Right to Warn about Advanced Artificial Intelligence

We are current and former employees at frontier AI companies, and we believe in the potential of AI technology to deliver unprecedented benefits to humanity.

We also understand the serious risks posed by these technologies. These risks range from the further entrenchment of existing inequalities, to manipulation and misinformation, to the loss of control of autonomous AI systems potentially resulting in human extinction. AI companies themselves have acknowledged these risks [1, 2, 3], as have governments across the world [4, 5, 6] and other AI experts [7, 8, 9].

We are hopeful that these risks can be adequately mitigated with sufficient guidance from the scientific community, policymakers, and the public. However, AI companies have strong financial incentives to avoid effective oversight, and we do not believe bespoke structures of corporate governance are sufficient to change this.

AI companies possess substantial non-public information about the capabilities and limitations of their systems, the adequacy of their protective measures, and the risk levels of different kinds of harm. However, they currently have only weak obligations to share some of this information with governments, and none with civil society. We do not think they can all be relied upon to share it voluntarily.

So long as there is no effective government oversight of these corporations, current and former employees are among the few people who can hold them accountable to the public. Yet broad confidentiality agreements block us from voicing our concerns, except to the very companies that may be failing to address these issues. Ordinary whistleblower protections are insufficient because they focus on illegal activity, whereas many of the risks we are concerned about are not yet regulated. Some of us reasonably fear various forms of retaliation, given the history of such cases across the industry. We are not the first to encounter or speak about these issues.

We therefore call upon advanced AI companies to commit to these principles:

* That the company will not enter into or enforce any agreement that prohibits “disparagement” or criticism of the company for risk-related concerns, nor retaliate for risk-related criticism by hindering any vested economic benefit;

* That the company will facilitate a verifiably anonymous process for current and former employees to raise risk-related concerns to the company’s board, to regulators, and to an appropriate independent organization with relevant expertise;

* That the company will support a culture of open criticism and allow its current and former employees to raise risk-related concerns about its technologies to the public, to the company’s board, to regulators, or to an appropriate independent organization with relevant expertise, so long as trade secrets and other intellectual property interests are appropriately protected;

* That the company will not retaliate against current and former employees who publicly share risk-related confidential information after other processes have failed. We accept that any effort to report risk-related concerns should avoid releasing confidential information unnecessarily. Therefore, once an adequate process for anonymously raising concerns to the company’s board, to regulators, and to an appropriate independent organization with relevant expertise exists, we accept that concerns should be raised through such a process initially. However, as long as such a process does not exist, current and former employees should retain their freedom to report their concerns to the public.

Nvidia hits $3tn and surpasses Apple as world’s second most valuable company

AI chipmaker’s stock has surged 147% so far in 2024, underscoring shift in tech world as demand for its processors far outstrip supply

Reuters, Wed 5 Jun 2024 21.46 BST

Shares of Nvidia rallied to record highs on Wednesday, with the artificial-intelligence chipmaker’s stock market valuation hitting the $3tn mark and overtaking Apple to become the world’s second most valuable company.

The chipmaker’s stock was up 5.16% at $1,224.40, giving Nvidia a market value of $3.01tn at market close. Apple’s market capitalization was at $3.00tn at market close as its stock climbed 0.78%.

The latest rally for Nvidia comes as it prepares to split its stock 10-for-one, effective on 7 June, a move that could increase its appeal to individual investors.

The surge in Nvidia’s stock market value above Apple’s underscores a shift in Silicon Valley, where the company co-founded by Steve Jobs has dominated since it launched the iPhone in 2007.

Microsoft, based in Redmond, Washington, remains the world’s most valuable company with a market value of $3.14tn as its shares climbed slightly the same day, the only other company to reach such a stratospheric valuation.

Demand for Nvidia’s top-of-the-line processors is far outstripping supply as Microsoft, Meta Platforms and Google parent Alphabet race to build out their AI computing capabilities and dominate the emerging technology.

Nvidia has rallied nearly 30% just since 22 May, when it issued its latest stellar revenue forecast.

Optimism about AI lifted chip stocks broadly on Wednesday, with the PHLX chip index surging about 4%. Super Micro Computer, which sells AI-optimized servers built with Nvidia chips, climbed nearly 5%.

..More

VCs are selling shares of hot AI companies like Anthropic and xAI to small investors in a wild SPV market

Marina Temkin

10:00 AM PDT • June 1, 2024

VCs are clamoring to invest in hot AI companies, and willing to pay exorbitant share prices for coveted spots on their cap tables. Even so, most aren’t able to get into such deals at all. Yet small, unknown investors, including family offices and high-net-worth individuals, have found their own way to get shares of the hottest private startups like Anthropic, Groq, OpenAI, Perplexity, and Elon Musk’s X.ai (the maker of Grok).

They are using special purpose vehicles, or SPVs, where multiple parties pool their money to share an allocation of a single company. SPVs are generally formed by investors who have direct access to the shares of these startups and then turn around and sell a part of their allocation to external backers, often charging significant fees while retaining some profit share, known as carry.

While SPVs aren’t new – smaller investors have relied on them for years – there’s a growing trend of SPVs successfully getting shares from the biggest names in AI.

These investors are finding that the most popular AI companies, except OpenAI, are not all that hard for them to buy at their smaller levels of investing. That’s because early backers in sought-after AI startups are eager to exercise their pro-rata rights, which allow them to buy more shares each time a company raises, maintaining their percentage ownership. That’s the perfect scenario for an SPV. Rather than giving up the shares because the early investor can’t afford them, they’ll create the SPV, fund it by raising money from others, and, in most cases, charge additional fees.

In many cases, the VCs will offer access to the SPV to their existing limited partner investors, but they also may use brokers to offer access to a much larger universe of potential investors. In fact, the same AI startup may have multiple SPVs on their cap table, representing lots of small investors. But the terms each small investor will pay depend on the SPV. It’s a bit of a wild west, buyer-beware situation.

Ken Sawyer, co-founder of Saints Capital, a secondaries market VC firm, said he regularly sees SPVs for the same company marketed with different terms. “Fees and carry are all over the map,” he said, adding that SPV sponsors can charge as high as 2% of the total money invested and keep 20% of the profits.

What’s more, some SPVs are formed on top of another SPV. For instance, when Menlo Ventures was raising a $750 million SPV to invest in Anthropicearlier this year, some funds that invested in it resold a slice of their SPV allocation to other investors, charging additional fees on their second-layer SPV, Sawyer said.

..Lots More

News Of the Week

Crunchbase Monthly Recap May 2024: AI Leads Alongside An Uptick In Billion-Dollar Rounds

June 5, 2024

Gené Teare, @geneteare

Venture funding rebounded in May to reach $31 billion, the highest monthly tally so far this year. Investment was up over 40% month over month and 29% year over year, with AI leading as the sector that raised the most funding.

A spate of billion-dollar fundings contributed to the total, with $11 billion — over a third of capital raised last month — invested in six companies in rounds at $1 billion or more. This was the highest count of billion-dollar fundings in a single month since the venture market slowdown began in 2022.

Elon Musk’s xAI raised the largest funding, $6 billion at a $24 billion value. Billion-dollar rounds also went to CoreWeave, Wayve, Abound, Scale AI and Wiz. Investors who led or co-led these fundings include Lightspeed Venture Partners, Andreessen Horowitz, Accel and GSR Ventures on the venture side. Growth investors Thrive Capital, Coatue and SoftBank also led rounds.

AI leads

In total, companies in the AI sector raised 40% of venture funding in May with $12.5 billion invested across more than 250 companies, based on an analysis of Crunchbase data. xAI raised close to half of that amount.

Other leading sectors include healthcare and biotech companies, which raised $5.1 billion, and financial services companies, which raised $3.9 billion last month.

As of the end of May, AI, healthcare and biotech are the leading sectors so far this year, with each raising around $27 billion in funding.

Are the M&A markets making a comeback?

A record five venture-backed companies were acquired for more than $1 billion this past month. Three were biotech companies EyeBiotech, HI-Bio and Mariana Oncology. In the enterprise software sector, Venafi, a machine identity security company, and AuditBoard, a cloud compliance management software provider, were acquired.

..More

Elon Musk ordered Nvidia to ship thousands of AI chips reserved for Tesla to X and xAI

PUBLISHED TUE, JUN 4 20249:00 AM EDT

Lora Kolodny @IN/LORAKOLODNY/

KEY POINTS

* Emails circulated inside Nvidia and obtained by CNBC show that Elon Musk told the chipmaker to prioritize shipments of processors to X and xAI ahead of Tesla.

* Musk has said he can grow Tesla into a major player in artificial intelligence and that the company is spending heavily on Nvidia’s AI processors.

* By ordering Nvidia to let X jump the line ahead of Tesla, Musk delayed the automaker’s receipt of over $500 million in processors by months.

Elon Musk, chief executive officer of SpaceX and Tesla and owner of X, speaks at the Milken Conference 2024 in Beverly Hills, California, May 6, 2024.

David Swanson | Reuters

Elon Musk says he can grow Tesla into “a leader in AI & robotics,” an ambition that he’s said will require a lot of pricey processors from Nvidia to build up its infrastructure.

On Tesla’s first-quarter earnings call in April, Musk said the electric vehicle company will increase the number of active H100s — Nvidia’s flagship artificial intelligence chip — from 35,000 to 85,000 by the end of this year. He also wrote in a post on X a few days later that Tesla would spend $10 billion this year “in combined training and inference AI.”

But emails written by Nvidia senior staff and widely shared inside the company suggest that Musk presented an exaggerated picture of Tesla’s procurement to shareholders. Correspondence from Nvidia staffers also indicates that Musk diverted a sizable shipment of AI processors that had been reserved for Tesla to his social media company X, formerly known as Twitter.

Tesla shares slipped as much as 1% on the news Tuesday morning.

By ordering Nvidia to let privately held X jump the line ahead of Tesla, Musk pushed back the automaker’s receipt of more than $500 million in graphics processing units, or GPUs, by months, likely adding to delays in setting up the supercomputers Tesla says it needs to develop autonomous vehicles and humanoid robots.

“Elon prioritizing X H100 GPU cluster deployment at X versus Tesla by redirecting 12k of shipped H100 GPUs originally slated for Tesla to X instead,” an Nvidia memo from December said. “In exchange, original X orders of 12k H100 slated for Jan and June to be redirected to Tesla.”

A more recent Nvidia email, from late April, said Musk’s comment on the first-quarter Tesla call “conflicts with bookings” and that his April post on X about $10 billion in AI spending also “conflicts with bookings and FY 2025 forecasts.” The email referenced news about Tesla’s ongoing, drastic layoffsand warned that head-count reductions could cause further delays with an “H100 project” at Tesla’s Texas Gigafactory.

..More

Introducing video to Substack Chat

Speak directly to subscribers in a space you own

JASMINE SUN, JUN 05, 2024

Today we’re bringing video to Substack Chat. Now, for the first time, you can easily record a video on your phone and send it directly to your subscribers. Posting a video to Chat instantly notifies your audience, and the video can be paywalled to paid subscribers or your founding tier.

When we introduced video to Notes in April, we saw an explosion of creativity across the platform. Many Substackers jumped on the opportunity to introduce themselves to the broader Substack network, bringing potential new subscribers behind the scenes of their work. We saw Wu Fei 吴非 sing to a local hummingbird, Dr Sharon Blackie announce her new book, and Viv Chen share an outfit of the day. Others asked for the option to use video in a more private space that they own and control, where they can be candid with their community. We built video in Chat for publishers who wish to speak directly to subscribers in this way.

Think of video in Chat like sending a voice memo to a group chat, or recording a video for your Instagram story—minus the opaque algorithm deciding whether your post gets seen. Rather than getting lost in a sea of content, video in Chat is an easy way for creators to speak directly to their subscribers.

How to share videos in Substack Chat

* Open your publication’s chat in the Substack app by tapping on the Chat tab (the messages icon). Then tap on the orange “New chat” button. If you’ve enabled chat, your publication will be listed at the top.

* Tap the plus icon in the bottom left corner, next to the composer. Choose “Video” to upload from your gallery, or “Camera” to record a video directly from your phone’s camera. 

* You can then choose to add a caption, paywall the video thread, or send an email to notify subscribers.

* You’re done! Subscribers will get an instant push notification to their mobile device, prompting them to react and reply.

Videos in Chat can be up to five minutes long. For the smoothest experience, we recommend uploading at 1080p or lower. If you allow subscribers to start their own chat threads, they are able to share their own videos with the community (video replies are coming soon!). 

..More

Instagram’s Testing Video Ads That Stop You From Scrolling Further

Published June 2, 2024

By Andrew Hutchinson, Content and Social Media Manager

Unskippable video ads in your main Instagram feed? How would that work?

According to various reports, Instagram is currently testing out a new video ad format that does indeed stop users from scrolling in the main feed of the app until they’ve viewed a video ad.

As you can see in this example, shared by photographer Dan Levy, Instagram’s new in-feed ad units appear with a timer at the bottom, and you can’t scroll past the ad till the timer runs down.

Here’s an explainer of how the new ad units work:

As Instagram explains, you’ll actually need to view the ad before you can keep scrolling, so these are essentially unskippable video ads in IG form.

Which, as you can imagine, is not going down great with Instagram users.

YouTube’s unskippable video ads have long been cited as a key reason why people download ad blockers, because there are few things more annoying on the web than being forced to view disruptive, all-encompassing promotions for things that you’re not interested in.

Ideally, digital ad targeting would have gotten so advanced by this stage that the targeting element is less of an issue, but really, there’s no way to always display the right ad to the right user every time. So you are going to get random promos, particularly from big brands, blasted at you from time-to-time at least, and this new format would provide another way to force such messaging down your throat as you scroll through Instagram.

Which, from a brand perspective, I can understand the benefits of, in terms of exposure, timed placement, etc. But for users, not so much.

So why would Instagram do it?

Well, now that your main Instagram feed is half filled by AI-recommended content from profiles that you don’t follow, predominantly short-form Reels video clips, that presents a great opportunity for Meta to add in more promotions, because if 50% of the content in your feed is from profiles that you don’t follow anyway, you’re not going to be as affronted by ads within that stream.

But the scroll-stopping part, I’m not so sure about.

Startup of the Week

NBA Nears $76 Billion TV Deal, a Defining Moment for Media and Sports

Advanced talks with NBC, Amazon and ESPN spotlight the staggering value of sports rights and could portend industry changes

By Joe Flint, Amol Sharma and Isabella Simonetti

Updated June 5, 2024 at 8:37 am ET

The National Basketball Association entered its first TV negotiations in a decade with a problem: Its main business partners seemed to be on shaky footing.

TNT parent Warner Bros. Discovery WBD 0.73%increase; green up pointing triangle was saddled with more than $40 billion in debt, while ESPN parent Disney DIS -1.77%decrease; red down pointing triangle was battling a Wall Street activist over its slumping stock. Each company was reluctant to pony up the full premium the league wanted. But the NBA had quietly laid the groundwork with two other potential partners, Amazon AMZN 1.08%increase; green up pointing triangle and NBC, which pounced as soon as they got the chance.

Now, with negotiations progressing as the Boston Celtics and Dallas Mavericks prepare to face off in the NBA Finals, the league is on track to score big: It is closing in on deals with NBC, ESPN and Amazon that would bring in about $76 billion in media revenue over 11 years, people familiar with the discussions said. 

The NBA sweepstakes has turned into a defining moment for the TV industry, highlighting the anxieties of traditional media companies about the collapse of cable and their uncertain financial futures in the streaming world. It has put front and center the paradox that sports content is outrageously expensive but also critical to own in an industry in which it is one of the few reliable ways to draw in audiences. 

“Entertainment is a swamp, and sports is the only firm ground,” said former Fox Sports chief David Hill. 

NBC is near an accord with the league to pay an average of $2.5 billion a year, people familiar with the deal talks said. It would show around 100 games per season, with about half airing exclusively on the Peacock streaming service, reflecting a major bet on the future of streaming. Games would air on NBC on Tuesdays and Sundays when there isn’t a conflict with NBC’s “Sunday Night Football.”

Amazon’s $1.8 billion-a-year package would include regular-season and playoff games, the new NBA in-season tournament, and the “play-in” games in which teams compete for the final playoff spots. It also would have a share of the conference finals, which the media partners would split in a rotation, the people familiar with the terms said.

Disney would retain an NBA package and would continue to air the NBA Finals, with payments averaging about $2.6 billion a year, people familiar with the terms say, up from $1.5 billion under the current deal. Disney would get fewer games than under its current deal. ESPN’s deal will allow the company to air games on its direct-to-consumer streaming service, which is set to launch in 2025. 

Warner, led by Chief Executive David Zaslav, still has a right to match a rival package, and the league could always carve out a new package for the company in the final stretch, but its options are limited. 

The deals would go into effect after the 2024-2025 season and would include rights to WNBA telecasts, as that league grows in popularity with the rise of rookie sensation Caitlin Clark. Owners must approve the deals, and any announcement could still be a few weeks away.

The deals are clarifying the media industry’s pecking order and could set the table for big mergers down the road. For the league, the deals would translate into a windfall that would help fund blockbuster contracts for stars such as Jayson Tatum and Luka Doncic in the coming years.

The NBA is on track to increase its annual fees by more than 2.5 times under the new deal, to an average of nearly $7 billion. The NFL roughly doubled its fees under its last deal to around $10 billion a year. The NBA has much lower average ratings than the NFL, but it has more games and a young audience that is important to advertisers. It is very popular abroad, which is a big motivator for Amazon’s Prime Video.

“Yes, there’s risk at these fee levels given recent ratings, but they are also looking at the downside of the games being on competing services. Which is worse?” said Brent Magid, CEO of media consulting firm Magid.

..Lots More

X of the Week

Hat Tip to this week’s creators: @tedgioia, @benthompson, @stratechery, @peterwalker99, @omri_drory, @sama, @mariogabriele, @gruber, @giannandrea, @craigfederighi, @gregjoz, @alex, @MParekh, @waxeditorial, @romaindillet, @cookie, @ttunguz, @Kantrowitz

Contents

* Editorial: Checkmate!

* Essays of the Week

* Is Silicon Valley Building Universe 25?

* Apple Intelligence is Right On Time

* 2018 cohort graduation rates?

* How VCs Become A******s

* Startup Playbook

* How to Find a Unicorn

* Video of the Week

* John Gruber, John Giannandrea, Craig Federighi, and Greg Joswiak on Apple Intelligence

* AI of the Week

* OpenAI's growth is one of the most astounding business results of all time

* AI: New Focus on 'Accelerated' Local AI Devices. RTZ #387

* News Of the Week

* visionOS 2: Spatial Personas Can Touch Fingers, High Five, Fist Bump Each Other With Visual and Audio Feedback

* Raspberry Pi is now a public company

* Carta’s valuation to be cut by $6.5 billion in upcoming secondary sale

* LinkedIn Adds New Elements to Its Newsletter Creation Platform

* Startup of the Week

* Databricks' Accelerating Growth

* X of the Week

* 3, 3 Trillion Dollar Companies

Editorial: Checkmate!

Checkmate! That seems like the appropriate word if you analyze what happened with OpenAI this week.

After being built into every conceivable Microsft interface, Apple announced that it would integrate OpenAI into all of its operating systems across devices via Siri.

By locking up Microsoft and Apple, it has effectively locked out Google, at least for now. That will leave Google itself as the only large implementation of its Gemini AI family.

This gives Apple a global advantage in the iPhone versus Android battle. Few will prefer Gemini to OpenAI.

Beyond that, Apple successfully showed how its own ‘Apple Intelligence’ will face inwards to the device, interoperating with all apps and supporting ‘actions’ while leaving all user data on the device. And when you need more power than the device can deliver, the new Apple Intelligence Cloud steps up in a fully encrypted secure environment. Even Apple cannot decrypt your data as it has no keys.

Ben Thompson from Stratechery sums up Apple’s play as follows:

This is good news for Apple in two respects. First, with regards to the title of this Article, the fact it is possible to be too early with AI features, as Microsoft seemed to be in this case, implies that not having AI features does not mean you are too late. Yes, AI features could differentiate an existing platform, but they could also diminish it. Second, Apple’s orientation towards prioritizing users over developers aligns nicely with its brand promise of privacy and security: Apple would prefer to deliver new features in an integrated fashion as a matter of course; making AI not just compelling but societally acceptable may require exactly that, which means that Apple is arriving on the AI scene just in time.

The concept of “just in time” seems appropriate. Although, as a developer possessing all of the beta products, I can say that very few of the features announced are yet available.

The contrast with Microsoft couldn’t be more extreme. Its Recall product, which took a screen recording every five seconds and stored its findings in clear text on the device, got a backlash from journalists and privacy campaigners. Microsoft has all but canceled the product, and its PR tail is between its legs. Apple’s ‘Crush’ ad has almost been forgotten.

Microsoft could make a mistake here. It is already working on products competing with OpenAI and might be tempted to go alone. What Bing is to Google, Microsoft AI will be to OpenAI. If it does so, it will once again shoot itself in the foot. OpenAI is far ahead in features and capabilities. Google cannot integrate it. Microsoft has gained an advantage from having done so. Apple too. Don’t bite the hand that feeds you seems an apt reminder.

This week’s essays focus a lot on the social impact of innovation and venture capital.

Ted Gioia’s essay about “Universe 25” focuses on the Durkheim concept of ‘anomie.’ It is the idea that our isolation leads to meaninglessness in life.

“More than 100 years ago, sociologist Emile Durkheim studied the problem of anomie. That’s not a word you hear very often nowadays. But we need to bring it back.

Anomie is a sense that life has no purpose or meaning. The people who suffer from it are listless, disconnected, and prone to mental illnesses of various sorts. Durkheim believed, for example, that suicide was frequently caused by anomie.

But the most shocking part of Durkheim’s analysis was his view that anomie increased when social norms were lessened. You might think that people rejoice when rules and regulations get eliminated. But Durkheim believed the exact opposite.”

Gioia examines the aimlessness of a world where people live in social media.

The Venture Capital essays are excellent. Sam Altman’s ‘Startup Playbook’ contains intelligent advice for startup founding teams. And Mario Gabriele’s piece about ‘How to Find a Unicorn’ has good advice for emerging fund managers. Omri Drory’s piece: How VCs Become A******s - is both funny and true. A great read

Hat Tip to this week’s creators: @leopoldasch, @JoeSlater87, @GaryMarcus, @ulonnaya, @alex, @ttunguz, @mmasnick, @dannyrimer, @imdavidpierce, @asafitch, @ylecun, @nxthompson, @kaifulee, @DaphneKoller, @AndrewYNg, @aidangomez, @Kyle_L_Wiggers, @waynema, @QianerLiu, @nicnewman, @nmasc_, @steph_palazzolo, @nofilmschool

Contents

* Editorial: 

* Essays of the Week

* Situational Awareness: The Decade Ahead

* ChatGPT is b******t

* AGI by 2027?

* Ilya Sutskever, OpenAI’s former chief scientist, launches new AI company

* The Series A Crunch Is No Joke

* The Series A Crunch or the Seedpocalypse of 2024 

* The Surgeon General Is Wrong. Social Media Doesn’t Need Warning Labels

* Video of the Week

* Danny Rimer on 20VC - (Must See)

* AI of the Week

* Anthropic has a fast new AI model — and a clever new way to interact with chatbots

* Nvidia’s Ascent to Most Valuable Company Has Echoes of Dot-Com Boom

* The Expanding Universe of Generative Models

* DeepMind’s new AI generates soundtracks and dialogue for videos

* News Of the Week

* Apple Suspends Work on Next Vision Pro, Focused on Releasing Cheaper Model in Late 2025

* Is the news industry ready for another pivot to video?

* Cerebras, an Nvidia Challenger, Files for IPO Confidentially

* Startup of the Week

* Final Cut Camera and iPad Multicam are Truly Revolutionary

* X of the Week

* Leopold Aschenbrenner

Editorial

I had not heard of Leopold Aschenbrenner until yesterday. I was meeting with Faraj Aalaei (a SignalRank board member) and my colleague Rob Hodgkinson when they began to talk about “Situational Awareness,” his essay on the future of AGI, and its likely speed of emergence.

So I had to read it, and it is this week’s essay of the week. He starts his 165-page epic with:

Before long, the world will wake up. But right now, there are perhaps a few hundred people, most of them in San Francisco and the AI labs, that have situational awareness. Through whatever peculiar forces of fate, I have found myself amongst them.

So, Leopold is not humble. He finds himself “among” the few people with situational awareness.

As a person prone to bigging up myself, I am not one to prematurely judge somebody’s view of self. So, I read all 165 pages.

He makes one point. The growth of AI capability is accelerating. More is being done at a lower cost, and the trend will continue to be super-intelligence by 2027. At that point, billions of skilled bots will solve problems at a rate we cannot imagine. And they will work together, with little human input, to do so.

His case is developed using linear progression from current developments. According to Leopold, all you have to believe in is straight lines.

He also has a secondary narrative related to safety, particularly the safety of models and their weightings (how they achieve their results).

By safety, he does not mean the models will do bad things. He means that third parties, namely China, can steal the weightings and reproduce the results. He focuses on the poor security surrounding models as the problem. And he deems governments unaware of the dangers.

Although German-born, he argues in favor of the US-led effort to see AGI as a weapon to defeat China and threatens dire consequences if it does not. He sees the “free world” as in danger unless it stops others from gaining the sophistication he predicts in the time he predicts.

At that point, I felt I was reading a manifesto for World War Three.

But as I see it, the smartest people in the space have converged on a different perspective, a third way, one I will dub AGI Realism. The core tenets are simple:

* Superintelligence is a matter of national security. We are rapidly building machines smarter than the smartest humans. This is not another cool Silicon Valley boom; this isn’t some random community of coders writing an innocent open source software package; this isn’t fun and games. Superintelligence is going to be wild; it will be the most powerful weapon mankind has ever built. And for any of us involved, it’ll be the most important thing we ever do. 

* America must lead. The torch of liberty will not survive Xi getting AGI first. (And, realistically, American leadership is the only path to safe AGI, too.) That means we can’t simply “pause”; it means we need to rapidly scale up US power production to build the AGI clusters in the US. But it also means amateur startup security delivering the nuclear secrets to the CCP won’t cut it anymore, and it means the core AGI infrastructure must be controlled by America, not some dictator in the Middle East. American AI labs must put the national interest first. 

* We need to not screw it up. Recognizing the power of superintelligence also means recognizing its peril. There are very real safety risks; very real risks this all goes awry—whether it be because mankind uses the destructive power brought forth for our mutual annihilation, or because, yes, the alien species we’re summoning is one we cannot yet fully control. These are manageable—but improvising won’t cut it. Navigating these perils will require good people bringing a level of seriousness to the table that has not yet been offered. 

As the acceleration intensifies, I only expect the discourse to get more shrill. But my greatest hope is that there will be those who feel the weight of what is coming, and take it as a solemn call to duty.

I persisted in reading it, and I think you should, too—not for the war-mongering element but for the core acceleration thesis.

My two cents: Leopold underestimates AI's impact in the long run and overestimates it in the short term, but he is directionally correct.

Anthropic released v3.5 of Claude.ai today. It is far faster than the impressive 3.0 version (released a few months ago) and costs a fraction to train and run. it is also more capable. It accepts text and images and has a new feature that allows it to run code, edit documents, and preview designs called ‘Artifacts.’

Claude 3.5 Opus is probably not far away.

Situational Awareness projects trends like this into the near future, and his views are extrapolated from that perspective.

Contrast that paper with “ChatGPT is B******t,” a paper coming out of Glasgow University in the UK. The three authors contest the accusation that ChatGPT hallucinates or lies. They claim that because it is a probabilistic word finder, it spouts b******t. It can be right, and it can be wrong, but it does not know the difference. It’s a bullshitter.

Hilariously, they define three types of BS:

B******t (general)

Any utterance produced where a speaker has indifference towards the truth of the utterance.

Hard b******t

B******t produced with the intention to mislead the audience about the utterer’s agenda.

Soft b******t

B******t produced without the intention to mislead the hearer regarding the utterer’s agenda.

They then conclude:

With this distinction in hand, we’re now in a position to consider a worry of the following sort: Is ChatGPT hard b**********g, soft b**********g, or neither? We will argue, first, that ChatGPT, and other LLMs, are clearly soft b**********g. However, the question of whether these chatbots are hard b**********g is a trickier one, and depends on a number of complex questions concerning whether ChatGPT can be ascribed intentions.

This is closer to Gary Marcus's point of view in his ‘AGI by 2027?’ response to Leopold. It is also below.

I think the reality is somewhere between Leopold and Marcus. AI is capable of surprising things, given that it is only a probabilistic word-finder. And its ability to do so is becoming cheaper and faster. The number of times it is useful easily outweighs, for me, the times it is not. Most importantly, AI agents will work together to improve each other and learn faster.

However, Gary Marcus is right that reasoning and other essential decision-making characteristics are not logically derived from an LLM approach to knowledge. So, without additional or perhaps different elements, there will be limits to where it can go. Gary probably underestimates what CAN be achieved with LLMs (indeed, who would have thought they could do what they already do). And Leopold probably overestimates the lack of a ceiling in what they will do and how fast that will happen.

It will be fascinating to watch. I, for one, have no idea what to expect except the unexpected. OpenAI Founder Illya Sutskever weighed in, too, with a new AI startup called Safe Superintelligence Inc. (SSI). The most important word here is superintelligence, the same word Leopold used. The next phase is focused on higher-than-human intelligence, which can be reproduced billions of times to create scaled Superintelligence.The Expanding Universe of Generative Models piece below places smart people in the room to discuss these developments. Yann LeCun, Nicholas Thompson, Kai-Fu Lee, Daphne Koller, Andrew Ng, and Aidan Gomez are participants.

Hat Tip to this week’s creators: @PeterJ_Walker, @mgsiegler, @jglasner, @lennysan, @AndreRetterath, @alex, @pmarca, @nklsrh, @dmehro, @timmarchman, @adamclarkestes, @Kyle_L_Wiggers, @MTemkiContents

Editorial: 

Essays of the Week

Is there an AI Bubble?

Robotics Startups On The Rise In 2024

Behold: the Hackquisition

The Entrapment of Apple

The social radar: Y Combinator’s secret weapon | Jessica Livingston

Can We Fully Automate Startup Investing?

The 2024 IPO I’m Most Excited About

Video of the Week

The true story -- as best I can remember -- of the origin of Mosaic and Netscape.

AI of the Week

I Will F*****g Piledrive You If You Mention AI Again

Perplexity Is a B******t Machine

What, if anything, is AI search good for?

Andrew Ng plans to raise $120M for next AI Fund

No MacBook Air Killer, All MacBook Air Filler

Hebbia raises nearly $100M Series B for AI-powered document search led by Andreessen Horowitz

News Of the Week

No, a $100m + Series A Round isn’t Normal

It takes ten years to succeed as a Startup

Elon Musk has won $56bn pay package despite judge ruling it void, Tesla argues

Kleiner Perkins announces $2 billion in fresh capital, showing that established firms can still raise large sums

Startup of the Week

Webtoon Rises Modestly In IPO Debut

X of the Week

AI Poetry Camera? Seriously?Editorial

It’s Sunday, two days later than I usually send this out. Two excuses. I was in recovery from PTSD after the “debate.” And then I almost had a relapse watching England in the Euro last 16 game against Slovakia.

I’m unsure of my mental state now (we won 2-1 in extra time). But the other, more important “game” is still undecided.

But in AI, it seems everybody is getting PTSD from wild allegations that AI might kill the human race to now new suggestions that there may be a bubble in valuations for early-stage companies.

The items in this week’s newsletter are really good. MG Seigler, Alex Wilhelm and Peter Walker dominate. The first two are former TechCrunch writers (hats off to Mike Arrington for his talent-spotting). Peter is the leading contributor to VC data; he has access to Carta data and uses it super effectively.

MG and Alex have relatively new newsletter sites - SpyGlass and Cautious Optimism, respectively). They are great observers and even better writers - subscribe. Links in their articles are below.

Big tech seems to be running scared of AI regulation. This from MG Seigler’s : No MacBook Air Killer, All MacBook Air Filler

Microsoft really s**t the bed here both from a security and PR perspective. And what's left sounds very 'meh'. It's almost like Microsoft forget the 'Copilot' part of 'Copilot+ PCs'. And certainly they forgot the '+' part.

MG also wrote about the EU and Apple, claiming that the EU is seeking to entrap Apple by refusing to state what Apple can and cannot do with its AI intentions. Apple, in response, is saying it will not launch AI in Europe until the EU says what product flexibility it has.You have to smile. Apple plays this game super well.Finally, he has ‘Behold the Hackquisition’, which shows how big tech avoids M&A blocks by buying teams instead of companies.

Alex Wilhelm’s anticipation of the Circle (USDC) IPO is a great example of his regular style and substance.

Peter Walker heads up data storytelling at Carta (great title). This week, he also has three pieces, all originally posted on his LinkedIn profile.

‘Is there an AI bubble’ (my title) examines the spread of Series A venture funding valuations. He separates the percentiles and measures the spread between them, noting that the gap between the 50th percentile and the 95th is the widest ever - even wider than 2021 and 2022. This is for SaaS rounds that include much AI.

In H1 2019, the 50th percentile for pre-money valuations was $26M (Series A SaaS companies only, primary rounds). The 95th pct at that time was $96M.Now that's a pretty large gap. We're talking a 3.7x jump from the middle to the top end.But today things are even more skewed.𝗦𝗲𝗿𝗶𝗲𝘀 𝗔 𝗦𝗮𝗮𝘀 𝗩𝗮𝗹𝘂𝗮𝘁𝗶𝗼𝗻𝘀 𝗶𝗻 𝗛𝟭 𝟮𝟬𝟮𝟰• 50th pct: $44M• 95th pct: $203M• Gap: ~4.6xThat 4.6x gap is the largest of the past 5 years and likely the past 10, though I don't have full data to prove it.

Regular readers will know my point of view. Yes, there is a bubble in that smart money wants to be in the best AI companies and will compete on price to secure equity. And no, there is no bubble because this chase for future-winning companies is entirely rational. At a time when the entire planet is about to become AI users - even without being aware of it - enormous value will be created. The price of current participation is far below the actual value that will ultimately be created.

Hat Tip to this week’s creators: @jaredheyman, @PeterJ_Walker, @cartaInc, @Om, @davemcclure, @vntrcapital, @mgsiegler, @sarahfielding_, @elevenlabsio, @fredwilson, @markgurman, @e_howcroft, @UtkarshShetti, @steph_palazzolo, @runwayml, @EricHSchwartz, @Cloudflare

Contents

Editorial: Rise of the Algorithms: Private Markets Indexing is Coming.

Essays of the Week

Larry Fink says BlackRock’s deal to acquire Preqin could lead to indexing private markets.

On Rebel Theorem 3.0

First Cut—State of Private Markets: Q2 2024

The Future of Writing: How AI Will Reshape Our Tools

Video of the Week

From Startups to Secondary VC Investments: Dave McClure's Insights from 500 Startups and Paypal (VNTR)

AI of the Week

Lowering the Boom on the New Boom Times

You can now get AI Judy Garland or James Dean to read you the news

The USV Librarian

Apple Poised to Get OpenAI Board Observer Role as Part of AI Pact

OpenAI CTO Admits Creative Jobs Can Be Harmed By AI

News Of the Week

Circle Becomes First to Receive License in the EU to Issue Stablecoins Under MiCABritain's Revolut surges to record profit as it seeks $40 bln valuation

Kuo: New AirPods to Feature Cameras for Enhanced Spatial Experiences

Startup of the Week

Runway, an AI Video Startup, in Talks With General Atlantic for $4 Billion–Valuation Fundraise

X of the Week

Cloudflare AI bot blocker

I am still on my summer hiatus, but Andrew’s travel was postponed, and he wanted to do a show. So here it is, video only. Enjoy, and see you on August 16th.

Hat Tip to this week’s creators: @albertwenger, @chaykak, @washingtonpost, @pxlnv, @gideonrachman, @paulg, @KateClarkTweets, @scottehartley, @geneteare, @jesslivingston, @ycombinator, @garrytan, @rhodgkinson, @signalrank, @jordannovet, @erinkwoo, @markgurman, @Kyle_L_Wiggers, @CovariantAI, @_thatstartupguy

Hat Tip to this week’s creators: @BrankoMilan, @europressos, @AfPalasciano, @adam_tooze, @MCC_Brussels, @Norm_Lewis, @KateClarkTweets, @Alex_Lazarow, @AABerwick, @BenFoldy, @peternixey, @rhodgkinson, @andyjayhawk, @_odsc, @Kantrowitz, @amir, @steph_palazzolo, @Kyle_L_Wiggers, @girlstothefront, @mcbridesg, @geneteare, @elonmusk

Contents

Editorial: 

Essays of the Week

Can an international economic system exist in the world of nationalisms?

Draghi Says EU Itself at Risk Without More Funds, Joint Debt

Draghi's view of Europe: Investment, R&D & the US-EU comparison

Musk, Telegram and the European Assault on Online Speech

Venture Capitalists Turn to Novel Methods to Return Cash

The Rise Of Fintech Families

The Shadow Dollar That’s Fueling the Financial Underworld

Startup Success - How to Measure it?

Illiquidity is a feature, not a bug

Video of the Week

Elon Musk Live at All In Summit

AI of the Week

Waymo and Uber expand their robotaxi partnership to Austin and Atlanta

New AI Chip Surpasses Nvidia, AMD, and Intel with 20x Faster Speeds and Over 4 Trillion Transistors

Is OpenAI’s New “o1” Model The Big Step Forward We’ve Been Waiting For?

OpenAI COO Says ChatGPT Passed 11 Million Paying Subscribers

OpenAI In Talks To Raise $6.5 Billion at $150 Billion Valuation

Keen On: Gary Marcus on How to Tame Silicon Valley’s AI Barons

Mistral releases Pixtral 12B, its first multimodal model

News Of the Week

Why the SpaceX spacewalk is such a huge deal

Silicon Valley’s Y Combinator to Double Number of Cohorts Per Year

The Unicorn Board Adds 8 New Companies, With One Newly Minted Entry Valued At $16B 

Startup of the Week

AI-Powered Work Assistant Glean Doubles Valuation To $4.6B In Less Than Seven Months

X of the Week

Australian Government is “Fascist” - Elon Musk

There is one winner regarding the most significant story this week. Elon Musk and Vivek Ramaswamy have been made advisors to the Trump administration on Government efficiency in a department called DOGE (Department of Government Efficiency). Their advisor status is widely assumed to be to avoid apparent conflicts, but in reality, they are likely to wield much power.

It is rumored that Marc Andreessen was also seen on election night in Mara-a-Lago and is engaged in giving Trump advice on Tech issues.

Many of my friends (perhaps you are one of them) are horrified that Elon has this much power and are inclined to assume bad things will happen. That may well be right, but…..

#44 of the 2024 That Was The Week Newsletter. I'm with Musk discusses the politicization of everything and the need to focus on the core ideas and how they relate to human progress.

Here's a prioritized list of talking points focusing on the gravity of each issue for humanity, based on the provided sources:

• The rapid advancement of AI and its potential impact on society:

◦ The editorial highlights that technological advancement is reshaping the world at an unprecedented speed, raising questions about the value of civilization itself.

◦ The AI revolution could lead to post-scarcity abundance, potentially solving humanity’s most intractable problems.

• The geopolitical implications of AI and chip manufacturing:

◦ The semiconductor supply chain remains precarious despite the booming AI industry.

◦ The U.S. chip ban and restrictions have unintended consequences, potentially causing countries to rely on China.

◦ Sheikh Tahnoon bin Zayed Al Nahyan is leveraging wealth to propel the UAE to the forefront of the global AI race, balancing ties with China and the U.S..

• The transformation of information interfaces and potential for democratization of knowledge:

◦ AI-powered browsers may democratize knowledge and reduce information asymmetries, enabling individuals to navigate complexity independently.

• The role of government in the age of AI and regulation:

◦ The government should enable experimentation while establishing guardrails, avoiding control or restriction of development.

◦ There are mounting concerns among European founders that the region’s bureaucracy is impeding its capacity for innovation and growth.

• The limitations of AI and the need for human wisdom:

◦ While AI excels at qualitative insights, it still struggles with deterministic tasks.

◦ In venture capital, the ability to make "irrational" decisions based on gut feeling and emotional intelligence becomes a priceless asset.

• The increasing competition and innovation in the AI sector:

◦ Chinese companies like DeepSeek are disrupting markets, spurring competition.

◦ Tencent unveiled an AI model to rival DeepSeek’s rapid response system.

• The emergence of AI-powered apps and "vibecoding":

◦ ChatGPT prompts could evolve into standalone apps, potentially reshaping software development.

◦ A.I. tools allow nontechnical hobbyists to build apps and websites by typing prompts.

• The launch of new AI models and tools:

◦ OpenAI launched GPT-4.5 “Orion,” its largest AI model.

◦ Anthropic released Claude 3.7 Sonnet, a "hybrid reasoning model".

• Venture capital investment trends:

◦ Data-driven research has commoditized VC, making human judgment more critical.

◦ VC Firm Slow Ventures is investing in content creators.

◦ Taktile's AI decision platform is receiving funding from top investors.

• Other startup and tech industry developments:

◦ Perplexity is launching its AI browser, Comet.

◦ Stripe's valuation is surging, reflecting VC hopes and fears.

◦ Snowflake is growing its startup accelerator.

◦ Venus Williams is backing the WeWard startup that rewards users for walking.

◦ Nomagic is developing AI-powered robotic arms.

Talking Points from the Newsletter’s Editorial

Critique of European Commission’s Regulatory Actions

• The editorial strongly criticizes the European Commission’s enforcement of interoperability requirements under the Digital Markets Act (DMA), particularly targeting Apple. It views these measures as an example of governmental overreach into business decisions, arguing that market forces are sufficient to regulate companies like Apple.

• Key EU demands include opening iOS features to third-party developers, which Apple claims will hinder innovation and compromise user privacy.

• The editorial contrasts this regulatory approach with the organic diffusion of AI technologies, as described by OpenAI CEO Sam Altman, who likens AI’s impact to the transistor—ubiquitous, cheap, and transformative.

Technological Innovation vs. Ideological Divides

• The editorial highlights a growing ideological divide between progressives and conservatives regarding technology. Progressives are portrayed as skeptical of technological advancements, while conservatives embrace innovation and acceleration.

• Jaye Chen’s essay on STEM graduates leaning toward conservative ideologies underscores this shift, attributing it to progressives’ failure to integrate technical talent into their causes and their tendency to view technology as a problem needing control.

Celebration of Recent Tech Achievements

• The editorial celebrates notable technological breakthroughs, including:

• OpenAI’s launch of its high-performance O1-Pro AI model.

• BYD’s unveiling of EV batteries capable of recharging in five minutes.

• Nvidia’s announcement of next-generation products that are 100 times faster than current offerings.

Introduction of ‘Reflect’ App

• The editorial introduces a new app called Reflect, designed to help teens privately discuss life challenges. It leverages AI tools such as OpenAI, Perplexity, and Anthropics Claude as conversational partners for emotional support.

Advocacy for Market-Driven Innovation

• The overarching theme advocates for minimizing government interference in economic and technological decisions. It argues that markets are better equipped to judge corporate failures or successes without regulatory micromanagement

Show Notes: AI Gets Into Publishing

Overview

This newsletter issue brings together a diverse range of stories that center around how artificial intelligence is reshaping the technology, investment, legal, and media landscapes. While AI is fueling record-breaking funding rounds and accelerating product innovations, it is also stirring legal debates and forcing publishers and content creators to rethink their business models in a rapidly evolving digital ecosystem.

Listeners can expect an engaging discussion on how advanced funding and interoperability trends are driving AI’s integration into products and operations, alongside the challenges of copyright enforcement and digital disruption in media. The collection underscores the multifaceted impact of AI—from high-stakes investments and legal contestations to product innovations that bridge text and image, and even the transformation of publishing itself.

Key Trend 1: Massive AI Funding and Investment Transformations

Across several articles, the newsletter highlights how record-breaking funding rounds and strategic investments are accelerating AI development. Investors are betting big on AI innovations—from OpenAI’s nearly $40 billion funding initiative to unicorn startups driven by healthcare, cybersecurity, and agentic AI applications.

- Talking Point 1: The surge in capital backing AI ventures underscores the strategic importance of financial support for cutting-edge innovation.

- For example, TechCrunch reported that OpenAI is close to closing a SoftBank-led $40 billion round, emphasizing that “substantial capital is becoming critical for scaling advanced AI research” ([TechCrunch](https://techcrunch.com/2025/03/26/openai-will-reportedly-close-its-softbank-led-40-billion-round-soon/)).

- Similarly, venture capital trends observed in the “Venture Beacon” report show improved fundraising conditions and fewer down rounds, signaling renewed investor confidence ([DEallawyers](https://www.deallawyers.com/blog/2025/03/survey-the-state-of-venture-capital.html)).

- Talking Point 2: The evolving model of liquidity in venture-backed companies, where secondary transactions now dominate, marks a fundamental restructuring of investment dynamics.

- As highlighted in “The Great Liquidity Shift,” 71% of exit dollars originated from secondary transactions rather than traditional IPOs or M&A, reflecting an adaptive strategy in turbulent markets ([Tom Tunguz](https://tomtunguz.com/the-exit-path-of-2024/)).

- Unicorn reports from Crunchbase further illustrate how investments in sectors like healthcare and cybersecurity are reshaping the valuation landscape and fueling innovation ([Crunchbase](https://news.crunchbase.com/cybersecurity/healthcare-unicorns-ai-february-2025/)).

Key Trend 2: Legal and Ethical Challenges in AI Commercialization

The newsletter also delves into the legal front where AI’s rapid evolution collides with longstanding copyright and ethical concerns. Legal disputes and regulatory uncertainties are emerging as key hurdles that tech companies and publishers must navigate.

- Talking Point 1: AI’s use of copyrighted content is under intense legal scrutiny, as seen in the lawsuit against OpenAI.

- A recent ruling allowed a copyright lawsuit, initiated by the New York Times, against OpenAI to proceed, highlighting the risks of using copyrighted materials without permission ([TheInformation](https://www.theinformation.com/briefings/judge-allows-copyright-lawsuit-openai-proceed)).

- This case opens the debate on balancing technological innovation with the protection of intellectual property rights—a challenge that is critical in shaping future AI training practices.

- Talking Point 2: Traditional publishers are grappling with how AI-driven tools disrupt established economic models and audience engagement.

- For instance, the World History Encyclopedia’s dramatic 25% drop in traffic due to Google’s AI Overviews demonstrates how AI-driven content summarization can undercut traditional revenue streams ([BigTechnology](https://www.bigtechnology.com/p/as-ai-takes-his-readers-a-leading?publication_id=46510&utm_campaign=email-post-title&r=ktr9&utm_medium=email)).

- This tension invites a broader discussion about reimagining compensation and support structures for content creators in the age of AI.

Key Trend 3: Integration and Interoperability of AI Across Technologies

A recurring theme is the drive toward openness and integration across AI platforms, which is transforming user experiences and broadening the capabilities of digital tools.

- Talking Point 1: Open standards and interoperability are becoming essential as firms seek to integrate AI functions seamlessly into their products.

- OpenAI’s decision to adopt Anthropic’s Model Context Protocol signals a commitment to interoperability—enabling better data integration and more scalable AI solutions ([TechCrunch](https://techcrunch.com/2025/03/26/openai-adopts-rival-anthropics-standard-for-connecting-ai-models-to-data/)).

- This collaborative evolution between past rivals underlines the fact that open source solutions are a strategic lever for rapid innovation.

- Talking Point 2: Technological breakthroughs in multimodal AI systems are setting new consumer expectations.

- The introduction of GPT-4o’s native image generation within ChatGPT marks a leap forward, merging text and visuals to deliver “a frightening degree of verisimilitude” ([TechJuice](https://www.techjuice.pk/openai-enhances-chatgpt-with-powerful-native-image-generation-using-gpt-4o/)).

- Such advancements not only redefine creative workflows for digital artists but also raise important questions about ethical usage and intellectual property protections.

Key Trend 4: The Evolving State of Digital Publishing and Media

Digital publishers are being forced to innovate as AI disrupts legacy models of content distribution and audience engagement. Traditional media outlets are exploring new strategies to sustain relevance and revenue.

- Talking Point 1: AI-powered tools are reshaping how readers access and engage with content, challenging longstanding agreements between publishers and tech platforms.

- The experience of the World History Encyclopedia, which lost 25% of its traffic to AI-generated summaries by Google, underscores the disruptive impact of AI in digital publishing ([BigTechnology](https://www.bigtechnology.com/p/as-ai-takes-his-readers-a-leading?publication_id=46510&utm_campaign=email-post-title&r=ktr9&utm_medium=email)).

- This trend pushes publishers to reconsider their business models while also prompting questions about fairness and compensation.

- Talking Point 2: In response, some traditional outlets are embracing change by integrating independent creator networks to diversify their content and engage newer audiences.

- A notable example is Fast Company’s launch of a creator network featuring independent writers, which aims to bridge the gap between conventional journalism and the digital content revolution ([TheInformation](https://www.theinformation.com/articles/30-year-old-magazine-embracing-creators)).

- This approach not only rejuvenates content delivery but also serves as a model for how heritage media can adapt in a rapidly shifting digital ecosystem.

Discussion Questions

- How do the massive funding rounds for AI companies influence the pace of technological innovation, and what risks do these investments entail?

- In what ways should legal frameworks evolve to address the challenges posed by AI’s use of copyrighted content?

- Can the integration of open standards in AI systems truly accelerate innovation, or does it create new vulnerabilities in an increasingly interconnected ecosystem?

- How should traditional publishers rethink their revenue models when AI-driven content summarization threatens direct engagement?

- What are the implications of shifting exit strategies in venture capital, particularly with the rise of secondary transactions over traditional IPOs?

- Is the democratization of creative tools through multimodal AI a net positive for artistic communities, or does it risk eroding the value of human creativity?

- How can media outlets balance the need for innovative content delivery with maintaining rigorous ethical and copyright standards?

Closing Segment

The discussion today underlines four fundamental trends: record-setting AI investments, mounting legal and ethical challenges, the push for interoperability and groundbreaking multimodal innovations, and the evolving landscape of digital publishing. Together, these trends highlight not only the transformative potential of AI but also the complex interplay of finance, law, and creative expression. As we consider the future of technology and media, it’s clear that innovation must be balanced with responsibility—ensuring that the rapid pace of change benefits society as a whole.

A compelling final thought: In an era defined by disruption, the true winners will be those who not only drive innovation but also establish ethical and robust frameworks that safeguard creativity, fairness, and integrity.

Overview

This week’s newsletter centers on the explosive rise of AI, highlighting how OpenAI’s massive funding round and soaring valuation are signaling a transformative shift in both technology and finance. The content weaves together themes on the evolving nature of creativity in the AI era, intense debates around copyright and intellectual property rights, and strategic investments that are helping AI expand into new sectors such as education. The interplay of technology, ethics, and global market dynamics makes this a compelling discussion for anyone watching the AI revolution unfold.

Key Trend 1: Explosive Growth and Valuation in AI

Across the newsletter, OpenAI emerges as the poster child of AI’s rapid ascent—raising $40 billion at a $300 billion valuation, with projections hinting at exponential revenue growth over the next few years.

Talking Point 1:

The funding round “of $40 billion at $300 billion valuation” is a clear indication of the immense investor confidence in AI. 

Quote: “No one would have predicted that $1 trillion is almost too small to contain what is being built.” (Editorial) 

Reference: NY Times article on OpenAI’s valuation

Talking Point 2:

This financing milestone, when compared to historic tech deals, underscores how AI is redefining the scale and pace of innovation. 

Evidence: “After Wiz sold to Google for $32 billion in cash, and X ‘sold’ to xAI… Enter OpenAI with a new $40 billion raise…” (Editorial)

Key Trend 2: The Evolution of Creativity and Authorship in the Age of AI

The newsletter prompts us to re-examine the creative process as AI tools become increasingly intertwined with content creation. One burning question is: “When does writing stop being ‘yours’?” as AI begins to shoulder some of the creative workload.

Talking Point 1:

The evolving role of AI in writing invites debate on what constitutes true authorship and originality. 

Quote: “How does the emergence of AI reshape our understanding of authorship and originality?” (Editorial quoting JF Martin essay)

Talking Point 2:

Despite the sophisticated capabilities of AI, the content emphasizes that “the creation of truly meaningful and high-quality content still relies heavily on human direction and insight,” fostering a creative partnership rather than a displacement of human ingenuity.

Evidence: “The intricate dance of crafting prompts, providing feedback, and ultimately evaluating the AI's output…” (Editorial)

Key Trend 3: Copyright Controversies and the Ethics of AI Training

Alongside the excitement around AI, ethical and legal debates are emerging—most notably around how AI models are trained, especially when they use copyrighted materials without explicit permission.

Talking Point 1:

Controversies over using copyrighted content, such as O’Reilly books, have already led to lawsuits and heated debates about intellectual property rights. 

Quote: “Reports suggesting that AI models, potentially including OpenAI's, have been trained on copyrighted material like O'Reilly books…” (Editorial) 

Reference: TechCrunch article on copyrighted AI training

Talking Point 2:

This evolving legal landscape signals an urgent need for more transparent guidelines and ethical frameworks that balance technology’s potential with respect for content creators.

Evidence: “Navigating these ethical and legal complexities will be essential as AI becomes more deeply embedded in content creation.” (Editorial)

Key Trend 4: AI’s Growing Role in Education and Personalized Learning

The investment in SchoolAI highlights an important application of AI beyond traditional tech sectors, as it moves into education to personalize learning and improve both teacher and student experiences.

Talking Point 1:

SchoolAI’s innovative approach uses AI to “personalize education for every student and teacher,” making learning more engaging and adaptable to individual needs.

Quote: “My first 30-minute meeting with SchoolAI founder Caleb Hicks stretched to over ninety as we delved into his vision.” (Editorial) 

Reference: SchoolAI investment article

Talking Point 2:

By integrating AI into classrooms, SchoolAI is also addressing pressing challenges like teacher shortages and the need for customized support for each student.

Evidence: “SchoolAI’s platform is used in over 1 million classrooms across the U.S. and more than 80 countries…” (Editorial)

Discussion Questions

How sustainable is the current wave of massive AI funding given historical tech market cycles?

In what ways might the blending of human creativity and AI tools redefine traditional notions of authorship?

What ethical boundaries should be established regarding the use of copyrighted materials for training AI systems?

Could the integration of AI into education help bridge learning gaps, or might it exacerbate existing inequalities?

How will ongoing geopolitical tensions and evolving trade policies impact future innovation and investment in AI?

What kind of legal and regulatory frameworks are needed to balance innovation with intellectual property rights in the AI era?

How do we ensure that AI remains an enabler of human creativity rather than a replacement?

Closing Segment

The newsletter paints a vivid picture of an era defined by dramatic shifts in technology and market dynamics. The staggering growth in AI valuations, the redefinition of creative authorship, and the ethical challenges surrounding data and copyrights all point to a transformative period in business and culture. As AI finds new applications in education and beyond, the ultimate challenge—and opportunity—will be balancing rapid technological advances with ethical responsibility and sustained human oversight. 

Final Thought: As we stand at the crossroads of an AI-driven future, the choices we make about funding, regulation, and creative collaboration will shape not only industries but the very way we understand and preserve human ingenuity.

Overview

The "Whiplash" newsletter delves into various critical topics that reflect significant shifts in global dynamics, particularly in technology, geopolitics, and economic trends. These articles highlight the evolution of data infrastructure, the impact of U.S.-China trade tensions, advancements in AI and robotics, and the challenges facing globalization. This collection of content offers insights into how these trends are reshaping industries and international relations, emphasizing the need for adaptability and strategic alliances in an increasingly complex world.

Key Trends

Key Trend 1: Technological Advancements and AI

Significance: The articles highlight the transformative power of AI and graph technology in enhancing decision-making processes and creating more personalized experiences. AI is increasingly crucial in optimizing business operations and amplifying human potential rather than replacing it.

Talking Point 1: Reid Hoffman's perspective on AI emphasizes its potential to enhance human capabilities, making us more human. This view is reflected in his book Superagency, which argues that AI leads to more human agency rather than less.

Talking Point 2: The integration of AI into SaaS models is revolutionizing unit economics by improving customer experiences, predictive analytics, and operational efficiency. This shift is making businesses more agile and efficient.

Key Trend 2: Geopolitical Tensions and Trade

Significance: The articles discuss the escalating tensions between the U.S. and China, particularly over trade policies and technological sovereignty. These tensions are reshaping global trade dynamics and challenging traditional economic alliances.

Talking Point 1: The U.S. tariffs imposed on China have inadvertently benefited China by prompting it to focus on domestic consumption and technological innovation. This strategic shift is making China more self-sufficient.

Talking Point 2: The TikTok negotiations illustrate the complexities of cross-border technology regulation and the challenges of aligning national security concerns with economic interests.

Key Trend 3: Globalization and Economic Shifts

Significance: The articles explore the potential collapse of globalization due to rising nationalism and trade barriers. This trend has significant implications for economic growth, cultural exchange, and international cooperation.

Talking Point 1: The shift away from globalization is driven by protectionist policies and geopolitical conflicts, which could lead to slower economic growth and increased instability.

Talking Point 2: China's rise as a dominant trade partner reflects a broader trend of economic power redistribution, with implications for global market dynamics and technological innovation.

Discussion Questions

What are the potential long-term consequences of the U.S.-China trade tensions on global economic stability?

How can AI be effectively integrated into business operations to enhance productivity and retain human value?

In what ways does the shift towards protectionism affect international cooperation and global governance?

How might the evolution of data infrastructure impact industries like finance and healthcare?

What role do strategic alliances play in countering economic challenges posed by major powers like China?

How can businesses adapt to the changing landscape of globalization and technological advancements?

What ethical considerations arise from the increasing reliance on AI in decision-making processes?

Closing Segment

The most important trends highlighted in the "Whiplash" newsletter revolve around technological innovation, geopolitical tensions, and economic shifts. These themes underscore the need for strategic adaptability, international cooperation, and ethical considerations in navigating the complex dynamics of the modern world. As AI continues to transform industries and global trade patterns evolve, understanding these trends is crucial for businesses, policymakers, and individuals seeking to thrive in an increasingly interconnected and rapidly changing world. The final thought: In a world where change is the only constant, embracing innovation and fostering cooperation will be key to unlocking future success and stability.

Show Notes: Are Google and Meta Screwed?

And does it make any Sense?

April 18, 2025

OverviewThis week’s newsletter delves into a pivotal moment for two of tech’s biggest players: Meta and Google. Long dominant through strategic acquisitions and platform control, both are now under intense legal scrutiny. At the same time, a new platform shift—centered on AI—threatens to upend their business models, just as geopolitical forces reshape global markets.

Listeners will gain insight into how antitrust battles, legacy acquisitions, AI innovation, and trade wars intersect to challenge the future of these giants. We’ll connect disparate articles to reveal patterns that go beyond individual stories.

Key TrendsKey Trend 1: Government Antitrust Pressure and Legal BattlesSignificance: After decades of unchecked growth, Meta and Google face unprecedented antitrust scrutiny. The outcomes could reset the rules for digital markets—and determine whether breakups or massive fines become the norm.

Talking Point 1: Meta’s High-Stakes Trial

“In a just world, the FTC has no shot to win this case. The case is so nebulous and weak…”– M.G. Siegler, “The Meta Points of Meta’s Trial” (https://spyglass.org/meta-trial/)• Highlights the FTC’s challenge: litigating past acquisitions with vague theories of harm.

Talking Point 2: Google Guilty in Ad Tech Monopoly

“A judge ruled that Google holds a monopolistic position in the technology of online advertising, unfairly harming rivals and advertisers.”– David McCabe, New York Times(https://www.nytimes.com/2025/04/17/technology/google-ad-tech-antitrust-ruling.html)• Marks the second major U.S. court loss for Google in under a year, setting the stage for structural remedies.

Key Trend 2: Strategic Platform Shifts and Legacy AcquisitionsSignificance: Meta’s survival has hinged on buying Instagram and WhatsApp; now those very deals are under fire. The pattern echoes past shifts—desktop to mobile—and underscores how acquisitions can both secure and imperil platform relevance.

Talking Point 1: The Value and Vulnerability of Instagram

“Without Instagram, Meta is screwed.”– M.G. Siegler, Spyglass (https://spyglass.org/without-instagram-meta-is-screwed/)• Shows Instagram’s ad revenue underpins Meta’s funding for new bets (metaverse, AI).

Talking Point 2: Echoes of the Mobile Battle

“Facebook 2.0 will try to kill Facebook 1.0 and Google 2.0 will try to kill Google 1.0.”– Editorial, “Are Google and Meta Screwed?” (Newsletter for April 11, 2025)• Reminds us how prior platform shifts demanded reinvention—AI may require the same.

Key Trend 3: AI‑Driven Disruption and the Next PlatformsSignificance: Just as mobile upended desktop, AI is redrawing the map of search, discovery, and social engagement. Meta and Google must adapt to challengers like OpenAI, Anthropic, xAI and novel features such as memory and reasoning.

Talking Point 1: AI Search and Discovery Race

“OpenAI, Anthropic, Perplexity, and Grok capture users for AI based search and discovery.”– Editorial, “Are Google and Meta Screwed?”• Signals user migration away from traditional search and feeds.

Talking Point 2: The AI Price War and Memory Features

“OpenAI slashes prices for GPT‑4.1 by up to 75%, igniting an AI price war among tech giants.”– Bryson Masse, VentureBeat (https://venturebeat.com/ai/gpt-4-1-ai-price-war-developers/)“Claude’s memory feature … allows the chatbot to recall details from previous interactions.”– Michael Nuñez, VentureBeat(https://venturebeat.com/ai/claude-just-gained-superpowers-anthropics-ai-can-now-search-your-entire-google-workspace-without-you/)• Underscores how product feature arms races could outflank legacy ad models.

Key Trend 4: Global Economic Realignments and Trade WarsSignificance: Tech doesn’t operate in a vacuum. Tariffs and nationalism are reshaping supply chains and consumer behavior, with knock‑on effects for digital giants reliant on ad dollars and global audiences.

Talking Point 1: Tariffs as a “Tectonic Plate Shift”

“Trump’s tariffs are part of a broader movement in the global economy which he describes as a ‘tectonic plate shift.’”– Peter R. Orszag, New York Times video (https://www.nytimes.com/video/opinion/100000010103488/trumps-tariffs-are-part-of-a-tectonic-plate-shift-in-the-global-economy.html)• Reflects how trade policy uncertainty seeps into tech investment and consumer prices.

Talking Point 2: The End of Globalism vs Economic Globalization

“Globalisation as we’ve known it for the past couple of decades has come to an end.”– Frank Furedi, Spiked (https://www.spiked-online.com/2025/04/15/the-end-of-globalism-is-nigh/)• Positions economic nationalism alongside persistent interdependence—tech firms must navigate both.

Discussion Questions

How do the FTC’s and DOJ’s strategies against Meta and Google reflect a shift in government confidence and capability to regulate tech giants?

Would breaking up Instagram and WhatsApp—or forcing Google to divest its ad tech—spur innovation or simply weaken platforms in an era of AI competition?

In what ways has the shift from mobile to AI mirrored past platform transitions, and what lessons should Meta and Google apply as they pursue “2.0” strategies?

Is the AI price war (GPT‑4.1 cuts, Claude memory, Grok features) a sustainable model for developers and businesses, or will it erode margins across the ecosystem?

Do Trump’s tariffs and rising economic nationalism ultimately strengthen China’s tech incumbents (Huawei, Temu, Shein) more than they pressure U.S. companies? (Controversial)

With visionaries like Jack Dorsey and Elon Musk calling to “delete all IP law,” how should tech firms balance creator rights against AI training needs? (Controversial) 7. How does the narrative of “the end of globalism” influence Big Tech’s investment in international expansion and localized product strategies?

Closing IdeasMeta and Google stand at a crossroads: legal rulings threaten their core business structures while AI challengers redefine user engagement.

Their historic playbook—acquiring emerging rivals and evolving ad models—now collides with fast‑moving technology, activist regulators, and geopolitical headwinds.

Final Thought: Survival for these giants will depend on agility—embracing AI as the next platform, rethinking past acquisitions, and navigating a world where borders, both digital and national, are being redrawn.

Generated on 4/18/2025 with Newsletter Creator

Live Sports – The Next Streaming War

THE DIGITAL SEATS REVOLUTION

By Keith Teare • Issue #316

An average sports stadium can hold 50-100,000 fans. But teams have millions and sometimes billions of fans. What is the true value of the rights to stream games? This week Amazon bought UK Champions League rights. Can we expect more money to come for sports rights and who should own them?

Contents

Live Sports — The Next Streaming War

Essays of the Week

* Will China Build Your Next Car?

* China EV Battery Breakthrough

* Howard Morgan’s Amazing Career

* Critiquing Crypto Promoters

* Startup Workforce Trends from Carta

* Does VC Investing Violate Crypto Ethics

* Software Salaries — Europe and USA

* Web3 Use Cases Part II

Good News

* Sequoia raising $2.25bn?

* EF raises $158m Series C

* Plural launches €250m Entrepreneur Led Fund

* Long Term Stock Exchange Raises $100m

* Normalyze Series A

Bad News

* A16Z slows pace of investments

* VCs advise company sales

* Substack cuts 13 jobs

* Unity loses 4% of workforce

Startup of the Week

* Pave

Tweet of the Week

* BlockFi sold for $25m after raising $1.2bn?

Editorial

Software is about to eat live sports. The signs have been coming for some time. Apple pioneered the trend by buying the rights to Friday night baseball and MLS soccer. It is rumored to be interested in Sunday Ticket for NFL streaming.

Now Amazon is strongly favored to buy the rights to one of the biggest football competitions in the world — the UEFA Champions League — in one of its biggest markets — the UK. This follows the deal announced in March, an 11-year deal, valued at $1bn (£824m) annually, for Amazon to broadcast live NFL football in the US.

These deals highlight the next stage in the competition between broadcast, cable, and satellite networks on one side and streaming giants on the other. Live sports and live news are the only significant content that consumers want and streamers historically did not have.

The value of live sports to a rights owner is that it compels sports fans to buy subscriptions to services that host their favored events.

Rupert Murdoch pioneered the approach with Sky Sports when building out his BSkyB franchise. It required every football (soccer) loving home to install a satellite dish and set-top box. And they did.

Now Apple and Amazon are playing their game and have very deep pockets for doing so.

The key to understanding how to play the game is to understand its value. I am familiar with the English Premier League so using it as an illustration here are the facts.

The EPL has 20 teams. Between them, they have over 2 billion global fans who have 380 games per season. That is a total market available of 760 billion viewers. The EPL is currently planning to sell the rights for £10.5 bn ($14.2) for 3 years:

For the 2022 to 2025 rights cycle, The Times says international deals will be worth UK£5.3 billion (US$7.1 billion), up 30 per cent, while domestic deals bring in UK£5.1 billion (US$6.9 billion), with commercial partnerships taking the total to UK£10.5 billion (US$14.2 billion).

That makes $4.73 bn per year. On a per viewer/game basis that is point six of a cent per viewer/game in revenue.

* Games Per Week 10

* Total Fan base 2,000,000,000

* Number of Weeks 38

* Total viewer/games 760,000,000,000

* Rights per year $4,730,000,000

* Revenue per viewer/game $0.006

Of course, the rights buyers monetize the games at a multiple of their cost, by selling subscriptions and advertisements. The total value of the league measured in income is unknown. But clearly, it is well over $4.73bn a season. Perhaps 9–10 times that.

The income goes to the rights buyers, not to the League.

So if streamers gain control of the EPL, how much might it be worth?

Let us assume that 50% of the fan base watches one game a week and pays $1 a game. That would be as follows:

* Total Fan Base 1,000,000,000

* Number of weeks 38

* Games Per Week Per Fan: 1

* Viewer Games Per Week 1,000,000,000

* Price per game: $1

* Weekly Revenue: $1 billion

* Seasonal Revenue: $38 billion

* Revenue per viewer/game $1

So at 1 game per week, at $1 a game, streaming could generate $38 billion per season. In reality, the price per game can be higher and most fans would watch more than one game per week.

The untapped fortune here is what I call digital seats. Liverpool FC can fit under 70,000 fans into its Anfield stadium. But over 500,000,000 would pay to watch live games. Double that for Manchester United. Streamers can create these digital seats. Over time they can deliver a better than stadium experience to those seats.

This means that the price Amazon is paying for European football is very small compared to the opportunity.

Beyond that, the EPL itself should probably retain the rights and offer ticket-based streaming directly to fans globally. In that case, the revenue would come back to the EPL and not be placed into the hands of middlemen.

The real promise of streaming is to cut out the middlemen and simply pay for production and transport, as a cost. Movies, TV series, News, and Sports will all go that way. This week Amazon is shining a light on this.

Video

That Was The Week’s video cast streams live each Friday. The recorded version is available only to subscribers. Subscribe here.

Live Sports — The Next Streaming War

Amazon close to deal over Champions League rights in UK

US retailer and streaming giant set to split UK rights with BT Sport, while BBC to broadcast highlights in new Match of the Day edition

Amazon is close to securing a groundbreaking deal to broadcast live Champions League football in the UK from 2024, with highlights returning to terrestrial TV for the first time in nearly a decade in a midweek BBC Match of Day show.

The US internet retailer and streaming giant, which already has a broadcast portfolio spanning Premier League football, tennis and rugby, is understood to be set to split the UK rights with existing holder BT Sport in a new deal with the governing body, Uefa, running from 2024 until 2027.

Continue reading…

www.theguardian.com • Share

Essays of the Week

China Built Your iPhone. Will It Build Your Next Car?

RUMORS OF AN Apple electric car project have long excited investors and iPhone enthusiasts. Almost a decade after details of the project leaked, the Cupertino-mobile remains mythical — but that hasn’t stopped other consumer electronics companies from surging ahead. On the other side of the world, people will soon be able to order a vehicle from the Taiwanese company that mastered manufacturing Apple’s gadgets in China. Welcome to the era of the Foxconn-mobile.

In October 2021, Hon Hai Technology Group, better known internationally as Foxconn, announced plans to produce three of its own electric vehicles in collaboration with Yulon, a Taiwanese automaker, under the name Foxtron. Foxconn, which is best known for assembling 70 percent of iPhones, has similar ambitions for the auto industry: to become the manufacturer of choice for a totally new kind of car. To date it has signed deals to make cars for two US-based EV startups, Lordstown Motors and Fisker.

Foxconn’s own vehicles — a hatchback, a sedan, and a bus — don’t especially ooze Apple-chic, but they represent a big leap for the consumer electronics manufacturer. Foxconn’s ambitious expansion plan also reflects a bigger shift across the auto world, in terms of technology and geography. The US, Europe, and Japan have defined what cars are for the last 100 years. Now the changing nature of the automobile, with increased electrification, computerization, and autonomy, means that China may increasingly decide what car making is.

If Foxconn succeeds in building a major auto-making business, it would contribute to China becoming an automotive epicenter capable of eclipsing the conventional powerhouses of the US, Germany, Japan, and South Korea. Foxconn did not respond to requests for an interview.

The automobile industry is expected to undergo big transformations in the coming years. An October 2020 report from McKinsey concluded that carmakers will dream up new ways of selling vehicles and generating revenues through apps and subscription services. In some ways, the car of the future sounds an awful lot like a smartphone on wheels.

That’s partly why there’s no better moment than now for an electronics manufacturer to try car making, says Marc Sachon, a professor at IESE Business School in Barcelona, who studies the automotive industry.

www.wired.com • Share

China’s CATL Announces 1,000-Km / 620-Mile CTP 3.0 EV Battery

The company says its energy density is 255 Wh/kg and that it will debut in 2023, although it did not mention for which application.

insideevs.com • Share

The Petty Pleasures of Watching Crypto Profiteers Flounder

Behind all the Web3 bluster is just “hollow abstraction.”

I cannot stop watching videos of Web3 boosters failing to explain the usefulness of the technology. I realize this is petty, but the videos are deeply cathartic.

I’m talking about two clips in particular, both of which were posted by Liron Shapira, a tech investor and writer, and a critic of crypto and Web3. The first is of Packy McCormick, a newsletter writer, investor, and advisor to A16z’s crypto venture-capital team. I urge you to watch this clip before reading any further (but I’ll also summarize parts of it below):

McCormick is questioned by Zach Weinberg, a crypto skeptic who asks McCormick to reason through why a given problem might be better solved with a Web3 or blockchain-based project. McCormick offers up the example of a blockchain-based real-estate transaction, which he says hasn’t been done yet but is touted as one of Web3’s “promised” examples. Property buying outside of the blockchain is a long, onerous process, McCormick argues. He suggests that, “theoretically, you could make all these things NFTs … you could transact very quickly, borrow against them in the global market as opposed to going to Bank of America to take out your mortgage. You have a more open system that people are able to transact in more creative ways in.”

Weinberg stress-tests this particular scenario (putting your house on the blockchain) first by asking: What would happen in a decentralized mortgage market if a mortgage lender couldn’t get its money back? McCormick responds, essentially, that the lender could take legal action via the courts. They go back and forth a bit about smart contracts, and at every turn Weinberg pushes McCormick with some version of the same question: What makes this blockchain version better than the current system? McCormick has no answer. Here’s a transcript of the end of their exchange:

newsletters.theatlantic.com • Share

Compensation report: The state of startup compensation, H1 2022

For most startups, payroll is the primary driver of cash burn. And with inflation and economic unease on the rise, knowing trends within compensation is critical. How can a founder balance the need to conserve capital with the imperative to grow? How can leaders pay employees fairly through boom and bust cycles?

At Carta, we see it as our responsibility to share the insights that come from an unmatched amount of data about the private market. That includes data on startup headcount, payroll and equity metrics, salary medians, and remote work. We created this compensation report from data using more than 127,000 employee records from startups that use Carta Total Comp, the premier compensation management platform for private companies.

Key trends:

* Remote hiring soars: In 2019, about 35% of new hires were based in a different state than the primary company headquarters. So far this year, that number has ballooned up to 62%.

* Geo-adjusting is the norm: The vast majority of companies (84%) take employee location into account when deciding on compensation packages.

* Engineering is a key hire: Engineering accounts for nearly half of payroll spend in companies valued between $1 and 10 million.

* Terminations rise: Across all of Carta’s platform, involuntary terminations made up 29% of departures in May 2022 (the rest were employees leaving their jobs by choice). That’s nearly double the 15% termination share recorded in August of 2021.

Note: If you’re looking for compensation benchmarks against companies like yours, you can also download the addendum to this report to get an extended dataset.

www.carta.com • Share

Does Venture Capital Investment Violate the Ethos of Crypto? Sequoia Says No — Ep. 367

unchainedpodcast.com • Share

The Trimodal Nature of Software Engineering Salaries in the Netherlands and Europe

Update: dozens of hiring managers confirmed this trimodal model applies to all global markets: from the US, through Asia to Latin America as well. Also see TechPays.com for data recorded for a growing number of countries in the three tiers. (Watch this article as video narrated by me, with

blog.pragmaticengineer.com • Share

Web3 Use Cases: The Future

Will web3 justify the hype?

Today, real people are spending real money to use real products, even if some seem silly or circular.

But the real question isn’t whether there are any use cases, but whether there will be use cases that, collectively, are worth the hype.

In other words, will web3 produce use cases that justify all of the venture dollars, investment, and talent dedicated to the space? I think it will. That’s what today’s essay is about.

There are two time-scales on which I’m excited about web3’s potential: the next few years and the next few decades.

If there is another bull cycle in the next few years, I think it will happen on the backs of real products that people use at scale, not speculation. When those hit, speculation will follow, but that will look more like a traditional tech bull run than pure speculation. These products are on the way — the applications are coming and the infrastructure continues to improve.

In the next few decades, I believe that web3 infrastrastructure will become the fabric of much of what we do online and in our financial lives. I also believe that the experiments web3 protocols are running in economic design, incentive alignment, and governance will jump out of the internet and impact “real-world” institutions.

Today, I’ll dive into some of the future use cases and potential benefits I’m excited about.

The Next Few Decades

So let’s begin with the future. If all of this pans out, so what?

www.notboring.co • Share

Good News

Sequoia Capital Targets $2.25 Billion for Two U.S. VC Funds

Sequoia Capital, defying the tech market sell-off that’s chilled startup fundraising, is asking investors to commit money to two new U.S.-focused funds, according to two people familiar with the matter.

The Menlo Park, Calif.-based venture capital firm behind Airbnb and DoorDash expects to dedicate $1.5 billion to a U.S. growth fund focused on more mature companies, the people said. It’s also planning a $750 million fund focused on earlier-stage deals, one of the people said. The firm expects to close the new funds in July.

They’re the latest of what Sequoia is calling “sub-funds,” launched after the firm overhauled the structure for its U.S. and European business. In a bid to make it easier to hold stock in companies after their initial public offerings, Sequoia set up an evergreen main fund called the Sequoia Capital Fund. The firm is now inviting investors in that fund to place their money in these new sub-funds.

www.theinformation.com • Share

Why we’ve raised our $158M Series C to invest in the next generation of co-founders — Entrepreneur First

Entrepreneur First (EF) is the best place in the world to find a co-founder and start a startup from scratch. We are excited to announce we’ve raised a $158 million Series C round from a global alliance of some of the world’s top technology founders and investors. They include: Patrick and John Collison, co-founders of […]

www.joinef.com • Share

Wise’s Taavet Hinrikus among four co-founders in group seeking to disrupt traditional venture capital in the region

Plural launches €250mn entrepreneur-led fund for European tech start-ups — Financial Times

Four European entrepreneurs have launched a €250mn fund to back tech start-ups across the region, seeking to disrupt the traditional venture capital model by creating a peer-to-peer investment platform. Called Plural, the new fund’s co-founders are Taavet Hinrikus, co-founder of the international payments company Wise; Ian Hogarth, the co-founder of Songkick; Sten Tamkivi, the co-founder of Teleport; and Khaled Helioui, the former chief executive of Bigpoint. The group aims to invest in more than 25 start-ups over the next 18 months, taking early-stage stakes of between €1mn and €10mn. If successful, Plural will enlist dozens more entrepreneurs as investors and raise bigger funds to boost the European start-up sector. The move comes during a tech downturn which has led many VCs to slow investment, complaining that it has become difficult to value start-ups at a time of turmoil in public and private markets. But Hinrikus, who last year floated Wise in London at a valuation of close to £9bn, said the fund was a response to the European start-up sector beginning to mature like Silicon Valley, with one generation of successful entrepreneurs backing the next.

www.ft.com • Share

Stock-Exchange Startup Gets $100 Million Investment Funded by Walton Family Member — The Wall Street Journal

The Long-Term Stock Exchange, a Silicon Valley firm trying to push for sustainable investing, said it raised $100 million in June from James Walton, part of the famed family associated with Walmart Inc. WMT -0.16%▼

The investment comes as traditional venture-capital firms are pumping the brakes on funding startups right now, wary of taking on new risk when the markets and economy appear to be in a tenuous position. Companies are instead having to strike deals at big discounts to their prior funding rounds, cut costs or look to less common investors, such as corporations, to write checks.

Mr. Walton, the grandson of Walmart founder Sam Walton, is a philanthropist and conservationist, a co-leader of the social impact fund Wend Collective. He and The Space Between, the venture fund with which Mr. Walton partnered to provide the funding, started discussions with the exchange months ago.

The exchange was talking to Mr. Walton, TSB and several other investors about a Series C funding round this winter when the markets “dropped out on us,” said LTSE founder and chief executive Eric Ries. Other investors who said they would participate in the funding round backed out, skittish from a stock market roiled by soaring inflation, a war between Russia and Ukraine, and a swift retreat from fast-growing companies, including most tech stocks.

www.wsj.com • Share

Normalyze’s multicloud management tools aim to tighten security and lower cost | VentureBeat

Data security has become more complex due to the proliferation of data, an explosion of microservices, rapid cloud adoption, hybrid work environments, compliance, remote work and more.

“Today’s enterprises find their data scattered throughout their various cloud environments with limited visibility of where sensitive data resides. It’s a massive problem that current cloud security offerings aren’t equipped to handle,” said Amer Deeba, cofounder and CEO at Normalyze.

“We built Normalyze to classify and secure sensitive data across all public clouds,” Deeba said. Normalyze announced today that it’s coming out of stealth with $22.2 million in series A funding. This round brings the company’s total funding to $26.6 million to date.

“Our graph-powered platform is a hub that connects all data with assets, identities, accesses, misconfigurations and vulnerabilities to help security teams continuously discover sensitive information, determine attack paths and automate remediation efforts to secure it,” said Ravi Ithal, Normalyze cofounder and CTO.

venturebeat.com • Share

Bad News

Even A16z Is Slowing Its Investing Pace

Andreessen Horowitz is one of the most-recognized venture capital firms in Silicon Valley and it just keeps growing. But amid a broader pullback in venture investment, the firm also appears to be slowing down its investing pace this quarter, at least compared to where it was last year.

To be clear, a16z hasn’t hit the brakes. In fact, it’s still one of the most active investors in the United States, according to Crunchbase data, along with Tiger Global Management.It’s just not investing at the same rapid pace it adopted last year, according to our data.

The firm has participated in 46 funding rounds totaling around $2.5 billion so far in the second quarter, the lowest levels since before 2021, Crunchbase data shows. The number of rounds it has participated in and the amounts raised in those funding rounds is also down quite a bit from the first quarter of this year, when the firm participated in 62 funding rounds that totaled around $6.1 billion.

Andreessen Horowitz did not respond to a request for comment or to verify our data.

news.crunchbase.com • Share

‘Put up the for-sale sign,’ more VCs tell founders as market sours — PitchBook News & Analysis

After years of telling their portfolio companies to grow at all costs, investors are dishing out an entirely different type of advice.

Cut expenses, borrow venture debt, or raise additional capital at a flat or even slightly lower valuation than the previous round.

But if after trying to take those steps the startup is still at risk of running out of cash in 12 months or less, then some investors are telling companies to resort to even more drastic measures: try to sell to a strategic buyer at a discount rather than risk going out of business.

“I’ve called founders [to say], ‘I think you should sell,’” said Chris Farmer, a partner and CEO at early-stage firm SignalFire. “A sale could be attractive to founders because they don’t have to lay off everyone, and investors can get some or all their money back. It’s a soft landing.”

Some startups that are short on capital are trying to raise a financing round and run a sale process simultaneously, said Wayne Kawarabayashi, a partner and head of M&A at Union Square Advisors, a technology-focused investment bank.

“There are a lot of these dual-track conversations now,” Kawarabayashi said.

So far, there haven’t been many low-priced acquisitions in this market cycle. But we may soon see more sales like that of Tile, in which investors barely make their money back. Tile, a developer of tracking devices for personal items, was sold to Life360 for $205 million. Prior to the January sale, the company had raised a total of $150 million from investors like Bessemer, GGV and Khosla Ventures, according to PitchBook data.

pitchbook.com

Substack cuts 13 jobs to avoid raising more venture capital — TechCrunch

The newsletter platform Substack laid off 13 employees today, mostly in HR and writer support roles.

Co-founder and CEO Chris Best informed the company after holding meetings with the affected employees. The meetings also included founders Hamish McKenzie and Jairaj Sethi. That’s probably a better way to deliver the news than some other companies’ approaches (cough, Coinbase), but the news is still rough for a company that raised $65 million from Andreessen Horowitz (a16z) just last year. Even then, we were skeptical about how the company managed to earn a $650 million valuation so soon.

Like several other companies that boomed in a time when venture capital flowed more freely, Substack must figure out how to survive in a hostile economic time.

Substack reportedly tried to raise another venture round as recently as last month, but the platform chose not to take on more funding. According to The New York Times, Substack earned about $9 million in revenue in 2021, which comes from the 10% cut it takes from writer subscriptions. Aside from a 3% credit card processing fee, that means that Substack writers are earning around $90 million a year — though the top 10 writers earn $20 million of that pile of cash. These figures would have made it challenging for the company to raise at a higher valuation than its last round.

techcrunch.com • Share

Unity lays off 4 percent of its workforce to realign its resources

Unity has laid off hundreds of employees in its offices across the globe, according to Kotaku. The video game software development company known for its popular game engine has reportedly let around 300 to 400 staffers go so far. Layoffs are still ongoing, sources said, so those numbers may be higher by the time the company is done. Unity has confirmed to Engadget that it’s “realigning some of [its] resources,” which has led to the dismissal of approximately 4 percent of its entire workforce. That’s consistent with the report that it has let around 300 people go, since its LinkedIn page lists 8,048 employees.

The company told Engadget:

“As part of a continued planning process where we regularly assess our resourcing levels against our company priorities, we decided to realign some of our resources to better drive focus and support our long-term growth. This resulted in some hard decisions that impacted approximately 4% of all Unity workforce. We are grateful for the contributions of those leaving Unity and we are supporting them through this difficult transition.”

While the mass dismissal affects Unity’s entire workforce, Kotaku said it’s mostly concentrated on its AI and engineering divisions.

www.engadget.com • Share

Startup of the Week

Pave, whose software analyzes HR data to help companies close pay and equity gaps, raised a $100M Series C at a $1.6B valuation and acquired rival Option Impact

Allison Levitsky / Protocol:

Option Impact, a benchmark compensation product from Advanced-HR, has a new owner. — Pave, a fast-growing Option Impact competitor …

www.techmeme.com • Share

Tweet of the Week

That Was The Week - The Podcast is for paid subscribers to That Was The Week