The only way to understand this is by knowing: Meta already has two (!!) AI labs who are already at existential odds with one-another and both are in the process of failing spectacularly.
One (FAIR) is lead by Rob Fergus (who? exactly!) because the previous lead quit. Relatively little gossip on that one other than top AI labs have their pick of outgoing talent.
The other (GenAI) is lead by Ahmad Al-Dahle (who? exactly!) and mostly comprises of director-level rats who jumped off the RL/metaverse ship when it was clear it was gonna sink and by moving the centre of genAI gravity from Paris where a lot of llama 1 was developed to MPK where they could secure political and actual capital. They've since been caught with their pants down cheating on objective and subjective public evals and have cancelled the rest of Llama 4 and the org lead is in the process of being demoted.
Meta are paying absolute top dollar (exceeding OAI) trying to recruit superstars into GenAI and they just can't. Basically no-one is going to re-board the Titanic and report to Captain Alexandr Wang of all people. Its somewhat telling that they tried to get Koray from GDM and Mira from OAI and this was their 3rd pick. Rumoured comp for the top positions is well into the 10's of millions. The big names who are joining are likely to stay just long enough for stocks to vest and boomerang L+1 to an actual frontier lab.
I wouldn't categorize FAIR as failing. Their job is indeed fundamental research and are still a leading research lab, especially in perception and vision. See SAM2, DINOv2, V-JEPA-2, etc. The "fair" (hah) comparisons of FAIR are not to DeepMind/OAI/Anthropic, but to other publishing research labs like Google Research, NVIDIA Research, and they are doing great by that metric. It does seem that for whatever reason that FAIR resisted productization, unlike DeepMind, which is not necessarily a bad thing if you care about open research culture (see [1]). GenAI was supposed to be the "product lab" but failed for many reasons, including the ones you mentioned. Anyways, Meta does have a reputation problem that they are struggling to solve with $$ alone, but its somewhat of a category error to deem it FAIR's fault when FAIR is not a product LLM lab. Also Rob Fergus is a legit researcher; he published regularly with people like Ilya and Pushmeet (VP of Deepmind Research), just didn't get famous :P.
FAIR is failing. Dino and JEPA at least are irrelevant in this age. This is why GenAI exists. GenAI took the good people, the money, the resources and the scope. Zuck tolerates entertains ideas until he doesn’t. It’s clear blue sky research is going to be pushed even further into the background. For perception reasons you can’t fire AI researchers or disband an ai research org but it’s clear which way this is headed.
As for your comparisons, well Google Research doesn’t exist anymore (to all intents and purposes) for similar reasons.
This is why GenAI exists. GenAI took the good people, the money, the resources and the scope. Zuck tolerates entertains ideas until he doesn’t. It’s clear blue sky research is going to be pushed even further into the background
I agree with most this, I just think we have different meanings of failure. FAIR has "failed" in the eyes of Meta leadership in that they have not converted into a "frontier AI lab" like Deepmind, and as a result they are being sidelined (much like Google Research, which I admit was a bad example). But the orgs were founded to pursue basic research and I think it's not the a failure of the scientists at FAIR that management has failed to properly spin out GenAI. Of course, it sounds like your metric is "AI/LLM competitiveness" and we have no disagreements that FAIR is failing on that end (I just don't think its only important or right metric to be judging FAIR).
* Normatively, I think that it's good to have monopolistic big tech firms be funding basic open research as a counterbalance to academia and also because good basic research requires lots of compute these days. It feels somewhat shortsighted to reallocate all resources to LLM research.
* DINO and JEPA aren't particularly useful for language modeling, but are still important for embodiment/robotics/3D, which indeed seems to be the "next big thing." Also, to their credit, FAIR is still doing interesting and useful work on LLMs for encoders [1], training dynamics [2], and multimodality [3], just not training frontier models.
** GenAI took the money, scope, and resources, but not sure about the good people lol, that seems to be their problem.
This is exactly why Zuck feels he needs a Sam Altman type in charge. They have the labs, the researchers, the GPUs, and unlimited cash to burn. Yet it takes more than all that to drive outcomes. Llama 4 is fine but still a distant 6th or 7th in the AI race. Everyone is too busy playing corporate politics. They need an outsider to come shake things up.
The corporate politics at Meta is the result of Zuck's own decisions. Even in big tech, Meta is (along with Amazon) rather famous for its highly political and backstabby culture.
This is because these two companies have extremely performance-review oriented cultures where results need to be proven every quarter or you're grounds for laying off.
Labs known for being innovative all share the same trait of allowing researchers to go YEARS without high impact results. But both Meta and Scale are known for being grind shops.
Can't upvote this enough. From what I saw at Meta, the idea of a high performance culture (which I generally don't have an issue with) found its ultimate form and became performance review culture. Almost every decision made filtered through "but how will this help me during the next review". If you ever wonder about some of the moves you see at Meta, perf review optimization was probably at the root of it.
I may or may not have worked there for 4 years and may or may not be able to confirm that Meta is one of the most poorly run companies I've ever seen.
They are, at best, 25-33% efficient at taking talent+money and turning it into something. Their PSC process creates the wrong incentives, they either ignore or punish the type of behavior you actually want, and talented people either leave (especially after their cliff) or are turned into mediocre performers by Meta's awful culture.
Beyond that, the leaders at Facebook are deeply unlikeable, well beyond the leaders at Google, which is not a low bar. I know more people who reflexively ignore Facebook recruiters than who ignore recruiters from any other company. With this announcement, they have found a way to make that problem even worse.
Interesting that "high-impact" on the one hand, and innovative/successful in the marketplace on the other, should be at odds at Meta. Makes one wonder how they measure impact.
It doesn't matter much how they measure if it's empirical. Once they say the scoring system, all the work that scores well gets done, and the work that resists measurement does not get done.
The obvious example was writing eng docs. It was probably the single most helpful things you could do with your time, but there was no way to get credit because we couldn't say exactly how much time your docs might have saved others (the quantifiable impact from your work). That meant that we only ever developed a greater and greater unfilled need for docs, but it only ever got riskier and riskier to your career to try to dive into that work.
People were split on how to handle this. Some said "do the work that most needs doing and the perf review system will work it out long term." Other said, "just play the perf game to win."
I listened to the first group because I'm what you call a "believer." In a tech role I think my responsibility is primarily to users. I was let go (escorted off campus) after bottoming out a stack ranking during a half in which I did a lot of great work for the company that half (I think) but utterly failed to get a good score by the rules of the perf game (specifically I missed the deadline to land a very large PR and so most of my work for the half failed to make the key criteria for perf review: it had to be *landed* impact)
I think I took it graciously, but also I will never think of these companies as a home or a family again.
These people should better make a lot of money while they can, because for most of them their careers may be pretty short. The half life of AI technologies is measured in months.
This is wrong. OpenAI has almost no upside now at these valuations and there is a >2 year effective cliff on any possibility of liquidity whereas Meta is paying 7-8 figures liquid.
Metas problem is that everyone knows that it’s a dumpster fire so you will only attract people who only care about comp which is typically not the main motivation for the best people.
It means that you can keep those shares even if you leave. Otherwise the term vesting cliff would be meaningless at any startup where the shares are not liquid.
They are yours. That’s a huge difference between a real cliff and illiquid stock.
If you decide you don’t like it, you take what’s vested after the cliff and leave. Even if you have to wait another year and a half to sell, you still got the gain.
Except you can only sell a prescribed amount at an undetermined time. By the earliest possible sell date you have already made 8 figures liquid at Meta.
Anyone know what scale does these days beyond labeling tools that would make them this interesting to Meta? Data labeling tools seem more of a traditional software application and not much to do with AI models themselves that would be somewhat easily replicated, but guessing my impression is out of date. Also now apparently their CEO is leaving [1], so the idea that they were super impressed with him doesn't seem to be the explanation.
OpenAI and Anthropic rely on multiple data vendors for their models so that no outside company is aware of how they train their proprietary models. Forbes reported the other day that OpenAI had been winding down their usage of Scale data: https://www.forbes.com/sites/richardnieva/2025/06/12/scale-a...
Yeah, but they know how to get the quality human labeled data at scale better than anyone — and they know what Anthropic and OpenAI wanted — what made it quality
But then huge revenue streams for Scale basically disappear immediately.
Is it worth Meta spending all that money just to stop competitors using Scale? There are competitors who I am sure would be very eager to get the money from Google, OpenAI, Anthropic etc that was previously going to Scale. So Meta spends all that money for basically nothing because the competitors will just fill the gap if Scale is turned-down.
I am guessing they are just buying stuff to try to be more "vertically integrated" or whatever (remember that Facebook recently got caught pirating books etc).
Yeah, also the industry could come up with their own Scale if they were forced to.
But probs. it just makes sense on paper, Scale's revenue will pay this for itself and what they could do is to give/keep the best training sets for Meta, for "free" now.
Zuck's not an idiot. The Instagram and WhatsApp acquisitions were phenomenal in hindsight.
> The metaverse will happen, IMO. The tech is just not there, yet.
This seems possible, and it just sounds so awful to me. Think about the changes to the human condition that arose from the smartphone.
People at concerts and other events scrolling phones, parents missing their children growing up while scrolling their phones. Me, "watching" a movie, scrolling my phone.
VR/AR makes all that sound like a walk in the park.
“We went outside this weekend. Terrible. I wasn’t hot anymore, the smog was everywhere. House was tiny. No AI to help with conversations and people were unfriendly. I’m staying plugged in, where we can fly amongst the stars on unicorns. Some say it’s fake but I say life has been fake for a while.”
Meta has done great work on the underlying technology of the metaverse, but what they really need is a killer app. And I don't think Meta or really Silicon Valley types have the proper institutional ability or really cultural acumen to achieve it. We think back to Horizon Worlds that looked more like a amateur weekend asset flip than the product of a billion dollar conglomerate.
If it does come, it will likely come from the gaming industry, building upon the ideas of former mmorpgs and "social" games like Pokemon Go. But recent string of AAA disasters should obviously tell you that building a good game is often orthogonal to the amount of funding or technical engineering. It's creativity, and artistic passion, and that's something that someone who spends their entire life in the real world optimizing their TC for is going to find hard to understand.
The prevailing theory is that Meta did a 49% deal so it didn't set off anti-trust alarm bells. In other words, the 49% doesn't give them ultimate power, but you can best believe when Meta tells them to jump, the board and the execs are going to ask "how high?".
Power struggles like this are weird to me. Is kicking the board likely to succeed at 49%? If so it feels like the control percentage isn't the primary factor in actual control.
At 49% I'm certain they would become the largest shareholder, by far. Then allying with another smaller shareholder to get majority - especially as you are Meta and can repay in various ways - is trivial. This is control, in all forms but name.
There's a lot of things shareholders can do to screw over other shareholders. Smaller shareholders are at least somewhat likely to follow along with the largest shareholder, just to avoid becoming their enemies and getting squeezed out.
It's a smart purchase, it's just that I don't see how these datasets factor into super-intelligence. I don't think you can create a super-intelligent AI with more human data, even if it's high-quality data from paid human contributors.
Unless we watered-down the definition of super-intelligent AI. To me, super-intelligence means an AI that has an intelligence that dwarfs anything theoretically possible from a human mind. Borderline God-like. I've noticed that some people have referred to super-intelligent AI as simply AI that's about as intelligent as Albert Einstein in effectively all domains. In the latter case, maybe you could get there with a lot of very, very good data, but it's also still a leap of imagination for me.
I think this is kind of a philosphical distinction to a lot of people: the assumption is that a computer that can reason like a smart person but still runs at the speed of a computer would appear superintelligent to us. Speed is already the way we distinguish supercomputers from normal ones.
I'd say superintelligence is more about producing deeper insight, making more abstract links across domains, and advancing the frontiers of knowledge than about doing stuff faster. Thinking speed correlates with intelligence to some extent, but at the higher end the distinction between speed and quality becomes clear.
If anything, "abstract links across domains" is the one area where even very low intelligence AI's will still have an edge, simply because any AI trained on general text has "learned" a whole lot of random knowledge about lots of different domains; more than any human could easily acquire. But again, this is true of AI's no matter how "smart" they are. Not related to any "super intelligence" specifically.
Similarly, "deeper insight" may be surfaced occasionally simply by making a low-intelligence AI 'think' for longer, but this is not something you can count on under any circumstances, which is what you may well expect from something that's claimed to be "super intelligent".
I don't think current models are capable of making abstract links across domains. They can latch onto superficial similarities, but I have yet to see an instance of a model making an unexpected and useful analogy. It's a high bar, but I think that's fair for declaring superintelligence.
In general, I agree that these models are in some sense extremely knowledgeable, which suggests they are ripe for producing productive analogies if only we can figure out what they're missing compared to human-style thinking. Part of what makes it difficult to evaluate the abilities of these models is that they are wildly superhuman in some ways and quite dumb in others.
It is really more of a value judgement of the utility of the answer to a human.
Some kind of automated discovery across all domain pairs for something that a human finds utility in the answer seems almost like the definition of an intractable problem.
Superintelligence just seems like marketing to me in this context. As if AGI is so 2024.
> It's a high bar, but I think that's fair for declaring superintelligence.
I have to disagree because the distinction between "superficial similarities" and genuinely "useful" analogies is pretty clearly one of degree. Spend enough time and effort asking even a low-intelligence AI about "dumb" similarities, and it'll eventually hit a new and perhaps "useful" analogy simply as a matter of luck. This becomes even easier if you can provide the AI with a lot of "context" input, which is something that models have been improving at. But either way it's not superintelligent or superhuman, just part of the general 'wild' weirdness of AI's as a whole.
I think you misunderstood what I meant about setting a high bar. First, passing the bar is a necessary but not sufficient condition for superintelligence. Secondly, by "fair for" I meant it's fair to set a high bar, not that this particular bar is the one fair bar for measuring intelligence. It's obvious that usefulness of an analogy generator is a matter of degree. Eg, a uniform random string generator is guaranteed to produce all possible insightful analogies, but would not be considered useful or intelligent.
I think you're basically agreeing with me. Ie, current models are not superintelligent. Even though they can "think" super fast, they don't pass a minimum bar of producing novel and useful connections between domains without significant human intervention. And, our evaluation of their abilities is clouded by the way in which their intelligence differs from our own.
Comparing the process of research to tending a garden or raising children is fairly common. This is an iteration on that theme. One thing I find interesting about this analogy is that there's a strong sense of the model's autoregressiveness here in that the model commits early to the gardening analogy and then finds a way to make it work (more or less).
The sorts of useful analogies I was mostly talking about are those that appear in scientific research involving actionable technical details. Eg, diffusion models came about when folks with a background in statistical physics saw some connections between the math for variational autoencoders and the math for non-equilibrium thermodynamics. Guided by this connection, they decided to train models to generate data by learning to invert a diffusion process that gradually transforms complexly structured data into a much simpler distribution -- in this case, a basic multidimensional Gaussian.
I feel like these sorts of technical analogies are harder to stumble on than more common "linguistic" analogies. The latter can be useful tools for thinking, but tend to require some post-hoc interpretation and hand waving before they produce any actionable insight. The former are more direct bridges between domains that allow direct transfer of knowledge about one class of problems to another.
> The sorts of useful analogies I was mostly talking about are those that appear in scientific research involving actionable technical details. Eg, diffusion models came about when folks with a background in statistical physics saw some connections between the math for variational autoencoders and the math for non-equilibrium thermodynamics.
These connections are all over the place but they tend to be obscured and disguised by gratuitous divergences in language and terminology across different communities. I think it remains to be seen if LLM's can be genuinely helpful here even though you are restricting to a rather narrow domain (math-heavy hard sciences) and one where human practitioners may well have the advantage. It's perhaps more likely that as formalization of math-heavy fields becomes more widespread, that these analogies will be routinely brought out as a matter of refactoring.
> It's a smart purchase, it's just that I don't see how these datasets factor into super-intelligence.
It's a smart purchase for the data, and it's a roadblock for the other AI hyperscalers. Meta gets Scale's leading datasets and gets to lock out the other players from purchasing it. It slows down OpenAI, Anthropic, et al.
These are just good chess moves. The "super-intelligence" bit is just hype/spin for the journalists and layperson investors.
I'll believe that AI is anywhere near as smart as Albert Einstein in any domain whatsoever (let alone science-heavy ones, where the tiniest details can be critical to any assessment) when it stops making stuff up with the slightest provocation. Current 'AI' is nothing more than a toy, and treating it as super smart or "super intelligent" may even be outright dangerous. I'm way more comfortable with the "stochastic parrot" framing, since we all know that parrots shouldn't always be taken seriously.
Earlier today in a conversation about how AI ads all look the same, I described them as 'clouds of usually' and 'a stale aftertaste of many various things that weren't special'.
If you have a cloud of usually, there may be perfectly valid things to do with it: study it, use it for low-value normal tasks, make a web page or follow a recipe. Mundane ordinary things not worth fussing over.
This is not a path to Einstein. It's more relevant to ask whether it will have deleterious effects on users to have a compliant slave at their disposal, one that is not too bright but savvy about many menial tasks. This might be bad for people to get used to, and in that light the concerns about ethical treatment of AIs are salient.
> I'm way more comfortable with the "stochastic parrot" framing, since we all know that parrots shouldn't always be taken seriously.
First, comfort isn't a great gauge for truth.
Second, many of us have seen this metaphor and we're done with it, because it confuses more than it helps. For commentary, you could do worse than [1] and [2]. I think this comment from [2] by "dr_s" is spot on:
> There is no actual definition of stochastic parrot, it's just a derogatory
> definition to downplay "something that, given a distribution to sample
> from and a prompt, performs a kind of Markov process to repeatedly predict
> the most probable next token".
>
> The thing that people who love to sneer at AI like Gebru don't seem to
> get (or willingly downplay in bad faith) is that such a class of functions
> also include thing that if asked "write me down a proof of the Riemann
> hypothesis" says "sure, here it is" and then goes on to win a Fields
> medal. There are no particular fundamental proven limits on how powerful
> such a function can be. I don't see why there should be.
I suggest this: instead of making the stochastic parrot argument, make a specific prediction: what level of capabilities are out of reach? Give your reasons, too. Make your writing public and see how you do. I agree with "dr_s" -- I'm not going to bet against the capabilities of transformer based technologies, especially not ones with tool-calling as part of their design.
To go a step further, some counter-arguments take the following shape: "If a transformer of size X doesn't have capability C, wait until they get bigger." I get it: this argument can feel unsatisfying to the extent it is open-ended with no resolution criteria. (Nevertheless, increasing scale has indeed shown to make many problems shallow!) So, if you want to play the game honestly, require specific, testable predictions. For example, ask a person to specify what size X' will yield capability C.
It seems very short-sighted given how far Meta's latest model release was behind Qwen and DeepSeek, both of which relied heavily on automatically generated reasoning/math/coding data to achieve impressive results, not human annotated data. I.e. Scale's data is not going to help Meta build a decent reasoning model.
yes probably. but it already is. there is also an assumption that meta would turn it off. not saying they will or will not just that there an assumption here.
This is by all indications the world's most expensive acquihire of a single person. Reporting has been that Zuckerberg has seen Wang as a confidant of sorts, and has proposed a vision of AI that's said to be non consensus.
Wang didn't get $14b, he only owns about 15% of Scale. We also don't know how much he sold. He could have sold all of his stock (netting him around $4.5b), none, or something in the middle.
It looks like security/surveillance play more than anything. Scale has strong relationships with the US MIC, the current administration (predating Zuck's rebranding), and gulf states.
Their Wikipedia history section lists accomplishments that align closely with DoD's vision for GenAI. The current admin, and the western political elite generally, are anxious about GenAI developments and social unrest, the pairing of Meta and Scale addresses their anxieties directly.
I doubt Scale is interesting by itself. This is all about Alexandr Wang. Guy is in his mid 20s and has somehow worked his way up in Silicon Valley to the same stature as CEOs of multi trillion dollar companies. Got a front row seat at Trump's inaugration. Advises the DoD. Routinely rubs shoulders with world leaders. I can't say whether there's actual substance or not, by clearly Zuck sees something in him (probably a bit of himself).
It's a wild story for sure. Dropped out of MIT after freshman year and starts Scale to do data labeling. Three years later Scale has a $1B valuation and two years after that Wang is the world's youngest billionaire. Nine years after Scale's founding they're still doing less than $1B in annual revenue. Yet Meta is doing a $14B acquihire. There's definitely more than meets the eye. I suspect it involves multiple world governments including the US.
I didn't mean to imply he started it alone. Though his co-founder Lucy Guo is almost as bizarre of a story as Wang himself. I'm curious, what were they doing before data labeling?
> Though his co-founder Lucy Guo is almost as bizarre
Well, kind of. I went to school with Lucy, and she was a completely different person back then. Sure she was among the more social of the CS majors, but the gliz and glamour and weirdness with Lucy came after she got her fame and fortune.
I suspect a similar thing happen with Wang. When you are in charge of a billion dollar business, you tend to grow into the billion dollar CEO.
> what were they doing before data labeling?
They were building an API for mechanical turks. Think "send an api call, with the words 'call up this pizza restaurant and ask if they are open'" and then this API call would cause a human to follow the instructions and physically call the restaurant, and type back a response that is sent back to your API call.
The pivot to data labelling, as money poured into self driving cars, makes some amount of sense given their previous business idea. Is almost the same type of "API for humans" idea, except much more focussed on one specific usecase.
I’m nowhere near fully confident in these rumors… so there’s nothing to spill. I don’t post specific accusations without some completely reliable basis.
i don't know Alex directly that well but i believe his "freshman year" skipped all GIRs and was spent polishing off the most advanced graduate courses in CS theory (18.404), machine learning (6.867), algorithms (6.854), etc.
so basically he did MIT at the PhD level in 1 year.
As a classmate myself who did it in 3, at a high level too (and I think Varun - of Windsurf - completed his undergrad in 3 years also)...
Wang's path and trajectory, thru MIT at least, is unmatched to my knowledge.
That courseload is completely unremarkable for a first-year with experience in competitive programming (like Wang had). I know a dozen people who did the same.
i know a dozen who come close but none who did the same, nor who had the entrepreneurial bent so early... curious who are these people you have in mind?
Alexandr is just a dude, like you or me, with his own life and his own worries and his own problems. He’s more like the rest of us than you seem to think.
Not trying to diminish his academic accomplishments, but it isn't that uncommon for experienced freshman students to just jump straight into advanced topics. If you're the type that has been coding since you were 10, been active in Olympic teams, or whatever, you can probably do just fine in such courses.
If anything, you'd be bored with some undergrad courses.
Meta buys a non-controlling stake and says no customers will be affected but the CEO and others are leaving Scale for Meta. Meta also says they won’t have access to competitor data but at 49% ownership they get major investor rights?
The host on this podcast[0] had a good point about the "investment". It was really a merger, but framed as an investment to sidestep regulators. Key attributes:
These types of "Aaackshually" business strategies are repulsive, and are evidence that these people who wield immense responsibility do not deserve it.
The stake of FB and people now employed at FB at the executive level is clearly over 50% it seems very odd they are convincing anyone this is a minority?
> people now employed at FB at the executive level
I think it's reasonable that this is not counted, unless there's some possible condition on the stock ownership that I'm not aware of. If they ultimately disagree with the decisions from Facebook then they can, in theory, get help from the other stakeholders to override them.
That said, I would not be the least bit surprised if this turned out to be some scheme in which they use a series of technicalities that make the deal look like a merger but "be" an investment.
Perhaps, but it's worth hedging against a potential Trump-Zuck fallout. Also, the statute of limitations for commencing an antitrust investigation is 4 years (15 U.S.C. § 15b).
Reverse acquisition? IE, similar to how Disney "bought" Pixar, but much of Pixar's IP overshadows Disney's IP; or how Apple bought Next and the current MacOS is basically NextOS under the hood.
It's a technique that companies do to avoid disruption: Buy early stage startups, and by the time they could "disrupt" the parent company, the parent company's management is ready to retire, and the former startup's management is ready to take their place.
In what way does Pixar's IP overshadow Disney's? Listing the highest-grossing media franchises [1], Mickey Mouse, Winnie the Pooh, Star Wars, and Disney Princesses are on #2-#5 respectively, while Pixar's top spot is #16 with Cars.
Because, in the 1990s, Pixar's IP was more popular than Disney's. The story (as I remember it from a Jobs biography) was that, in the Disney parks, there were longer lines for Pixar characters than Disney characters.
Someone in leadership (don't remember the name) basically swallowed pride and bought Pixar from Jobs. It was considered a "reverse acquisition" because Jobs had so much stock he technically controlled Disney afterwards.
This was certainly true for animated movies in the 2000s (where Pixar clearly dominated), although not the companies as a whole. Pixar shareholders (including Jobs) owned about 15% after the deal.
This isn't a reverse acquisition, it's just a normal acquisition. Company A (Disney) has many things but is missing one thing (an animation team that doesn't suck), so they buy a company that does have that thing.
It might reduce scrutiny, but not completely prevent it.
Clayton act says
"No person engaged in commerce or in any activity affecting commerce shall acquire, directly or indirectly, the whole or any part of the stock or other share capital and no person subject to the jurisdiction of the Federal Trade Commission shall acquire the whole or any part of the assets of another person engaged also in commerce or in any activity affecting commerce, where in any line of commerce or in any activity affecting commerce in any section of the country, the effect of such acquisition may be substantially to lessen competition, or to tend to create a monopoly."
It does seem likely that the deal was at least partially structured to avoid antitrust scrutiny but my impression is that under the DMA/DSA (I can never keep track of which is which) in Europe Meta is technically a gatekeeper and has different obligations so I'll be curious to see what happens there
If this is marketed as a strategic acquisition for the national interest of the US tech industry in order to counter-act the Chinese trying to catch up on AI then nothing of the sorts will happen.
That's the MO for all these big players. They don't shell out merely for the marketplace advantage, there's always some meta (no pun intended) Gordon Gecko corpo warfare schtick going on in the background.
To quote Peter Thiel, "competition is for losers".
It doesn't really affect the other frontier labs too much because OpenAI and Anthropic rely on multiple data vendors for their models so that no outside company is aware of how they train their proprietary models. Forbes reported the other day that OpenAI had been winding down their usage of Scale data: https://www.forbes.com/sites/richardnieva/2025/06/12/scale-a...
Of all the tech companies, Meta is the most ruthless and shameless. You'd have to be a total fool to trust Zuck, especially Zuck who put billions into AR for not much return and now billions into AI to create lackluster lagging models.
Off base when considering the likes of Palantir and many others.
Not a fan of the person or many of Meta's business practices. But Meta has given a lot back with Llama and PyTorch, among many other open source contributions. Which others in the space are not doing.
> Llama [...] among many other open source contributions
Llama is not Open Source. Don't buy Meta's marketing that's trying to dilute the term. Llama is only available under restrictive terms that favor Meta.
Fair point. I cannot amend my original comment but you are correct in that the weights have restrictions which go against the nature of Open Source software.
React made quite a mess of the web just so we couldn't browse with JavaScript disabled, thereby allowing Facebook to track us through those like buttons that popped up everywhere.
Are there hidden barbs in llama and pytorch too? I'm not close enough to them to know.
Not a fan of Facebook or React (though React Native is IMHO the one eyed among the blind for cross platform mobile development), but I think that's a bit far fetched. I do think Facebook has (or had?) genuinely an engineering culture that wants to give something back.
This is true. I've been to several conferences where FB sent engineers to talk about their open source projects or how they used a particular language or framework.
I remember the conflicted feeling of strongly disliking their products and leadership but liking their contributions. Same energy but more intense in both directions many years later.
From my personal experience, yes, but your mileage may vary. I tried to like Flutter multiple times, but can't. Capacitator etc feel fairly hacky. All the other options are comparatively obscure.
It helps that I like React alright. I don't think it's particularly well designed or enjoyable to use, and I hate debugging React code, but it's manageable with good development practices. Same goes for JS/TS. Not great, not terrible.
React is the defacto standard of web development for a reason. That's not the reason you can't browse the web with JS (it would be Angular if it wasn't React or others). And just because you use React, doesn't mean Meta can track you.
Their point was that (i) React becoming the defacto standard played into the hands of Meta, who are interested in tracking people. (ii) Tracking is made easier by running arbitrary JavaScript in the browser. And (iii) before SPAs were big (pre-React), more people used to completely disable JS in their browser.
Not saying I buy this theory. Just trying to explain what I think they were alluding to, as I had the impression you missed it and went in a different direction.
I'm not sure their tech contributions in any way offset the various scandals they've had with data and like, actively targeting teens when it appears they're in a vulnerable state. Who cares about friggin 'open source' Llama when they've done evil stuff like that. Their 'social credit' is way deep in the red, esp with people who have no knowledge of those contributions.
They are incredibly ruthless and shameless in my opinion.
Yes they would? Mega corps can afford to commoditize various layers which prevents competition from accessing any profit. Meanwhile Meta et al can capture that profit in their own layers instead.
Bread and circuses to keep the people happy while they do they shady stuff behind closed doors. This is millenia old. Can't say that as fact but it certainly looks that way when you examine their record.
Remember when they were into swaying elections, giving extra data to Cambridge analytica? Here's more
First, the only model creators ones who have not "given back" in the way you mean, are OpenAI and Anthropic, everyone else has at least some models in the open.
Second, I would argue that it's strange how we are discounting the contribution of OpenAI and Anthropic, because being the first to show that something valuable is possible actually counts for quite a lot in my book. Competition and open-source copies are nice, but the value add attribution in ai labs feels really strange at times.
What Meta has given, so far, are decent copies, which mostly serve their own needs and are making it harder for the above companies (who actually have to generate revenue through AI efforts, because it's all they do) to exist. And that's fine and all, Meta can do what they want to the degree the law permits, but I have a hard time understanding them as the good guys in the AI space, unless I squint very heavily.
I don't think it's a big stretch to say that Meta has not only been more successful than Palantir at mass surveillance, but has also likely caused a greater magnitude of harm (a lot through negligence) when considering events like the genocide in Myanmar.
I'd trust Zuck if I had a signed, airtight agreement for a large amount of money he paid into an escrow account for something I owned or was transferring ownership.
He's very close to peak homo economicus. (EDIT: this next point is wrong, the oral history I heard referred to Winklevoss pops, not Zuckerberg, and I misremembered) Which makes sense, given his father is deep in actuarial services.
I get that people hate Oracle for a variety of reasons, but this is just such a ridiculous assertion. They've been one of the largest tech companies for multiple decades. Do you honestly believe that a majority of their revenue came from legal settlements from suing their own customers, at any time in their history?
Do you have a citation for this claim? I mean if the company is as absurdly litigious as you're saying, it stands to reason that you wouldn't make unsubstantiated claims about them in a public forum, right?
I'd guess it's something to do with Oracle's licensing policies. My understanding is they'd audit businesses who used their software and bill them an additional fee for violations. Maybe it's not strictly legal settlements but it's plausible that they made more money from these fees than from their regular fees at some point and even ongoing today. (That also lines up with jokes I've heard about them hiring more lawyers than software developers given someone's gotta do the audits.)
No, I do not believe it is even remotely plausible that they have ever made a majority of their revenue from licensing violation fees, especially today, when their total annual revenue is over $57 billion.
Oracle is an enormous company. I'm in my 40s, and literally every non-startup I've worked for in my career has been an Oracle customer, across multiple product lines. They're a 48-year-old company with more than 150,000 employees.
To be absolutely clear, I'm not expressing an opinion here on Oracle or its licensing and auditing practices. I'm just responding to the wild claims about revenue from lawsuits or license violations. Oracle stock has been publicly-traded for nearly four decades, so there's plenty of data available from their earnings statements. If these claims were even remotely based in reality, it would be easy to cite a source.
Maybe a few years ago at <$megacorp> where I work, Oracle requires, as part of their licensing, the ability to scan every machine owned by the company to make sure there is no unlicensed use of any of their software. If any offending installations were found, they would charge the company the cost of the license for every machine. So, thousands of users times $thousands per license.
Even if you had a license for a Java runtime for, say, your Oracle database instance, if that was found to be used for another purpose you'd get hit. Again, for every machine in the entire company, not just the offending one.
Needless to say, there was a huge firedrill to root out any rogue installs.
OK, but that anecdote is orthogonal to your original claim. No mention of a lawsuit or actually having to pay extra fees. And "rogue installs" essentially means "using copyrighted software in a quantity that exceeds what we actually paid for", i.e. theft.
> No mention of ... actually having to pay extra fees.
> If any offending installations were found, they would charge the company the cost of the license for every machine.
I don’t think you read that correctly. To use an analogy, it’s similar to Costco requiring me to pay again for every item in my cart because I forgot to ring up a carton of eggs when I went through self-checkout. Maybe you don’t call that “extra” but I think most people would.
No, I read it correctly, did you? They didn't say they ultimately had to pay any of those fees, just that the violation fees were dangled as a threat. They explicitly said "there was a huge firedrill to root out any rogue installs" which strongly implies they did not actually pay any of those extra violation fees, because they rooted out those license violations before being charged!
So $0 contribution to Oracle's revenue from fees in that anecdote, was my point. (The key word there in my comment was "actually", as in actually paying the fees, whereas you focused on the word "extra" instead. I don't debate that if the fees were actually paid, then yes that is quite obviously an extra fee.)
My original assertion was just that Meta is unlikely to be 'the most ruthless and shameless [of all the tech companies].' There's so much competition out there for that title.
But also for a long time the best available open-weights models on the market - this investment has done a lot to kickstart open AI research, which I am grateful for no matter the reasons.
> especially Zuck who put billions into AR for not much return
While, it's indisputable about the current state of AR/VR. Zuck has a large exetensial risk to Microsoft/Apple/Google. If those companies want to revoke access to Meta's apps (ex [1]) they can and Zuck is in trouble. At one point Google was trying to compete with FaceBook with Google+ and while that didn't work, it's still a large business risk.
Putting billions into trying to get a moat for your product seems like prudent business sense when you're raking in hundreds of billions.
This is a very interesting buy because Scale AI has been spamming anyone and everyone on freelancer platforms; and they don’t have a very good reputation online so far from people they have contracted with.
Just go look at what people say about them on Reddit. It’s rare to find anything positive, or even a single brand champion that had some sort of great experience with them.
Just like Uber, Doordash & co don't have a good reputation among their contract workers. The entire business model is based on exploitation of labor. That doesn't mean it isn't valuable (in a capitalist sense).
No, those were entirely different user experiences when the services you mentioned were gaining traction and finding product market fit.
UberCab and Palo Alto Delivery were both services that had great success at user experiences for everyone involved including drivers, riders, small businesses, people ordering food. These experiences created brand champions who went out and raved about these technological innovations nonstop.
I don’t see any mentions of any positive experiences with Scale Ai here on HN or Reddit.. maybe that’s the reason behind the acquisition?
People on HN aren't the ones driving Ubers, so I'm not sure what experiences you are expecting to hear about. Go talk to actual drivers and you'll find that things aren't exactly rosy.
There were plenty of people on HN who signed up for the app to drive people back home before and after work.
Being able to see your car move in real time on the uber database with >2s lag between your car GPS and customers phone was magical in a way that's hard to describe today.
Lots of things were amazing when there was unlimited VC money flowing in and no expectation of profit. No point bringing it up 15 years later in a new reality.
I just don't get why Scale and/or Alexandr Wang are so important to Meta. Like sure, data is good and all, but does Scale really bring something so unique and valuable to the table? What vision or insight does Wang offer that's worth so much?
Until now I've actually been a believer in the amount of money that Zuck has poured into metaverse investments. I'm not a believer of the metaverse per se, but a believer that innovation takes unafraid capex. The last thing you want to be is scared money like microsoft who chose to scuttle the hololense project over the thought of spending a couple extra billion dollars on it.
But this deal really has left me with my head scratching. Scale is, to put it charitably, a glorified wrapper over workers in the Philippines. What meta gets in this deal is, in effect, is Alexander Wang. This is the same Wang who has said enough in public for me to think, "huh?" Said a lot of revealing stuff like at Davos (dont have the pull quotes off the top of my head) that made me realize he's just kind of a faker. A very good salesman who ultimately gets his facts off the same twitter feed we all do.
On top of what makes this baffling is that Meta has very publicly faced numerous issues and setbacks due to very poor data from Scale that caused public fires in both companies. So you're bringing in a guy whose company has caused grief for your researchers, is not research nor product oriented, and expect to galvanize talent from both the inside and outside to move towards GAI? What is Mark thinking?
Zuckerberg seems to have had all the pieces to make this work but I'm a lot less confident if I'm a shareholder now than a week ago. This is a huge miss.
Sam Altman is a huge risk to META. He has similar morals to Zuck and a much better technical team. If OpenAI turns on the slop generator, they could hit Facebook and Instagram hard. Wang is probably smart enough to help navigate that risk.
$14.3 Billion seems excessive for it to be a pure aquihire play. There's undoubtedly some IP acquisition (or at least exclusive access to certain IP) involved.
It's about 0.85% of Meta's market cap - less than the 1% they paid for (granted, all of) Instagram. They also paid about 1% of market cap for Oculus ($2b into a ~$220b market cap)
Seems about par for Facebook when it comes to company-shifting acquisitions.
Little known secret is they paid $2.7B, not $2B. And Zuck and the FB head of M&A were talking shit about John Carmack’s crazy wife, who was doing his negotiation for him. On WhatsApp no less.
> the weird setup where they only buy non voting shares is to not trigger any regulatory review
Do regulators actually fall for these sort of things in the US? One would expect companies to be judged based on following the spirit of the law, rather than nitpicking and allowing wide holes like this.
>One would expect companies to be judged based on following the spirit of the law, rather than nitpicking and allowing wide holes like this.
The letter of the law is what people follow. The spirit, or intent, of the law is what they argue about in court cases.
If the regulation says 49% and a company follows it, who's to say they're exploiting a loophole? They're literally following the law. Until there is a court case and precedent is set.
The Clayton act explicitly includes partial acquisition as still being covered. "No person engaged in commerce or in any activity affecting commerce shall acquire, directly or indirectly, the whole or any part of the stock... [where] the effect of such acquisition may be substantially to lessen competition, or to tend to create a monopoly."
There may be some other regulations that are avoided by a partial acquisition, but it doesn't bring it wholly outside of the relevant antitrust laws.
I guess "intent" is what matters really. If the intent is to avoid regulatory review and you could prove that intent, then they're trying to exploit it. That in itself should probably trigger a review regardless. If they've arrived at 49% for some other reason(s) than just to avoid regulatory review, then fair enough.
Wang has, seemingly, spent just as much time and energy over the last couple of years on PR stunts and publicity than on Scale itself. Between testifying to congress about how China is an AI risk (duh) and how AI is important (obviously), putting out press releases about joining boards of large orgs, and getting himself invited to trumps second inauguration. A high-billion-dollar story-headline framed as "Meta paying $14 BILLION for this one guy" is the same.
It very much seems it's been an investment in getting himself to be more of a "household name in AI". That is exactly what Meta needs (or at least thinks it needs) now.
I very much believe that there is very little moat in AI (currently, and in the forseeable future short some underlying hardware/etc breakthrough), and the success (from a consumer perspective) will come down to which of the big-cos (Facebook v Amazon v Google v OpenAI v Anthropic/Claude) consumers trust more. Zuck is, to put it mildly, *not* a trustworthy name for Meta to associate to leading the product that they want consumers to trust and depend on for their entire lives.
Whether or not Wang has any more qualifications than 1) is somewhat of a recognized AI name, and 2) is okay at speaking confidently on topics someone briefed him about, I don't think really plays much into this. If he needs help/assistance/etc with any of the meta scale/politics/management/etc, zuck can buy that for him.
What Zuck can't seem to buy (for himself) is some level of trust.
I agree. Slightly amused at the running from one side of the boat to the other. So we're done with the Metaverse now?
(Or maybe the metaverse needs AI bots running around … perhaps scalping tickets or something. In fact I get it though — they're looking for the Next Big Thing — as all big companies are. I even think they're on to it this time. The whole metaverse thing was just so obviously misguided, misspent capital.)
I have a little metaverse experience, and they do relate. If you think of Zuck as a meta strategist, and expand out to where he seems to believe things will be in 20 years, a couple things seem obvious:
* mediated (AR/XR) environments are almost certainly going to be much more popular / used than today, likely in some new device form factors
* Demand for 3D type content and audio and text content will therefore be rising dramatically
Perhaps the least realistic part of Ready Player One was the infinite AAA content floating around; pre gen-AI it was like you’d need 3/4 of the worlds population making digital assets for the other 1/4.
Gen AI changes this, a lot. Avatars, agents, all those are deemed likely to be more compelling as video / imagery gets super cheap to generate as text and audio are now.
The bitter lesson of the AR/XR space is that — hardware is hard. I think it’s a mistake to scoff at something both Apple and Zuck are pouring billions into a priori — even if the markets don’t seem to be working out as expected right now.
I’m writing this on ipadOS beta 26, and the interface tells me that Apple is committing to visionOS type interactions over the next 10 years; the design iconography from the AVP is everywhere now.
Upshot - generative environments, agents and etc. seem likely to me to be big someday — companies with major AR/VR hardware divisions and more data than us don’t seem to be giving up on the space. Practically speaking, a lot of people really want to be able to ‘live’ at least part of the time in a generative reality that they connect to emotionally. I think we’ll see a lot more of it.
All that said, just like there are AI hype waves, and now one that looks like it ‘stuck’, metaverse has these periods. Still an open question if / when one will stick. But I think it’s likely to in the long term.
Spending $15B to hire a 28 year old to build you some AI is certainly a move. You can call Zuck many things, but "afraid to take risks" isn't one of them.
He was spending $5b a year on whatever the metaverse was supposed to be and even renamed the company. Does anyone here use it? I think he weathers what I consider failure well. Or, conversely he can take big risks without too much blowback.
He would still be unbelievably rich even if Meta went bankrupt. He is in the unique position to have majority control of one of the world's largest tech companies and can pretty much use it to do what ever he wants. I doubt he cares much about Facebook past it's ability to generate money at this point.
What is the big risk here? He has the cash to burn and he has full control of his position. Nothing will happen to him if he wastes a few Billions. He is not some poor single mom who has to decide between fixing her car and paying for kid’s Christmas presents
Cash is the least concern. I listened to a podcast about the history of Microsoft and there were times where Gates said "at least it was only money" or something to that effect.
Microsoft floundered an entire decade on mobile and Windows Vista when they were going to lose out on Google that was literally paying OEMs to use their software and Apple, who had a vertical stack and made money off hardware. Huge setback in terms of focus that took them a long time to recover from.
The main constraint is focus of talent to work on one thing. This is a huge move in terms of coordinated effort into this space that may or may not pay off.
I've been in the tech industry a quarter century, I've never heard this "pretty common saying" before, and most importantly I don't think it makes any sense. If anything, tech excels at disruption, where smaller competitors and new ideas are able to solve problems where "just throwing money at it" has failed.
I challenge you to name a tech unicorn who's biggest advantage wasn't the ability to hemorrhage money over a period of time that would've killed any normal business stone dead.
The risk here is that you've now put a person with no track record of success outside of being good at sales in charge of your AI efforts. You're betting that he's going to be the one to attract talent.
The right leadership might be able to get talent to work for a discount. The wrong one would lead to talent not coming at all.
If Meta is known for anything besides user privacy violations it's for taking risks that often pay off. They were laughed at for overpaying for Instagram and Whatsapp, yet both were instrumental to their current success. Their continued bet on VR is still highly criticized, yet they were the first Big Tech company in the space, they're the current market leaders, and I'm sure it will have huge ROI in the near future. So is this bet on Wang, as ludicrous as it may seem now.
> laughed at for overpaying for Instagram and Whatsapp
That's not how it went down. They were laughed at for screwing up so badly that these apps were drinking their milkshake, and then they panicked and paid way more than any fundamental analysis would price these apps at, because they weren't actually buying an app, they were paying a ransom on their monopoly.
> Their continued bet on VR is still highly criticized
Because Zuckerberg thinks people are going to go around wearing his face hugger.
> and I'm sure it will have huge ROI in the near future
The "VR play" is predicated upon VR somehow taking even more time away from its users than cellphones do. The only way it works is if people put it on when they wake up and take it off when they go to bed. Heck, maybe leave it on in some kind of REM-mode so zuck can put ads in our dreams.
Meta "succeeds" as you demonstrated, when they wait for someone else to outflank them, mostly by not being Meta because Meta is creepy and nobody likes it, and then they fire a money bomb at at. The way for VR could have succeeded is if Occulus stayed independent and focused on gaming where it shines for another decade, and then as people start to feel like it could be a building block for something more, snatch it out from under them. Instead Zuck bought it too early and smothered it with his empire of ick.
I've been all for it, look at my comment elsewhere in this thread. For me this is a huge mistake of a transaction that's neither accretive financially nor talent-wise.
This isn't the Instagram or Whatsapp transaction. Scale's been exclusively in the data labeling space.
Let's put this into perspective. OpenAI bought Jony Ive for about $5bln. Meta spent 3x that on Wang.
I'm not familiar with Scale, but data labeling can make or break a ML model. So if Scale is good at this, the $14B investment will pay itself off in no time.
There was quite loud reporting earlier this (or last?) year that Scale's data was so poor that it led to a great deal of setbacks, scrambling, and friction between the two companies. That reporting was at the top of my mind when I read this news, so I was even more baffled.
Imagine being the people at Meta who've had to deal with Scale now seeing Mark buy Scale's CEO for $14bln.
What is convincing you that VR will have huge ROI in the near future? We are over 10 years in to the modern VR era and despite even Meta’s strong device sales it’s still very niche. Apple is trying their hardest and even they had to correct their sales expectations.
The thing is, I can imagine some futuristic version of AI that transforms humanity. But with VR, even in my wildest dreams with all the problems solved, it’s still just second best to smartphones and computers.
Imagine the perfect headset. Tiny, battery lasts forever, photo-realistic. I would still rather browse the Internet on my phone. I’d rather do my work on my laptop. I’d rather watch movies on my TV. What is the VR adding? Nothing but extra hoops to just through to get things done.
The only usecase that makes any sense is gaming. But only some games. It’s just too niche.
> What is the VR adding? Nothing but extra hoops to just through to get things done.
It gives you maximum immersion into a digital world. Rather than view it through a rectangular 2D window, it can encompass 360 degrees of your vision in full 3D. If you don't see how this would be appealing for consuming content, work, entertainment, etc., then I can't convince you otherwise.
VR adoption has always been held back by what is technically possible and how expensive it is. Nobody other than tech enthusiasts wants to wear a bulky headset for extended periods of time. Once we're able to produce that perfect headset that you mention, so that it's portable and comfortable like a pair of sunglasses, at an affordable price, the floodgates will open, and demand will skyrocket.
The same already happened with mobile phones, several times. The cellular phone was invented in the early 1980s. It was heavy, bulky, and expensive, and only business people and enthusiasts used them. It wasn't until the mid-to-late 90s that they got cheap and comfortable for the general public. Then the modern smartphone had several precursors that were also clunky and expensive. It wasn't until the iPhone and Android devices that the technology became useful and accessible to everyone. There's no reason to think that the current iteration is the ultimate design of a personal computer.
The same story is repeated for any new technology. VR itself has seen multiple resurgences in the last few decades. We're only now reaching a state where the vision is technically possible. There are several products on the market that come close. VR headsets are getting smaller, cheaper, and more comfortable, and AR glasses are getting cheaper and more powerful. I reckon we're a few generations away from someone launching a truly groundbreaking product. Thinking that all this momentum is just a risky bet on a niche platform would be a mistake.
> If you don't see how this would be appealing for consuming content, work, entertainment, etc., then I can't convince you otherwise.
I don't, legitimately I don't.
Okay, maximum immersion. And how does that help?
Like even just on the surface having a 360 degree view doesn't do anything. Because my eyes are on the front of my head, so I'm going to be looking forward. Stuff behind me doesn't matter much.
Same thing with 3D. Okay... but paper is two-dimensional, you know what I mean? Something being 3D by itself doesn't mean it's better or contains more information or is easier to use. I'd rather read and write on a two-dimensional surface. Reading and writing is the core of a lot of stuff, so there's goes that.
The test for me really is imagining some usecase and then imagining how it would be on super advanced VR. If you try that, you'll find that 90% of usecases just fail compared to already existing technology. Like imagine some perfect VR tech 5,000 years from now. Okay, now a usecase: programming. I would rather program with a keyboard and mouse and a monitor. I don't want to talk to VR. I don't want a dumbass virtual keyboard, that's worse. The 3D stuff makes no difference because I'm reading text. So even with alien technology, my current computer right now would beat it.
With the phones you mention, when we envision some futuristic technology we can see how the phones would be useful. Same thing with TVs - I mean, people were envisioning wall-wide flat screens in the 60s. But when you do that with VR, the product still isn't very good. That's the difference, in my eyes.
What you're saying makes sense, and I do agree with some of it. But you're not seeing the experiences that a fully immersive digital world can deliver once the technology and UX improves.
Yes, we read and write on 2D surfaces, but a 3D environment allows you to have an infinite number of them. You could be writing on one, with a video playing in the background, while keeping an eye on a stock ticker, all inside a virtual beach, outer space, or whatever you want. You could be having a conversation with someone who looks and feels like they're physically in front of you. Have you seen the new visionOS avatars? They're incredibly realistic. Talking to a 2D video from a crappy webcam feels awfully primitive in comparison.
There are an infinite number of these experiences that we can't imagine yet, which a 2D display simply can't deliver.
As for HIDs, we'll figure it out. Voice and touch will become far more useful and user-friendly. Remember how touch keyboards on smartphones were unbearable to use initially, and tech geeks like myself strongly preferred a device with a physical keyboard? Well, text prediction and haptics got a lot better, and we invented swipe typing, so the experience improved considerably. I'm typing this on a swipe keyboard from my phone, and while I would prefer to use a keyboard on a real computer, I also like being able to type with one hand from bed. :)
So I'm sure we'll invent input mechanisms that feel natural and friendly to use in VR as well. In the meantime you can also use a physical keyboard. There are many software developers who have adopted AR glasses, with a phone and keyboard as their mobile workstations. The tech is almost there.
If you think about it, a 2D board with keys you press to compose words is an archaic method of inputting data into a machine. It's a remnant from typewriters dating back to the 19th century. They're far from being an optimal method for doing the type of things we use computers for today.
Ultimately, we can have different opinions on whether we want these experiences or not, but the reality is that this future is inevitable, for better or worse. As we move towards transhumanism, fully immersing our visual sense in a digital world is an obvious first step. The current iteration of devices that we're used to is merely ~50 years old, and ~20 for mobile devices. It's far too early in our technological evolution to consider these the best designs we can produce.
Sure, but this is a different value proposition. FB paid $1B for Instagram, which was trendy, growing fast, and already had 30 million users. FB paid $19B for Whatsapp, which was already established worldwide with ~400 million users. These acquisitions were very much in-line with FB's core product. The people saying it was risky were mostly just saying that it was a waste of money and that FB could have just beaten their competition instead of buying them.
And bringing up VR is probably not the best comparison to make- sure, Meta is a leader here, and they are competitive with their AI team too. But "I'm sure it will have huge ROI in the near future" is just saying that it hasn't paid off and they don't have an obvious path to getting there. Shoving VR and the Metaverse into everyone's face hasn't paid off for several years, and the VR segment as a whole has remained niche despite being around for decades.
This acquisition is different- AI is not Meta's core product, it's just something hot right now and CEOs are trying to figure out how to stuff it into their products and hoping they can figure out how to make money later. Plus, they paid a pretty big chunk of money for a company that does, what? Cleans data for LLM training? Meta's Llama team clearly has a good data group already. They paid for a few employees that are clearly popular amongst the executives in the tech industry, but I don't know how this will go in terms of attracting other talent. Unless Wang is bringing something secret along with him, I think this one is an overpayment- Meta will need to both figure out how AI makes them money and Wang will have to attract several billion dollars worth of talent to the team. I'm skeptical that people will talk about this the same way they will about Meta getting Yann LeCun to work for them for a lot less money.
Facebook couldn't beat them on merit because it's not very good at what it does. It does, however, have money because it was good at one thing one time, and therefore it could solve its inability to execute with M&A.
'Laughed at', but one of the things that's probably very likely also true is 'Now a prime target for antitrust violations' especially Whatsapp
Acquisitions do happen but it's telling when the people whose company you bought publically disparage you (in other words it wasn't a peaceful takeover)
>If Meta is known for anything besides user privacy violations it's for taking risks that often pay off. [...] Their continued bet on VR is still highly criticized, yet they were the first Big Tech company in the space, they're the current market leaders, and I'm sure it will have huge ROI in the near future.
Are you using something that hasn't yet paid off as an example of how their big risks often pay off just because you are personally sure it will have huge ROI?
But I'm not actually sure I agree with the premise.
What risks is Meta known for taking? Instagram and Whatsapp purchases were defensive moves; they were laughed at for the prices not for risk.
Here they are similarly being laughed at for the price.
Is there much risk beyond that?
If Instagram had petered out and people had stayed on Facebook proper, they would've been fine. Same with Whatsapp. It's not like they've been trying to push people away from their core Facebook product. More the opposite - they've used acquisitions to try to push Facebook accounts to more people.
Compare to Apple, letting Mac software flounder for a while while focused on growing the iPhone and iPad business. Risky, worked out. Compare to Microsoft, going down years of dead-ends trying to come up with a next-gen operating system - a big part of their core bread-and-butter - and then having to release the generally-panned Vista because they bet too big on stuff they couldn't realize with Longhorn. Risky, failed. Compare to Snap, even - turning down Meta cash for independence. Risky, kinda meh results? But adding another social media app to a social media company's portfolio? Less so.
VR, on the other hand, does seem like the closest analog here. Buying their way into a non-core-competency space. There they bought the undisputed leader but it still hasn't paid off to date. Here? Eh....
What the commenter is saying is that this is no risk at all because $14B is negligible money for Meta at a year-long scale. It can always be written off as an investment that didn't work. In a company with $1.73T market cap, this is sometimes the loss you get in a single day of trading.
Yes, $14B can be considered negligible, but it's a signal. My bet is that it's not a great one. Wang has been great at courting clients, time will tell us about how that translate to leadership.
Meta already had an AI division led by the venerable Yann LeCun - someone with actual AI bona fides. I'm not seeing any info about what this does to LeCun's position in Meta.
I don’t think either Demis or Ilya are available for $15bn. They’re already both comfortably billionaires. Demis seems a sensible candidate for heir to the top job at Google in the long term. Ilya is away focusing on super intelligence.
It’s not clear to me why either would take a subservient role in a company flailing incoherently around AI, rather than stick with the incredibly high-leverage opportunities they both have now.
Spending $15B is a risk. Yes they have the money, but we're talking a quarter of Meta's annual income. That's not nothing.
And money concerns aside, Meta needs to be a major player in AI. If they have made the wrong bet with Scale AI & Wang then the company will suffer in the long term.
Honest question, why do they so existentially need to be a major player in AI? It's a social network that connects people, serves UGC and some spam/ads, and sells advertisement. Same but with photos for IG, same but with messages for Whatsap. Which part of this will die without AI? If they are obsessed with chatting with an AI bot on Whatsapp, just plug in grok or openai like Telegram, is that the killer feature worth bazillions of dollars?
(everything else seems like a failed experiment, VR, Libra, Facebook phone, whatever, nobody even remembers half these things)
You're thinking in the wrong scale. Meta is a $1.7T company, for them a $15B investment is less than 1% of the company. In the span of a year, this is negligible money.
I genuinely struggle to understand how that will affect him in any way. Not even any meaningful way, I mean, how could that possible change anything about his life, in any way?
I don't think people understand that once you're a billionaire with full ownership of your business and no risk of being ousted, making or losing billions is irrelevant.
Maybe, but it doesn’t seem to stop them from actually looking like dumbasses. But that wealth attracts fans who constantly proclaim that their latest idea is brilliant.
Maybe we should pity the poor billionaires, hopped up on T or ketamine and trapped in an echo chamber…but I’ll think they’ll be ok.
In light of these (accurate) critiques, I think I should've gone with my original wording, which referred to them still caring about their legacy regardless of how many billions they had. That's more what I was going for, but I dumbed it down, apparently too much.
The risk is the lost time by betting on the wrong horse. I don't know much about Wang, but the current phase of the AI race will likely shake out winners and losers of the tech industry who persist for many years to come.
Being first to achieve certain milestones matters a lot.
I actually ran into the Zuck eating Thai(could be wrong) food in Palo Alto at night. He was having dinner with his wife at the restaurants outdoor seating, sure looked risky for someone as important as him.
OpenAI uses scale via eg data made by humans through outlier. Part of this move could probably be seen as starving competition from data as much as buying talent at scale.
I was looking for side angles also. Thinking the size of the deal gives substantial information rights, so there is likely good visibility into competitors surface areas.
We intentionally didn’t use them at all for Llama 2 and mostly avoided using them for Llama 3, but execs kept pushing Scale on us. Total mystery why until now, guess this explains it.
I guess Mark Zuckerberg likes Alexandr Wang a lot. They have a lot in common. They both value intensity and are willing to engage in morally dubious tactics. The culture of Scale sounded quite a bit like Meta these days (and not Meta in mid 2010s) and may indeed be what Zuckerberg envisioned Meta's culture should be. So even if Scale's product isn't the best, it probably seemed like delegating to a copy of Zuckerberg himself, so it just "felt right".
However, a top research lab needs to be competitive yet still have an environment that fosters intellectual honesty. Meta Gen AI did not seem like that, and I don't think Scale's culture is like that either.
It was initially killed by a software filter. Those are tuned more strictly for (some) new accounts. It had nothing to do with the content of the comment, though admittedly that is less "interesting".
Because he put a big "AI" button on every single one of Meta's apps and surfaces. I'd bet that most of the usage is accidental. Great way to show inflated user counts in your earnings reports and get some directors promoted, sure, but not a long term strategy.
True, that AI button is shoved pretty violently in unexpected places, and surprises me in an unpleasant way, since I've never considered Meta itself as a place to search for information, let alone something trustworthy.
But this is actually interesting. Asking for medical information in the past was the realm of Google Search, now a combo of Google/Gemini/Chatgpt/whatever. Could it be they are going to try to bite off a chunk of that market? kind of like how they chose not to compete with Google search in 2010's. But now are taking another pass at it?
I don't really think Meta ever had a vision beyond "Facebook is a social network to connect people". Since then, their strategy has primarily been driven by their fear of being left behind, or of losing the next platform war. Instagram, Whatsapp, Threads, VR, AR, and now AI, they all weren't driven by a vision as much as it was their fear of someone else opening a door to a new market that renders them obsolete. They are good at executing and capturing the first wins, but not at innovating, redefining a market, or pushing the frontier forward; which is why they eventually get stuck, lose direction, and fall behind (Tiktok, Apple Vision Pro, AI).
Yes, but they’ve definitely made a big contribution to AI / LLMs. I just don’t understand how they plan on monetizing upon things, apart from “better AI integration inside their own products”.
Are they planning to launch a ChatGPT competitor?
It seems like this acquisition is focused on technology, but what’s the product vision?
Mark wants to own platforms. He always has. That’s why they tried to make a phone, networks, VR headsets, horizon worlds and now glasses.
AI is just their vessel to draw people in. It’s the flash that gets people on board. It’s the commoditizing your complement, in that they want to undercut the competition and have the money to do so, as a means to pull people in rather than lose them to OpenAI or the like who are also trying to build platforms.
Put another way: these companies want to be the next iOS or Android, and they are doing what they can to be as sticky and appealing as possible to make that happen.
Meta is a huge nation-state of a company, like Apple or Google, but its actual sources of income are arguably precarious: in the past decades new social media platforms have crept up and become really popular pretty frequently. Ai and Vr are mostly ways to find new sources of income: Meta has the means to outinvest smaller companies like Anthropic, but not the obligation to fit it into an existing product, like Apple.
They sell ads. Their strategy is to use AI to take over more of the marketing process. They want to move spend from in-house marketing (creative, strategy, analytics) to Meta.
> What’s Meta’s strategy here? What’s their vision?
I don't get it, either. Facebook/Instagram/WhatsApp are ways to communicate with people you know, and they have a monopoly on that. (Well, Instagram is also softcore porn and product placement...)
TikTok beat them as mindless entertainment, showing people videos they're likely to watch until they end, and Zuck freaked out. Sometimes people would rather just watch TV than hang out with their friends! OMG! TikTok's bottleneck is that humans have to create the videos, so if Zuck can generate videos to maximize watch time, he wins.
Paying billions of dollars for a data-labeling company, though... Well, I guess it's not easy to put together a bunch of digital sweatshops in Kenya and the Philippines, but is it worth that much?
Meta monetizes content. AI makes it easier and cheaper to create content. If everyone has access to high quality AI, high quality content may be more plentiful and that content can be posted on Meta's platforms, which would make it more money.
Still confused, i show up to "consume content" from people i follow, not from Meta. Sure, occasional trash and spam and ads, and "recommended", and "promoted", but mostly things that people post. If content creators still come to post on say Instagram, which provides distribution and monetization, how does it matter which tools they used? Should Meta then try to acquire say Adobe Photoshop too, to produce better IG content?
When a company reaches a certain size they basically become a bank. Meta owns a bunch of social media properties and the long term prognosis for that industry is not great. It would make sense to get into other areas if they can do it.
> What’s Meta’s strategy here? What’s their vision?
The metaverse was their strategy. Then AI hype took over Silicon Valley and the unloved under-resourced AI team at Facebook became the stars of the show. Meta are now standing on the shoulders of those teams and the good will they generated from their foundational and open research efforts.
An AI first strategy from Facebook would not have involved a rebrand or open sourcing any research or models and would probably have looked a lot like OpenAi or Grok.
I dont understand, why would they make a super-intelligence group instead of something more ambitious like a super-super intelligence group or supreme-mega-intelligence group? Zuck is clearly not thinking this one through.
Word on the street is scale.ai knows which data sets/data approaches anthropic and openai used to do their RL reasoning training. Meta is paying for that know how/information.
People are saying this is an acquihire, and the article states that Scale AI's CEO will join Meta in a "top leadership role" in their new Superintelligence lab. Does this mean Lecun is stepping down?
Superintelligence, really? I'm really looking forward to their "super intelligent" stochastic parrots — or stochastic llamas, as the case may be. The only thing "super" here is the ludicrous hype. It's totally out of control.
Meta buying their way into trends generally seems to pan out (WA, Insta, Oculus). Any reason to think this will be different? I’m not familiar with Scale but the particulars of this deal seem odd to me.
Sounds like they're getting paid based on his note to employees:
> "The proceeds from Meta's investment will be distributed to those of you who are shareholders and vested equity holders [...] The exceptional team here has been the key to our success, so I'm thrilled to be able to return the favor with this meaningful liquidity distribution."
Honestly if this acts as a liquidity event for a whole bunch of current employees, while at the same time giving off "Meta hand picked the CEO and whoever they felt were the best AI engineers and jumped ship" energy, I wouldn't be tooo surprised if current "scaliens" view this as the inflection point, and decide it's not worth staying for the other ~51% of their shares.
Looks like they are distributing a dividend to shareholders (14$, well below $25), and then diluting everyone.
Has anyone heard a bull case on being a minority shareholder in Scale.ai after this deal? Seems a bit like late stake investors are getting thrown under a bus.
Reminds me of "Don't dig for the gold, sell the shovels".
Could also be read:
> Meta spends 10% of last year's revenue to acquire 49% of a top AI data company and poach their leadership, to ensure they are a key player in what could be a ~5-trillion dollar industry by 2033.
Meta has a history of this. Acquiring Oculus (and leaning in on VR), Ray-Ban partnership (and leaning in on AR)... etc.
These all just seem like decisions to ensure the company's survival (and participation) in whatever this AI revolution will eventually manifest into.
What top AI company? Certainly not Scale, right? You realise that frontier labs don't really use Scale anymore exactly because they can't be trusted not to sell their secret-sauce human data collection protocols. No-one in the industry takes this guy seriously.
It's always a warning sign where the only thing I know about a CEO is how many podcasts and media events they do each week, and nothing about their business.
Bringing up Oculus and VR is quite fitting, because I think it's the same problem. Meta is attempting to find their next business, but like with social media they don't really have a plan. It worked out well with Facebook and some of the purchases surrounding social media, but it was never a clear path to profit, so they slapped ads on it.
Why does Meta want VR to work? Create the Meta-verse? We're back at why, what problem does it solve? Same with AI, what's the goal here, besides being an AI company?
Just a thought, but VR/AR is constantly recording video and audio.
It wouldn't surprise me if at least some of that data is being piped back to Meta. Data that can latter be used by LLMs to train on.
Even if this isn't enabled on consumer models, on the corporate side it can make sense. Say you're a risk adjuster for a factory. Walk around with your VR headset. In real time MetaOshaHelper can identify issues, you can tag them yourself.
Then send the video back to your on prem LLM for data processing. New hires get a VR headset which can use this data for help on boarding.
Or... Robots will use the data and replace human workers entirely.
I sort of doubt that most business would want that. Sorry to latch on to one specific thing in an interesting comment. But just imagine having AI tracking in the workplace, e.g. OSHA violations, violations of building code and workplace regulations in general. You'd have shitty manufactures, builders, trucking companies, kitchens, warehouses and everything in between begging you to stop.
Occasionally you're going to ignore things that get flagged, but I would love an AI to say oh by the way that machine over there isn't latched on correctly and can fall over if not corrected.
This deal brings into focus whether the shovels are data or GPUs. Advantage to data comes, surprisingly, in perishability: a GPU fleet remains cutting edge for only one product cycle.
Roblox, Rec Room, Epic/Fortnite are worth about 10-20% of Meta. There is a market there, Horizon just hasn't worked out and they don't have anything like the amount of technology behind Unreal Engine/Fortnite or even Roblox, closer to Rec Room but without the game design chops.
I mean have you seen the interview he did with Theo Von? The guy is a straight up Alien in the way he talks and acts, all those memes about him being a lizard aren't exactly far off.
He was isolated from the real world starting at around age, what, 22?
I'm all for calling out his random flailing in this space for what it is, but it always strikes me as strange when people are surprised that he's weird and robotic. I'm betting he never learned how to actually interact with other professional humans.
He's lived in a golden tower surrounded by people who agree with him or want something from him since he was 21 or 22. Imagine what you would be like if you didn't have any struggles from such an early age. Imagine what your personality would be like if you didn't have substantive, non-transactional, human interactions since the age of 22.
I kind of feel bad for the guy. His wealth and fame have ensured that he would never be normal, or anything approaching normal. Think about it - how does he even know if he has a bad idea? Do you think there are a ton of people around him that want to call out whatever dumbass idea he has? I doubt it. B-b-b-illions of dollars tends to flavor conversations, I would imagine.
That being said, I don't feel that bad, because he can literally change the world and chooses not to.
> Today's investment also allows us to give back in recognition of your hard work and dedication to Scale over the past several years. The proceeds from Meta's investment will be distributed to those of you who are shareholders and vested equity holders, while maintaining the opportunity to continue participating in our future growth as ongoing equity holders. The exceptional team here has been the key to our success, so l'm thrilled to be able to return the favor with this meaningful liquidity distribution.
Is this the same company that has their recruiters (or whatever the hell they're called) spamming me incessantly via all my emails, even the throwaway ones I've used literally one single time that they presumably got via some unscrupulous means, about "annotating" data for training AI? And their rate is something laughable like 20 euros an hour?
We truly live in a clown world when a casual $14B is being chucked at garbage like this, I hope those Iranian nukes turn out to be real this time and I get to be the first in line to be cleansed via nuclear fire, 'cause I'm tired boss.
Seems like desperation to convince the industry that they're still relevant in AI after the fiasco that was Llama4. Scale doesn't create foundational models, they compile proprietary datasets that everyone has already licensed and trained on - not a lot of reoccurring value. Maybe this slows down competitors a bit but I doubt it.
Get Plus
You said:
Usernames can only contain letters, digits, dashes and underscores, and must be between 2 and 15 characters long. Please choose another.
Create Account
username:
ChatGPT said:
It looks like you're trying to create a username and the system has specific rules:
Allowed characters:
Letters (A–Z, a–z)
Digits (0–9)
Dashes -
Underscores _
Not allowed:
Spaces
Symbols like @, ., !, #, etc.
Length: Must be between 2 and 15 characters.
Here are some username ideas that follow the rules:
Sky_Rider
tech-nerd23
LunaWolf
ace_92
PixelDash
Neo_Trek
JetStream7
coder_boy
Jade-Dragon
blink42
Would you like suggestions based on your name, interests, or a theme (e.g. gaming, tech, fantasy)?
You said:
Meta invests $14.3B in Scale AI to kick-start superintelligence lab (nytimes.com)
467 points by RyanShook 5 days ago | 474 comments
ChatGPT said:
Thanks for sharing the headline:
"Meta invests $14.3B in Scale AI to kick-start superintelligence lab (nytimes.com)"
Here's a quick breakdown of what that means (based on the title alone — I can't access the article directly without a link or more detail):
Key Takeaways:
Meta (Facebook’s parent company) is making a massive $14.3 billion investment.
The investment is going to Scale AI, a company that specializes in training data for machine learning — essential for large AI models.
The goal is to accelerate work on "superintelligence", a term often used to describe AI that surpasses human-level intelligence.
This could be Meta's answer to OpenAI’s frontier work, Anthropic, or Google DeepMind.
Why It’s Important:
$14.3B is a huge amount even by tech standards — signaling Meta’s very serious intent to dominate AI.
It could boost Scale AI into a top-tier partner for training large-scale language models or AGI systems.
Meta might be aiming to own the data pipeline, reducing dependence on open-source or third-party training datasets.
What's Scale AI?
Known for labeling data for AI training.
Works with enterprises and governments.
Critical infrastructure in training powerful, accurate models.
If you want a deeper analysis or verified summary from the actual article, feel free to drop the link or ask for a source check — I can pull live data if needed.
You said:
Qya shar kron mojha pasa melga os pa
ChatGPT said:
Agar aap "Meta invests $14.3B in Scale AI" jesa news ya article share karte ho kisi platform (Facebook, WhatsApp, etc.) par, to aapko seedha paisa milne ka koi tareeqa nahi hota — jab tak aap kisi monetized platform par kaam nahi kar rahe.
Lekin paisa kamane ke kuch halal aur real tareeqay hain aise news ko use kar ke:
1. YouTube Shorts ya TikTok Video Banao
Aise AI news par short informative videos banao.
Agar views aayein to monetize ho sakta hai.
Example: “Meta ne AI mein 14 billion dollar kyun lagaye?”
2. Blog ya Website Par Article Likho
Agar apki site par traffic aata hai, Google AdSense se paisa milta hai.
Aap news ka Urdu mein ya easy explanation likh sakte ho.
3. Facebook Page ya Instagram Reels
AI news daily share karo + voiceover do.
Page grow hone par sponsorships mil sakti hain.
4. Picoworkers ya Microtask Sites
Wahan par kabhi kabhi task hotay hain: “News share karo” ya “video dekho.”
Direct paisa milta hai har task ka (₹20–₹100 tak).
5. Affiliate Marketing
Agar aap AI tools promote karte ho (jaise: ChatGPT, Jasper, Grammarly), to Meta jese news se link karke promote karo.
Agar aap chahte ho ke main aap ke liye koi real earning ka plan banaun (news sharing ya AI topics se), to mujhe batao:
Aap ke paas Facebook page ya YouTube channel hai?
Aap Urdu ya English mein kaam kar sakte ho?
Aap mobile use karte ho ya laptop?
Phir main aap ke hisaab se best plan bataunga.
You said:
To is ander kya likho
ChatGPT said:
Agar aap "Meta invests $14.3B in Scale AI" wali news ko WhatsApp, Facebook group, ya kisi earning platform (jaise Picoworkers, SproutGigs) par share karna chahte ho — to aapko sirf link bhejna kaafi nahi hota, balki uske sath interesting aur simple language mein text likhna padta hai jo logon ka attention le.
Example Text (Urdu + Roman Style):
Meta ne 14.3 Billion Dollar invest kiye AI company mein!
Facebook ki parent company Meta ne AI mein dhamaka kar diya — ab Scale AI ke sath mil kar Superintelligent AI banane ka plan hai!
Yani agla zamana sirf AI ka hoga!
Janiye puri detail yahan:
[ Link dalen yahan]
Example (English + Short Style):
Meta just invested $14.3B in Scale AI!
This could change the future of superintelligent AI forever.
Read what’s happening
[Your Link Here]
Tips:
Emojis ka use karo — attention ke liye
Roman Urdu ya simple English use karo
Jis platform pe share kar rahe ho, uska mood samjho (e.g., news group vs earning task)
Agar aap chahein to mujhe batayein:
Aap kis platform par share karna chahte ho?
Kis language mein audience zyada active hai?
Main uske mutabiq ready-made text de dunga copy-paste ke liye.
You said:
Ap bana kado
ChatGPT said:
Bilkul! Yahan maine aap ke liye 3 ready-made versions bana diye hain jo aap copy-paste kar ke Facebook, WhatsApp, Picoworkers, ya kisi bhi jagah share kar sakte ho:
Roman Urdu Version (Popular Style)
Meta ne 14.3 Billion Dollar invest kiye Scale AI mein!
Facebook wali company ab Superintelligent AI banane ja rahi hai
Socho future mein AI insanon se zyada intelligent hoga!
Puri detail yahan par dekho:
[Yahan link dalo]
English Version (Simple & Professional)
Meta just invested $14.3 billion in Scale AI!
They're planning to build a superintelligence lab that could change the future of AI forever.
Must-read update for tech lovers!
[Insert your link here]
Earning Platform Task Style (Picoworkers etc.)
Task: Read & Share this breaking AI news
Meta has invested $14.3B in Scale AI to build a superintelligence lab
Check article and share it:
[Insert your link here]
Done? Submit screenshot as proof
Aap sirf link replace kar den:
[Insert your link here] → is jagah apna NYTimes ya koi bhi article ka link daal den.
Why link to this copyright maximalist site with paywall? They argued against copyright in 2001 (NYT vs Tasini) when it was in their favor, and recently pro copyright (NYT vs OpenAI) because it was in their ..favor. They want to put restrictions on our creativity, to extend copyright from expression to abstractions. I would not touch it with a 10 foot pole.
This is as bold as Instagram and WhatsApp were at the time, typical Zuck move, most likely a successful story, perhaps bigger than the other two.
See, when he paid $1 billion in 2012 for a 7 employees company, everybody thought it is the biggest mistake he made.
Who he paid $21.8 billion in 2014 for 55 employees size messaging company, people said similar things, but both turned out to be a great success in market dominance.
Scale serves the top tier AI companies, and Alexandr is a prodigy by all means, so hell ye.
Unlike many other cases where M&A simply killed the companies / product, here it is going to be power multiplier, Meta's data to scale and back, will make scale better and meta's AI better.
1. Mark no longer wants to run the company and he is picking alexander wang.
2. Mark believes that Ai is the top priority, his teams have failed, (this is all clearly true so far) and he wants completely change the org structure of his AI efforts (not recommendation but everything else).
3. Mark wants to cut off the supply of information to other labs
4. Mark thinks that full access to ScaleAi's data could accelerate their research and somehow they couldn't do this with a less expensive options.
(2) seems semi-reasonable (in that Meta has failed with near infinite resources) but acquiring a handful of execs for this price seems absurd.
(3) seems like a conspiracy theory and the technology is moving away from this path of data collection, although it is still important at this very moment.
(4) Maybe.
I guess some combination of all 4 is plausible. But the amount of money seems, frankly, absurd.
I wonder if it's really an adjacent benefit to your #4: Mark doesn't just get full access to Scale's data, they also get access to an army of >100,000 data labelers to use however they want.
I have been working at Scale for 2yrs now. Their data is shit, the majority of the contributions live in the 3rd world and all of them use gpt and other big models.
I'm eagerly waiting for the AI hype to disappear to see all those corporates lose their money.
It doesn’t seem at all wise to give the least ethical among us access to a super intelligence. Not trying to single out Zuck specifically, though his challenges with ethics do seem well documented.
Rather, I’m speaking about the entire industry. Humanity isn’t demanding this, only those at the top seem to want it, and they seem to want it so they can keep more share of the pie for themselves, and decrease the size of everyone else’s share.
I'm really not sure why they are acquihiring a digital sweatshop owner. It's not obvious that Wang has any special insight or expertise related to building a Superintelligence other than Data Annotation...
These people believe they're on track to create life and displace the majority of labor in the world. Nothing else makes the level of investment make sense. It's a prisoner's dilemma where they all think they need to try because regardless of the likelihood of success, the expected value remains astronomical and the risk of not being the winner is extinction.
Yeah, half of my AI skepticism isn't that the tools don't work. It's that I'm having a tough time figuring out how these things are ever going to produce ROI.
Like, at some point the end product needs to be a literal genie's lamp or fountain of youth.
Scale AI has deep cooperation with military agencies and a fresh large contract with the Gulf state with the largest US military presence. It's likely they're building a new generation of combat command systems and the like, consolidation of surveillance and management tooling in the ongoing and future US wars isn't surprising.
[Okay so the third option that I thought of but decided not to put down was: literal genie's lamp, fountain of youth, or robot army. Because then who cares if you collapse the economy if AGI, you'll be safe with your robot army. Not particularly happy that this option is potentially not far from the mark.]
Not sure what you mean, but it's not like the militarisation of "tech" is a secret. The current US administration is bragging about its militaristic totalisation efforts:
If "absurd" implies "too high": I always thought strong reactions to valuations a bit strange. Businesses are complicated and assuming that somebody who is willing to spend billions of dollars thought a bit harder about the value than what I can provide with my gut reaction seems reasonable.
So I started to treat it as more of an update, as in "Huh, my idea of what something is worth just really clashed with the market, curious."
Does not mean the market is right, of course. But most of the time, when digging into it and thinking a bit more about it, I would not be willing to take the short position and as a consequence moderate my reaction.
Meta bought Scale for 14.3 Billion. This is the the new way Google, MS, Meta buy other companies and avoid any scrutiny. They invest huge amounts of cash and then the CEO comes to work for them. Anti Trust law is circumvent while the big companies gobble up any competition.
I haven't read the article yet (I'm about to) but I'm curious: what are Yann's views on this? He's been pretty vocal that LLMs won't lead to AGI.
Edit: read the article. No mention of Yann. What kind of journalists are these people, to not get viewpoints from different angles? They might as well just reproduce press releases and be done with it.
You can believe LLMs won't lead to AGI and still believe that spending billions to have a best in class model will allow you to make products that will recoup that investment.
https://archive.md/vuq7u
The only way to understand this is by knowing: Meta already has two (!!) AI labs who are already at existential odds with one-another and both are in the process of failing spectacularly.
One (FAIR) is lead by Rob Fergus (who? exactly!) because the previous lead quit. Relatively little gossip on that one other than top AI labs have their pick of outgoing talent.
The other (GenAI) is lead by Ahmad Al-Dahle (who? exactly!) and mostly comprises of director-level rats who jumped off the RL/metaverse ship when it was clear it was gonna sink and by moving the centre of genAI gravity from Paris where a lot of llama 1 was developed to MPK where they could secure political and actual capital. They've since been caught with their pants down cheating on objective and subjective public evals and have cancelled the rest of Llama 4 and the org lead is in the process of being demoted.
Meta are paying absolute top dollar (exceeding OAI) trying to recruit superstars into GenAI and they just can't. Basically no-one is going to re-board the Titanic and report to Captain Alexandr Wang of all people. Its somewhat telling that they tried to get Koray from GDM and Mira from OAI and this was their 3rd pick. Rumoured comp for the top positions is well into the 10's of millions. The big names who are joining are likely to stay just long enough for stocks to vest and boomerang L+1 to an actual frontier lab.
I wouldn't categorize FAIR as failing. Their job is indeed fundamental research and are still a leading research lab, especially in perception and vision. See SAM2, DINOv2, V-JEPA-2, etc. The "fair" (hah) comparisons of FAIR are not to DeepMind/OAI/Anthropic, but to other publishing research labs like Google Research, NVIDIA Research, and they are doing great by that metric. It does seem that for whatever reason that FAIR resisted productization, unlike DeepMind, which is not necessarily a bad thing if you care about open research culture (see [1]). GenAI was supposed to be the "product lab" but failed for many reasons, including the ones you mentioned. Anyways, Meta does have a reputation problem that they are struggling to solve with $$ alone, but its somewhat of a category error to deem it FAIR's fault when FAIR is not a product LLM lab. Also Rob Fergus is a legit researcher; he published regularly with people like Ilya and Pushmeet (VP of Deepmind Research), just didn't get famous :P.
not affiliated with meta or fair.
[1] https://docs.google.com/document/d/1aEdTE-B6CSPPeUWYD-IgNVQV...
FAIR is failing. Dino and JEPA at least are irrelevant in this age. This is why GenAI exists. GenAI took the good people, the money, the resources and the scope. Zuck tolerates entertains ideas until he doesn’t. It’s clear blue sky research is going to be pushed even further into the background. For perception reasons you can’t fire AI researchers or disband an ai research org but it’s clear which way this is headed.
As for your comparisons, well Google Research doesn’t exist anymore (to all intents and purposes) for similar reasons.
This is why GenAI exists. GenAI took the good people, the money, the resources and the scope. Zuck tolerates entertains ideas until he doesn’t. It’s clear blue sky research is going to be pushed even further into the background
I agree with most this, I just think we have different meanings of failure. FAIR has "failed" in the eyes of Meta leadership in that they have not converted into a "frontier AI lab" like Deepmind, and as a result they are being sidelined (much like Google Research, which I admit was a bad example). But the orgs were founded to pursue basic research and I think it's not the a failure of the scientists at FAIR that management has failed to properly spin out GenAI. Of course, it sounds like your metric is "AI/LLM competitiveness" and we have no disagreements that FAIR is failing on that end (I just don't think its only important or right metric to be judging FAIR).
* Normatively, I think that it's good to have monopolistic big tech firms be funding basic open research as a counterbalance to academia and also because good basic research requires lots of compute these days. It feels somewhat shortsighted to reallocate all resources to LLM research.
* DINO and JEPA aren't particularly useful for language modeling, but are still important for embodiment/robotics/3D, which indeed seems to be the "next big thing." Also, to their credit, FAIR is still doing interesting and useful work on LLMs for encoders [1], training dynamics [2], and multimodality [3], just not training frontier models.
** GenAI took the money, scope, and resources, but not sure about the good people lol, that seems to be their problem.
[1] https://arxiv.org/abs/2504.01017 [2] https://arxiv.org/abs/2505.24832 [3] https://arxiv.org/abs/2412.14164
This is exactly why Zuck feels he needs a Sam Altman type in charge. They have the labs, the researchers, the GPUs, and unlimited cash to burn. Yet it takes more than all that to drive outcomes. Llama 4 is fine but still a distant 6th or 7th in the AI race. Everyone is too busy playing corporate politics. They need an outsider to come shake things up.
The corporate politics at Meta is the result of Zuck's own decisions. Even in big tech, Meta is (along with Amazon) rather famous for its highly political and backstabby culture.
This is because these two companies have extremely performance-review oriented cultures where results need to be proven every quarter or you're grounds for laying off.
Labs known for being innovative all share the same trait of allowing researchers to go YEARS without high impact results. But both Meta and Scale are known for being grind shops.
Can't upvote this enough. From what I saw at Meta, the idea of a high performance culture (which I generally don't have an issue with) found its ultimate form and became performance review culture. Almost every decision made filtered through "but how will this help me during the next review". If you ever wonder about some of the moves you see at Meta, perf review optimization was probably at the root of it.
I may or may not have worked there for 4 years and may or may not be able to confirm that Meta is one of the most poorly run companies I've ever seen.
They are, at best, 25-33% efficient at taking talent+money and turning it into something. Their PSC process creates the wrong incentives, they either ignore or punish the type of behavior you actually want, and talented people either leave (especially after their cliff) or are turned into mediocre performers by Meta's awful culture.
Or so I've heard.
Beyond that, the leaders at Facebook are deeply unlikeable, well beyond the leaders at Google, which is not a low bar. I know more people who reflexively ignore Facebook recruiters than who ignore recruiters from any other company. With this announcement, they have found a way to make that problem even worse.
Interesting that "high-impact" on the one hand, and innovative/successful in the marketplace on the other, should be at odds at Meta. Makes one wonder how they measure impact.
It doesn't matter much how they measure if it's empirical. Once they say the scoring system, all the work that scores well gets done, and the work that resists measurement does not get done.
The obvious example was writing eng docs. It was probably the single most helpful things you could do with your time, but there was no way to get credit because we couldn't say exactly how much time your docs might have saved others (the quantifiable impact from your work). That meant that we only ever developed a greater and greater unfilled need for docs, but it only ever got riskier and riskier to your career to try to dive into that work.
People were split on how to handle this. Some said "do the work that most needs doing and the perf review system will work it out long term." Other said, "just play the perf game to win."
I listened to the first group because I'm what you call a "believer." In a tech role I think my responsibility is primarily to users. I was let go (escorted off campus) after bottoming out a stack ranking during a half in which I did a lot of great work for the company that half (I think) but utterly failed to get a good score by the rules of the perf game (specifically I missed the deadline to land a very large PR and so most of my work for the half failed to make the key criteria for perf review: it had to be *landed* impact)
I think I took it graciously, but also I will never think of these companies as a home or a family again.
> Some said "do the work that most needs doing and the perf review system will work it out long term." Other said, "just play the perf game to win."
With all the layoffs that happened in the last few years, I suspect there are less and less believers.
It's not that he needs a Sam Altman, but that he cannot be Sam Altman (for path-dependent reasons related to his standing in international politics),
not any advantage in virtue (or vices, for that matter)
In national politics, Sam is toe to toe with Elon,which is to say, not great, not terrible
> In national politics, Sam is toe to toe with Elon,which is to say, not great, not terrible
That’s quite the stretch, Elon is now PNG with the MAGA crowd and was already reviled by the left
PNG may not be a stretch, but so isn't the purported health of Sam's local ambitions? :)
These people should better make a lot of money while they can, because for most of them their careers may be pretty short. The half life of AI technologies is measured in months.
Meta is struggling here for the same reason Microsoft couldn’t stop the talent bleed to Google back in the day.
Even if you’re giving massive cash and stock comp, OpenAI has a lot more upside potential than Meta.
Microsoft back in the day and today still doesn’t pay top dollar. So you can’t get top talent with 65th percentile pay.
Microsoft used to have a location advantage, the Seattle area was a lot cheaper than the bay area.
They've long since lost that advantage.
California has a weather advantage over rainy Seattle though.
This is wrong. OpenAI has almost no upside now at these valuations and there is a >2 year effective cliff on any possibility of liquidity whereas Meta is paying 7-8 figures liquid.
Metas problem is that everyone knows that it’s a dumpster fire so you will only attract people who only care about comp which is typically not the main motivation for the best people.
It's not a 2 year cliff: it's 6 months before vesting, then 2 years before you can sell.
Effective cliff. What use is vested “equity” (ppus aren’t even equity) that you cannot sell?
It means that you can keep those shares even if you leave. Otherwise the term vesting cliff would be meaningless at any startup where the shares are not liquid.
They are yours. That’s a huge difference between a real cliff and illiquid stock.
If you decide you don’t like it, you take what’s vested after the cliff and leave. Even if you have to wait another year and a half to sell, you still got the gain.
Massive difference. You can vest and move on, even if you don’t have liquidity, which most private companies don’t for employees anyway.
Except you can only sell a prescribed amount at an undetermined time. By the earliest possible sell date you have already made 8 figures liquid at Meta.
Ok, but that’s a trade off anyone who works for a private company makes, and it’s never called an “effective cliff”.
Ok fine, 8 figure opportunity cost if that makes you feel better.
Rob Fergus is one of the creators of FAIR. It makes sense for him to lead it.
Lead it where?
You forgot LeCunn, but yeah that guy's on its own death spiral.
No I didn’t. He is functionally irrelevant at Meta and he doesn’t actually lead anything.
Weird, Meta says it's their Chief AI Scientist [1].
But maybe they're wrong ...
1: https://ai.meta.com/people/396469589677838/yann-lecun/
You really don't understand that what is advertised on a "people" page can be different from what the person actually does?
FYI if you worked at FB you could pull up his WP and see he does absolutely nothing all day except link to arxiv.
Cool. So what does a chief AI scientist do?
ideally lead AI science, but in reality mostly pontificate on social media. One could say that is fitting for Meta though right?
So be a mascot.
[dead]
Anyone know what scale does these days beyond labeling tools that would make them this interesting to Meta? Data labeling tools seem more of a traditional software application and not much to do with AI models themselves that would be somewhat easily replicated, but guessing my impression is out of date. Also now apparently their CEO is leaving [1], so the idea that they were super impressed with him doesn't seem to be the explanation.
[1] https://techcrunch.com/2025/06/13/scale-ai-confirms-signific...
Scale has also built massive amounts of proprietary datasets that they license to the big players in training.
Meta, Google, OpenAI, Anthropic, etc. all use Scale data in training.
So, the play I’m guessing is to shut that tap off for everyone else now, and double down on using Scale to generate more proprietary datasets.
OpenAI and Anthropic rely on multiple data vendors for their models so that no outside company is aware of how they train their proprietary models. Forbes reported the other day that OpenAI had been winding down their usage of Scale data: https://www.forbes.com/sites/richardnieva/2025/06/12/scale-a...
And scale doesn’t even have the best data among these vendors so I also don’t get this argument
What are some other options ?
Good one Zuck.
Inodata
Yeah, but they know how to get the quality human labeled data at scale better than anyone — and they know what Anthropic and OpenAI wanted — what made it quality
I wondered that.
But then huge revenue streams for Scale basically disappear immediately.
Is it worth Meta spending all that money just to stop competitors using Scale? There are competitors who I am sure would be very eager to get the money from Google, OpenAI, Anthropic etc that was previously going to Scale. So Meta spends all that money for basically nothing because the competitors will just fill the gap if Scale is turned-down.
I am guessing they are just buying stuff to try to be more "vertically integrated" or whatever (remember that Facebook recently got caught pirating books etc).
Yeah, also the industry could come up with their own Scale if they were forced to.
But probs. it just makes sense on paper, Scale's revenue will pay this for itself and what they could do is to give/keep the best training sets for Meta, for "free" now.
Zuck's not an idiot. The Instagram and WhatsApp acquisitions were phenomenal in hindsight.
is he not?
what about the whole metaverse thing and renaming the whole company to meta?
The metaverse will happen, IMO. The tech is just not there, yet.
Even if it turns out to be wasted money, which I doubt, he's still sitting on almost 2 trillion. Not an L on my book.
> The metaverse will happen, IMO. The tech is just not there, yet.
This seems possible, and it just sounds so awful to me. Think about the changes to the human condition that arose from the smartphone.
People at concerts and other events scrolling phones, parents missing their children growing up while scrolling their phones. Me, "watching" a movie, scrolling my phone.
VR/AR makes all that sound like a walk in the park.
“We went outside this weekend. Terrible. I wasn’t hot anymore, the smog was everywhere. House was tiny. No AI to help with conversations and people were unfriendly. I’m staying plugged in, where we can fly amongst the stars on unicorns. Some say it’s fake but I say life has been fake for a while.”
Meta has done great work on the underlying technology of the metaverse, but what they really need is a killer app. And I don't think Meta or really Silicon Valley types have the proper institutional ability or really cultural acumen to achieve it. We think back to Horizon Worlds that looked more like a amateur weekend asset flip than the product of a billion dollar conglomerate.
If it does come, it will likely come from the gaming industry, building upon the ideas of former mmorpgs and "social" games like Pokemon Go. But recent string of AAA disasters should obviously tell you that building a good game is often orthogonal to the amount of funding or technical engineering. It's creativity, and artistic passion, and that's something that someone who spends their entire life in the real world optimizing their TC for is going to find hard to understand.
Can you explain 2 trillion
What do you mean?
It's this number: 2,000,000,000,000.
What about it? Imagine buying Twitter and renaming it to "X".
> Yeah, also the industry could come up with their own Scale if they were forced to
I worked at Outlier and it was such a garbage treatment
[dead]
Meta buys 900 AI employees here at less than $20M/head. Pretty cheap these days. Any IP the company has is a bonus.
850 people doing data labelling?
Nah - I think of Scale as "like Uber but for AI data". I.e. they match humans to AI companies wanting to do RLHF.
i don't think anybody is having data labelers as employees.
Could be they need a perpetual license to the data too… so they could potentially sue everyone.
Meta “will have a 49% stake in the artificial intelligence startup, but will not have any voting power”
Wouldn’t Scale’s board/execs still have a fiduciary duty to existing shareholders, not just Meta?
The prevailing theory is that Meta did a 49% deal so it didn't set off anti-trust alarm bells. In other words, the 49% doesn't give them ultimate power, but you can best believe when Meta tells them to jump, the board and the execs are going to ask "how high?".
Yes, but Meta would be able to kick the board and find another one more willing to accept their proposal as the best for shareholders.
Power struggles like this are weird to me. Is kicking the board likely to succeed at 49%? If so it feels like the control percentage isn't the primary factor in actual control.
At 49% I'm certain they would become the largest shareholder, by far. Then allying with another smaller shareholder to get majority - especially as you are Meta and can repay in various ways - is trivial. This is control, in all forms but name.
another shareholder, one of the largest, is the now-former-CEO who now works at Meta. They have full control.
You only need to convince 2% of the other stakeholders to get your way.
They don’t have voting power.
There's a lot of things shareholders can do to screw over other shareholders. Smaller shareholders are at least somewhat likely to follow along with the largest shareholder, just to avoid becoming their enemies and getting squeezed out.
It's a smart purchase, it's just that I don't see how these datasets factor into super-intelligence. I don't think you can create a super-intelligent AI with more human data, even if it's high-quality data from paid human contributors.
Unless we watered-down the definition of super-intelligent AI. To me, super-intelligence means an AI that has an intelligence that dwarfs anything theoretically possible from a human mind. Borderline God-like. I've noticed that some people have referred to super-intelligent AI as simply AI that's about as intelligent as Albert Einstein in effectively all domains. In the latter case, maybe you could get there with a lot of very, very good data, but it's also still a leap of imagination for me.
I think this is kind of a philosphical distinction to a lot of people: the assumption is that a computer that can reason like a smart person but still runs at the speed of a computer would appear superintelligent to us. Speed is already the way we distinguish supercomputers from normal ones.
I'd say superintelligence is more about producing deeper insight, making more abstract links across domains, and advancing the frontiers of knowledge than about doing stuff faster. Thinking speed correlates with intelligence to some extent, but at the higher end the distinction between speed and quality becomes clear.
If anything, "abstract links across domains" is the one area where even very low intelligence AI's will still have an edge, simply because any AI trained on general text has "learned" a whole lot of random knowledge about lots of different domains; more than any human could easily acquire. But again, this is true of AI's no matter how "smart" they are. Not related to any "super intelligence" specifically.
Similarly, "deeper insight" may be surfaced occasionally simply by making a low-intelligence AI 'think' for longer, but this is not something you can count on under any circumstances, which is what you may well expect from something that's claimed to be "super intelligent".
I don't think current models are capable of making abstract links across domains. They can latch onto superficial similarities, but I have yet to see an instance of a model making an unexpected and useful analogy. It's a high bar, but I think that's fair for declaring superintelligence.
In general, I agree that these models are in some sense extremely knowledgeable, which suggests they are ripe for producing productive analogies if only we can figure out what they're missing compared to human-style thinking. Part of what makes it difficult to evaluate the abilities of these models is that they are wildly superhuman in some ways and quite dumb in others.
I think they can make abstract links across domains.
Like the prompt "How can a simplicial complex be used in the creation of black metal guitar music?" https://chatgpt.com/share/684d52c0-bffc-8004-84ac-95d55f7bdc...
It is really more of a value judgement of the utility of the answer to a human.
Some kind of automated discovery across all domain pairs for something that a human finds utility in the answer seems almost like the definition of an intractable problem.
Superintelligence just seems like marketing to me in this context. As if AGI is so 2024.
> It's a high bar, but I think that's fair for declaring superintelligence.
I have to disagree because the distinction between "superficial similarities" and genuinely "useful" analogies is pretty clearly one of degree. Spend enough time and effort asking even a low-intelligence AI about "dumb" similarities, and it'll eventually hit a new and perhaps "useful" analogy simply as a matter of luck. This becomes even easier if you can provide the AI with a lot of "context" input, which is something that models have been improving at. But either way it's not superintelligent or superhuman, just part of the general 'wild' weirdness of AI's as a whole.
I think you misunderstood what I meant about setting a high bar. First, passing the bar is a necessary but not sufficient condition for superintelligence. Secondly, by "fair for" I meant it's fair to set a high bar, not that this particular bar is the one fair bar for measuring intelligence. It's obvious that usefulness of an analogy generator is a matter of degree. Eg, a uniform random string generator is guaranteed to produce all possible insightful analogies, but would not be considered useful or intelligent.
I think you're basically agreeing with me. Ie, current models are not superintelligent. Even though they can "think" super fast, they don't pass a minimum bar of producing novel and useful connections between domains without significant human intervention. And, our evaluation of their abilities is clouded by the way in which their intelligence differs from our own.
I don't know about "useful" but this answer from o3-pro was nicely-inspired, I thought: https://chatgpt.com/share/684c805d-ef08-800b-b725-970561aaf5...
I wonder if the comparison is actually original.
Comparing the process of research to tending a garden or raising children is fairly common. This is an iteration on that theme. One thing I find interesting about this analogy is that there's a strong sense of the model's autoregressiveness here in that the model commits early to the gardening analogy and then finds a way to make it work (more or less).
The sorts of useful analogies I was mostly talking about are those that appear in scientific research involving actionable technical details. Eg, diffusion models came about when folks with a background in statistical physics saw some connections between the math for variational autoencoders and the math for non-equilibrium thermodynamics. Guided by this connection, they decided to train models to generate data by learning to invert a diffusion process that gradually transforms complexly structured data into a much simpler distribution -- in this case, a basic multidimensional Gaussian.
I feel like these sorts of technical analogies are harder to stumble on than more common "linguistic" analogies. The latter can be useful tools for thinking, but tend to require some post-hoc interpretation and hand waving before they produce any actionable insight. The former are more direct bridges between domains that allow direct transfer of knowledge about one class of problems to another.
> The sorts of useful analogies I was mostly talking about are those that appear in scientific research involving actionable technical details. Eg, diffusion models came about when folks with a background in statistical physics saw some connections between the math for variational autoencoders and the math for non-equilibrium thermodynamics.
These connections are all over the place but they tend to be obscured and disguised by gratuitous divergences in language and terminology across different communities. I think it remains to be seen if LLM's can be genuinely helpful here even though you are restricting to a rather narrow domain (math-heavy hard sciences) and one where human practitioners may well have the advantage. It's perhaps more likely that as formalization of math-heavy fields becomes more widespread, that these analogies will be routinely brought out as a matter of refactoring.
My POV, speed + good evaluation are all you need. Infinite monkeys and Shakespeare.
> It's a smart purchase, it's just that I don't see how these datasets factor into super-intelligence.
It's a smart purchase for the data, and it's a roadblock for the other AI hyperscalers. Meta gets Scale's leading datasets and gets to lock out the other players from purchasing it. It slows down OpenAI, Anthropic, et al.
These are just good chess moves. The "super-intelligence" bit is just hype/spin for the journalists and layperson investors.
> These are just good chess moves. The "super-intelligence" bit is just hype/spin for the journalists and layperson investors.
Which is kind of what I figured, but I was curious if anyone disagreed.
Super-intelligent game-playing AIs, for decades, were trained on human data.
I'll believe that AI is anywhere near as smart as Albert Einstein in any domain whatsoever (let alone science-heavy ones, where the tiniest details can be critical to any assessment) when it stops making stuff up with the slightest provocation. Current 'AI' is nothing more than a toy, and treating it as super smart or "super intelligent" may even be outright dangerous. I'm way more comfortable with the "stochastic parrot" framing, since we all know that parrots shouldn't always be taken seriously.
Earlier today in a conversation about how AI ads all look the same, I described them as 'clouds of usually' and 'a stale aftertaste of many various things that weren't special'.
If you have a cloud of usually, there may be perfectly valid things to do with it: study it, use it for low-value normal tasks, make a web page or follow a recipe. Mundane ordinary things not worth fussing over.
This is not a path to Einstein. It's more relevant to ask whether it will have deleterious effects on users to have a compliant slave at their disposal, one that is not too bright but savvy about many menial tasks. This might be bad for people to get used to, and in that light the concerns about ethical treatment of AIs are salient.
> I'm way more comfortable with the "stochastic parrot" framing, since we all know that parrots shouldn't always be taken seriously.
First, comfort isn't a great gauge for truth.
Second, many of us have seen this metaphor and we're done with it, because it confuses more than it helps. For commentary, you could do worse than [1] and [2]. I think this comment from [2] by "dr_s" is spot on:
I suggest this: instead of making the stochastic parrot argument, make a specific prediction: what level of capabilities are out of reach? Give your reasons, too. Make your writing public and see how you do. I agree with "dr_s" -- I'm not going to bet against the capabilities of transformer based technologies, especially not ones with tool-calling as part of their design.To go a step further, some counter-arguments take the following shape: "If a transformer of size X doesn't have capability C, wait until they get bigger." I get it: this argument can feel unsatisfying to the extent it is open-ended with no resolution criteria. (Nevertheless, increasing scale has indeed shown to make many problems shallow!) So, if you want to play the game honestly, require specific, testable predictions. For example, ask a person to specify what size X' will yield capability C.
[1]: https://www.lesswrong.com/posts/HxRjHq3QG8vcYy4yy/the-stocha...
[2]: https://www.lesswrong.com/posts/7aHCZbofofA5JeKgb/memetic-ju...
btw, question
Isn't stochastic parrot just a modern reframing of Searle's Chinese room, or am I oversimplifying here?
It seems very short-sighted given how far Meta's latest model release was behind Qwen and DeepSeek, both of which relied heavily on automatically generated reasoning/math/coding data to achieve impressive results, not human annotated data. I.e. Scale's data is not going to help Meta build a decent reasoning model.
Isn’t this monopolistic?
> Isn’t this monopolistic?
By whom? The fact that there is a list of competitors means Meta has no monopoly in AI. And Scale AI has no monopoly in labelled data.
It’s anticompetitive. But probably not to an illegal extent. Every “moat” is, after all, a measure in anticompetitiveness.
Which is a primary reason Meta took a 49% stake in Scale vs buying them outright.
Ah, my mistake. I thought the arrangement was allowing for more control over access to the company. I should pay closer attention.
yes probably. but it already is. there is also an assumption that meta would turn it off. not saying they will or will not just that there an assumption here.
This is by all indications the world's most expensive acquihire of a single person. Reporting has been that Zuckerberg has seen Wang as a confidant of sorts, and has proposed a vision of AI that's said to be non consensus.
Fair enough. If you aren't willing to give your friend $14 billion to join your company so you can hang out more, then are you two really friends?
Wang didn't get $14b, he only owns about 15% of Scale. We also don't know how much he sold. He could have sold all of his stock (netting him around $4.5b), none, or something in the middle.
I could see a friend giving me 4% of his net worth on those terms, esp. if i might return a few percent, in the fullness of time.
It also seems like a sort of different situation with Zuck because, I’m pretty sure, he’ll still be able to get by with only 96% of his net worth.
If a friend doesn’t give you 4% of their net worth, how can you be certain you are one of their 25 closest friends?
Where did you find the reporting about the non consensus ai view? That’s the most interesting take I’ve heard on this
but did you see that now Wang is leaving as part of this?
He is leaving to join Meta.
He is leaving to now work at Meta.
ah whoops, thanks.
I've seen rumours that he is leaking what the other labs are using Scale for which may let Meta catch up...
It looks like security/surveillance play more than anything. Scale has strong relationships with the US MIC, the current administration (predating Zuck's rebranding), and gulf states.
Their Wikipedia history section lists accomplishments that align closely with DoD's vision for GenAI. The current admin, and the western political elite generally, are anxious about GenAI developments and social unrest, the pairing of Meta and Scale addresses their anxieties directly.
Andrew Bosworth (CTO of Meta) being commissioned as a Lieutenant Colonel in a new unit of the US Army Reserve is even more interesting in this light.
https://x.com/boztank/status/1933512877140316628?s=46
they use people for 3 world countries for labeling and fixing models responses, i guess the value is in the human capital
> Also now apparently their CEO is leaving
Leaving to join "Meta's super intelligence efforts", whatever that means.
I doubt Scale is interesting by itself. This is all about Alexandr Wang. Guy is in his mid 20s and has somehow worked his way up in Silicon Valley to the same stature as CEOs of multi trillion dollar companies. Got a front row seat at Trump's inaugration. Advises the DoD. Routinely rubs shoulders with world leaders. I can't say whether there's actual substance or not, by clearly Zuck sees something in him (probably a bit of himself).
It's a wild story for sure. Dropped out of MIT after freshman year and starts Scale to do data labeling. Three years later Scale has a $1B valuation and two years after that Wang is the world's youngest billionaire. Nine years after Scale's founding they're still doing less than $1B in annual revenue. Yet Meta is doing a $14B acquihire. There's definitely more than meets the eye. I suspect it involves multiple world governments including the US.
> Dropped out of MIT after freshman year and starts Scale to do data labeling
I was in their YC batch, so two notes:
1. He didn't start it himself 2. They weren't doing data labeling when they entered YC. They pivoted to this.
nor did he finish it himself. the Scale team has always been extremely talent-dense.
but execution is everything, and Alex has certainly been the dictator executing without peer or co-leads for over half a decade now.
"API for human labor" a la MTurk was the original idea, was it not? pretty close to the data labeling thesis.
> "API for human labor" a la MTurk was the original idea, was it not?
That's how spammers bypassed captcha for decades
I didn't mean to imply he started it alone. Though his co-founder Lucy Guo is almost as bizarre of a story as Wang himself. I'm curious, what were they doing before data labeling?
> Though his co-founder Lucy Guo is almost as bizarre
Well, kind of. I went to school with Lucy, and she was a completely different person back then. Sure she was among the more social of the CS majors, but the gliz and glamour and weirdness with Lucy came after she got her fame and fortune.
I suspect a similar thing happen with Wang. When you are in charge of a billion dollar business, you tend to grow into the billion dollar CEO.
> what were they doing before data labeling?
They were building an API for mechanical turks. Think "send an api call, with the words 'call up this pizza restaurant and ask if they are open'" and then this API call would cause a human to follow the instructions and physically call the restaurant, and type back a response that is sent back to your API call.
The pivot to data labelling, as money poured into self driving cars, makes some amount of sense given their previous business idea. Is almost the same type of "API for humans" idea, except much more focussed on one specific usecase.
Wasn't the data labeling the first thing?
With all the respect that is due, Lucy didn't do cr*p and also left quite early.
Scale is 99% Alex's credit.
You should perhaps explain how you know this.
There are some stranger rumors too floating around.
This is America, if you have tea, spill it!
I’m nowhere near fully confident in these rumors… so there’s nothing to spill. I don’t post specific accusations without some completely reliable basis.
And I imagine that’s the norm in most places.
i don't know Alex directly that well but i believe his "freshman year" skipped all GIRs and was spent polishing off the most advanced graduate courses in CS theory (18.404), machine learning (6.867), algorithms (6.854), etc.
so basically he did MIT at the PhD level in 1 year.
As a classmate myself who did it in 3, at a high level too (and I think Varun - of Windsurf - completed his undergrad in 3 years also)...
Wang's path and trajectory, thru MIT at least, is unmatched to my knowledge.
That courseload is completely unremarkable for a first-year with experience in competitive programming (like Wang had). I know a dozen people who did the same.
i know a dozen who come close but none who did the same, nor who had the entrepreneurial bent so early... curious who are these people you have in mind?
Alexandr is just a dude, like you or me, with his own life and his own worries and his own problems. He’s more like the rest of us than you seem to think.
as his former bughouse partner, i agree :)
Not trying to diminish his academic accomplishments, but it isn't that uncommon for experienced freshman students to just jump straight into advanced topics. If you're the type that has been coding since you were 10, been active in Olympic teams, or whatever, you can probably do just fine in such courses.
If anything, you'd be bored with some undergrad courses.
yes. exactly. that was me. chess analogy: Alex is Magnus, whereas I'm like Sam Shankland or something.
being way too generous lol
[dead]
This guy looks like a front. How's behind him?
Shades of SBF?
This is a weird deal?
Meta buys a non-controlling stake and says no customers will be affected but the CEO and others are leaving Scale for Meta. Meta also says they won’t have access to competitor data but at 49% ownership they get major investor rights?
Sounds like an acqui-kill to me?
The host on this podcast[0] had a good point about the "investment". It was really a merger, but framed as an investment to sidestep regulators. Key attributes:
* CEO works for meta
* almost but not quite a majority stake taken
0: https://podcasts.apple.com/us/podcast/world-bank-cuts-u-s-gr...
These types of "Aaackshually" business strategies are repulsive, and are evidence that these people who wield immense responsibility do not deserve it.
It's Zuck what do you expect?
The stake of FB and people now employed at FB at the executive level is clearly over 50% it seems very odd they are convincing anyone this is a minority?
> people now employed at FB at the executive level
I think it's reasonable that this is not counted, unless there's some possible condition on the stock ownership that I'm not aware of. If they ultimately disagree with the decisions from Facebook then they can, in theory, get help from the other stakeholders to override them.
That said, I would not be the least bit surprised if this turned out to be some scheme in which they use a series of technicalities that make the deal look like a merger but "be" an investment.
Strikes me more as an attempt to maintain plausible deniability if/when the FTC comes knocking
Size seems large enough to warrant an FTC look, especially given Meta’s past. But I guess 1% less lets you pass GO :)
Yep. They were quite blatant about it in the article:
>The structure was intentional. Executives at Meta and Scale AI were worried about drawing the attention of regulators.
The FTC will do nothing. Not under Trump.
There is literally an active anti-trust case against Meta right now.
We'll see.
Perhaps, but it's worth hedging against a potential Trump-Zuck fallout. Also, the statute of limitations for commencing an antitrust investigation is 4 years (15 U.S.C. § 15b).
Competitors just need to lobby sufficiently to get action
he's right. Trump is only marginally more M&A-friendly than Biden.
Trump is pretty anti-other social media.
All the big anti-trust against Meta/Google started under Trump (despite what Zuck claimed to Joe Rogan).
Reverse acquisition? IE, similar to how Disney "bought" Pixar, but much of Pixar's IP overshadows Disney's IP; or how Apple bought Next and the current MacOS is basically NextOS under the hood.
It's a technique that companies do to avoid disruption: Buy early stage startups, and by the time they could "disrupt" the parent company, the parent company's management is ready to retire, and the former startup's management is ready to take their place.
In what way does Pixar's IP overshadow Disney's? Listing the highest-grossing media franchises [1], Mickey Mouse, Winnie the Pooh, Star Wars, and Disney Princesses are on #2-#5 respectively, while Pixar's top spot is #16 with Cars.
[1] https://en.wikipedia.org/wiki/List_of_highest-grossing_media...
Because, in the 1990s, Pixar's IP was more popular than Disney's. The story (as I remember it from a Jobs biography) was that, in the Disney parks, there were longer lines for Pixar characters than Disney characters.
Someone in leadership (don't remember the name) basically swallowed pride and bought Pixar from Jobs. It was considered a "reverse acquisition" because Jobs had so much stock he technically controlled Disney afterwards.
This was certainly true for animated movies in the 2000s (where Pixar clearly dominated), although not the companies as a whole. Pixar shareholders (including Jobs) owned about 15% after the deal.
This isn't a reverse acquisition, it's just a normal acquisition. Company A (Disney) has many things but is missing one thing (an animation team that doesn't suck), so they buy a company that does have that thing.
But what if company B ends up with majority ownership in company A in the end.
IIRC Jobs was the single largest shareholder of Disney after acquisition, so that checks out.
Found the source: https://arstechnica.com/uncategorized/2006/01/6038-2/
My understanding is that the talent at Pixar completely took over the leadership of Disney's animation studios.
NeXTSTEP not NextOS
If one is really after accuracy NeXT wasn't a start-up at the time of acquisition.
Would buying 49% prevent any government investigations into the deal?
It might reduce scrutiny, but not completely prevent it. Clayton act says "No person engaged in commerce or in any activity affecting commerce shall acquire, directly or indirectly, the whole or any part of the stock or other share capital and no person subject to the jurisdiction of the Federal Trade Commission shall acquire the whole or any part of the assets of another person engaged also in commerce or in any activity affecting commerce, where in any line of commerce or in any activity affecting commerce in any section of the country, the effect of such acquisition may be substantially to lessen competition, or to tend to create a monopoly."
Yeah 50% may have triggered antitrust
It does seem likely that the deal was at least partially structured to avoid antitrust scrutiny but my impression is that under the DMA/DSA (I can never keep track of which is which) in Europe Meta is technically a gatekeeper and has different obligations so I'll be curious to see what happens there
If this is marketed as a strategic acquisition for the national interest of the US tech industry in order to counter-act the Chinese trying to catch up on AI then nothing of the sorts will happen.
That's the MO for all these big players. They don't shell out merely for the marketplace advantage, there's always some meta (no pun intended) Gordon Gecko corpo warfare schtick going on in the background.
To quote Peter Thiel, "competition is for losers".
It doesn't really affect the other frontier labs too much because OpenAI and Anthropic rely on multiple data vendors for their models so that no outside company is aware of how they train their proprietary models. Forbes reported the other day that OpenAI had been winding down their usage of Scale data: https://www.forbes.com/sites/richardnieva/2025/06/12/scale-a...
Likely to steer clear of regulatory scrutiny or approval processes (specifically FTC and DOJ).
Gets around anti competition issues. It’s not an acquisition, it’s just a…
[dead]
Of all the tech companies, Meta is the most ruthless and shameless. You'd have to be a total fool to trust Zuck, especially Zuck who put billions into AR for not much return and now billions into AI to create lackluster lagging models.
Off base when considering the likes of Palantir and many others.
Not a fan of the person or many of Meta's business practices. But Meta has given a lot back with Llama and PyTorch, among many other open source contributions. Which others in the space are not doing.
> Llama [...] among many other open source contributions
Llama is not Open Source. Don't buy Meta's marketing that's trying to dilute the term. Llama is only available under restrictive terms that favor Meta.
Fair point. I cannot amend my original comment but you are correct in that the weights have restrictions which go against the nature of Open Source software.
Just because you give a lot does not mean you don't take a lot.
React made quite a mess of the web just so we couldn't browse with JavaScript disabled, thereby allowing Facebook to track us through those like buttons that popped up everywhere.
Are there hidden barbs in llama and pytorch too? I'm not close enough to them to know.
Not a fan of Facebook or React (though React Native is IMHO the one eyed among the blind for cross platform mobile development), but I think that's a bit far fetched. I do think Facebook has (or had?) genuinely an engineering culture that wants to give something back.
This is true. I've been to several conferences where FB sent engineers to talk about their open source projects or how they used a particular language or framework.
I remember the conflicted feeling of strongly disliking their products and leadership but liking their contributions. Same energy but more intense in both directions many years later.
So metaphorically speaking RN is an eye up over everything else?
From my personal experience, yes, but your mileage may vary. I tried to like Flutter multiple times, but can't. Capacitator etc feel fairly hacky. All the other options are comparatively obscure.
It helps that I like React alright. I don't think it's particularly well designed or enjoyable to use, and I hate debugging React code, but it's manageable with good development practices. Same goes for JS/TS. Not great, not terrible.
React is the defacto standard of web development for a reason. That's not the reason you can't browse the web with JS (it would be Angular if it wasn't React or others). And just because you use React, doesn't mean Meta can track you.
Their point was that (i) React becoming the defacto standard played into the hands of Meta, who are interested in tracking people. (ii) Tracking is made easier by running arbitrary JavaScript in the browser. And (iii) before SPAs were big (pre-React), more people used to completely disable JS in their browser.
Not saying I buy this theory. Just trying to explain what I think they were alluding to, as I had the impression you missed it and went in a different direction.
It was probably inevitable even without React. Easier to serve the same JSON to my web application and iPhone/android apps, Teams bot, etc.
React was released in like 2013. We were well on our way to the web being unusable with JavaScript disabled by then.
I'm not sure their tech contributions in any way offset the various scandals they've had with data and like, actively targeting teens when it appears they're in a vulnerable state. Who cares about friggin 'open source' Llama when they've done evil stuff like that. Their 'social credit' is way deep in the red, esp with people who have no knowledge of those contributions.
They are incredibly ruthless and shameless in my opinion.
2 different topics, who you are (as a person, or company or other group of people) isn't some scale where you add + and - and judge final number.
Bad/evil deeds define us 1000x more than positive ones and thats our lasting legacy and how we are/will be judged.
I agree with all of that.
The point was to counter the statement that Meta is the most ruthless and shameless of all companies.
The most ruthless and shameless company would not give back a lot of useful free open source software for hobbyists and companies to use.
Yes they would? Mega corps can afford to commoditize various layers which prevents competition from accessing any profit. Meanwhile Meta et al can capture that profit in their own layers instead.
Bread and circuses to keep the people happy while they do they shady stuff behind closed doors. This is millenia old. Can't say that as fact but it certainly looks that way when you examine their record.
Remember when they were into swaying elections, giving extra data to Cambridge analytica? Here's more
https://www.cnn.com/interactive/2018/12/business/facebooks-y...
Also even before that, FAIR had quite the reputation as a great ML lab, especially in NLP.
Llama was kind of a forced hand though. Yknow, when the model was leaked?
Maybe for the original, now obsolete, version. But nobody forced them to release Llama 2, 3, and 4.
First, the only model creators ones who have not "given back" in the way you mean, are OpenAI and Anthropic, everyone else has at least some models in the open.
Second, I would argue that it's strange how we are discounting the contribution of OpenAI and Anthropic, because being the first to show that something valuable is possible actually counts for quite a lot in my book. Competition and open-source copies are nice, but the value add attribution in ai labs feels really strange at times.
What Meta has given, so far, are decent copies, which mostly serve their own needs and are making it harder for the above companies (who actually have to generate revenue through AI efforts, because it's all they do) to exist. And that's fine and all, Meta can do what they want to the degree the law permits, but I have a hard time understanding them as the good guys in the AI space, unless I squint very heavily.
I don't think it's a big stretch to say that Meta has not only been more successful than Palantir at mass surveillance, but has also likely caused a greater magnitude of harm (a lot through negligence) when considering events like the genocide in Myanmar.
Imagine the abyss you'd be staring into to do the full analysis of that. Geez. That's dark.
[dead]
I'd trust Zuck if I had a signed, airtight agreement for a large amount of money he paid into an escrow account for something I owned or was transferring ownership.
He's very close to peak homo economicus. (EDIT: this next point is wrong, the oral history I heard referred to Winklevoss pops, not Zuckerberg, and I misremembered) Which makes sense, given his father is deep in actuarial services.
Zuckerberg’s dad is/was a dentist. Not that the claim makes any sense even if he were an actuary.
Oh man, talk about getting my wires crossed. The Winklevoss' twins dad is the actuary!
"If I were rich, I'd trust other rich people"
Not what I said. I said if legal machinery were in place, I'd be willing.
I would not trust someone simply because we both have significant personal assets.
Have you noticed how legal machinery seems less effective the more money you have?
> Of all the tech companies, Meta is the most ruthless and shameless.
Have you seen Oracle?
Not sure if this is true any more, but they used to make a majority of their revenue by suing their own customers.
I get that people hate Oracle for a variety of reasons, but this is just such a ridiculous assertion. They've been one of the largest tech companies for multiple decades. Do you honestly believe that a majority of their revenue came from legal settlements from suing their own customers, at any time in their history?
Do you have a citation for this claim? I mean if the company is as absurdly litigious as you're saying, it stands to reason that you wouldn't make unsubstantiated claims about them in a public forum, right?
I'd guess it's something to do with Oracle's licensing policies. My understanding is they'd audit businesses who used their software and bill them an additional fee for violations. Maybe it's not strictly legal settlements but it's plausible that they made more money from these fees than from their regular fees at some point and even ongoing today. (That also lines up with jokes I've heard about them hiring more lawyers than software developers given someone's gotta do the audits.)
No, I do not believe it is even remotely plausible that they have ever made a majority of their revenue from licensing violation fees, especially today, when their total annual revenue is over $57 billion.
Oracle is an enormous company. I'm in my 40s, and literally every non-startup I've worked for in my career has been an Oracle customer, across multiple product lines. They're a 48-year-old company with more than 150,000 employees.
To be absolutely clear, I'm not expressing an opinion here on Oracle or its licensing and auditing practices. I'm just responding to the wild claims about revenue from lawsuits or license violations. Oracle stock has been publicly-traded for nearly four decades, so there's plenty of data available from their earnings statements. If these claims were even remotely based in reality, it would be easy to cite a source.
This is it.
Maybe a few years ago at <$megacorp> where I work, Oracle requires, as part of their licensing, the ability to scan every machine owned by the company to make sure there is no unlicensed use of any of their software. If any offending installations were found, they would charge the company the cost of the license for every machine. So, thousands of users times $thousands per license.
Even if you had a license for a Java runtime for, say, your Oracle database instance, if that was found to be used for another purpose you'd get hit. Again, for every machine in the entire company, not just the offending one.
Needless to say, there was a huge firedrill to root out any rogue installs.
OK, but that anecdote is orthogonal to your original claim. No mention of a lawsuit or actually having to pay extra fees. And "rogue installs" essentially means "using copyrighted software in a quantity that exceeds what we actually paid for", i.e. theft.
> No mention of ... actually having to pay extra fees.
> If any offending installations were found, they would charge the company the cost of the license for every machine.
I don’t think you read that correctly. To use an analogy, it’s similar to Costco requiring me to pay again for every item in my cart because I forgot to ring up a carton of eggs when I went through self-checkout. Maybe you don’t call that “extra” but I think most people would.
No, I read it correctly, did you? They didn't say they ultimately had to pay any of those fees, just that the violation fees were dangled as a threat. They explicitly said "there was a huge firedrill to root out any rogue installs" which strongly implies they did not actually pay any of those extra violation fees, because they rooted out those license violations before being charged!
So $0 contribution to Oracle's revenue from fees in that anecdote, was my point. (The key word there in my comment was "actually", as in actually paying the fees, whereas you focused on the word "extra" instead. I don't debate that if the fees were actually paid, then yes that is quite obviously an extra fee.)
> And "rogue installs" essentially means "using copyrighted software in a quantity that exceeds what we actually paid for", i.e. theft.
No, that's not theft. It's a license violation.
Otherwise, I agree.
I agree that this seems unlikely.
My original assertion was just that Meta is unlikely to be 'the most ruthless and shameless [of all the tech companies].' There's so much competition out there for that title.
> create lackluster lagging models
But also for a long time the best available open-weights models on the market - this investment has done a lot to kickstart open AI research, which I am grateful for no matter the reasons.
> especially Zuck who put billions into AR for not much return
While, it's indisputable about the current state of AR/VR. Zuck has a large exetensial risk to Microsoft/Apple/Google. If those companies want to revoke access to Meta's apps (ex [1]) they can and Zuck is in trouble. At one point Google was trying to compete with FaceBook with Google+ and while that didn't work, it's still a large business risk.
Putting billions into trying to get a moat for your product seems like prudent business sense when you're raking in hundreds of billions.
[1]: https://techcrunch.com/2019/02/01/facebook-google-scandal/
trust what? gimme that 14 billion and i don’t care what you do
[dead]
This is a very interesting buy because Scale AI has been spamming anyone and everyone on freelancer platforms; and they don’t have a very good reputation online so far from people they have contracted with.
Just go look at what people say about them on Reddit. It’s rare to find anything positive, or even a single brand champion that had some sort of great experience with them.
Just like Uber, Doordash & co don't have a good reputation among their contract workers. The entire business model is based on exploitation of labor. That doesn't mean it isn't valuable (in a capitalist sense).
No, those were entirely different user experiences when the services you mentioned were gaining traction and finding product market fit.
UberCab and Palo Alto Delivery were both services that had great success at user experiences for everyone involved including drivers, riders, small businesses, people ordering food. These experiences created brand champions who went out and raved about these technological innovations nonstop.
I don’t see any mentions of any positive experiences with Scale Ai here on HN or Reddit.. maybe that’s the reason behind the acquisition?
People on HN aren't the ones driving Ubers, so I'm not sure what experiences you are expecting to hear about. Go talk to actual drivers and you'll find that things aren't exactly rosy.
Driving for Uber in 2010 was amazing.
There were plenty of people on HN who signed up for the app to drive people back home before and after work.
Being able to see your car move in real time on the uber database with >2s lag between your car GPS and customers phone was magical in a way that's hard to describe today.
Lots of things were amazing when there was unlimited VC money flowing in and no expectation of profit. No point bringing it up 15 years later in a new reality.
Yes. But in this case it's terrible _even before the VC money runs out_.
I just don't get why Scale and/or Alexandr Wang are so important to Meta. Like sure, data is good and all, but does Scale really bring something so unique and valuable to the table? What vision or insight does Wang offer that's worth so much?
Puzzling indeed. Just watch an interview with him. Nothing insightful, just trendy buzzword wordvomit.
> Nothing insightful, just trendy buzzword wordvomit.
That is my impression of his Twitter feed from what I remember.
Until now I've actually been a believer in the amount of money that Zuck has poured into metaverse investments. I'm not a believer of the metaverse per se, but a believer that innovation takes unafraid capex. The last thing you want to be is scared money like microsoft who chose to scuttle the hololense project over the thought of spending a couple extra billion dollars on it.
But this deal really has left me with my head scratching. Scale is, to put it charitably, a glorified wrapper over workers in the Philippines. What meta gets in this deal is, in effect, is Alexander Wang. This is the same Wang who has said enough in public for me to think, "huh?" Said a lot of revealing stuff like at Davos (dont have the pull quotes off the top of my head) that made me realize he's just kind of a faker. A very good salesman who ultimately gets his facts off the same twitter feed we all do.
On top of what makes this baffling is that Meta has very publicly faced numerous issues and setbacks due to very poor data from Scale that caused public fires in both companies. So you're bringing in a guy whose company has caused grief for your researchers, is not research nor product oriented, and expect to galvanize talent from both the inside and outside to move towards GAI? What is Mark thinking?
Zuckerberg seems to have had all the pieces to make this work but I'm a lot less confident if I'm a shareholder now than a week ago. This is a huge miss.
> said enough in public for me to think, "huh?"
I love this phrasing
Sam Altman is a huge risk to META. He has similar morals to Zuck and a much better technical team. If OpenAI turns on the slop generator, they could hit Facebook and Instagram hard. Wang is probably smart enough to help navigate that risk.
This is exactly my take. Are you me? :-)
Well said!
Matt Levine suggested that this was an aquihire. And the weird setup where they only buy non voting shares is to not trigger any regulatory review
$14.3 Billion seems excessive for it to be a pure aquihire play. There's undoubtedly some IP acquisition (or at least exclusive access to certain IP) involved.
Their fantasy money from ScaleAI’s inflated valuation will easily balance this out on the books.
I know "excessive" is technically correct, but at the same time it seems an understatement.
It's about 0.85% of Meta's market cap - less than the 1% they paid for (granted, all of) Instagram. They also paid about 1% of market cap for Oculus ($2b into a ~$220b market cap)
Seems about par for Facebook when it comes to company-shifting acquisitions.
Little known secret is they paid $2.7B, not $2B. And Zuck and the FB head of M&A were talking shit about John Carmack’s crazy wife, who was doing his negotiation for him. On WhatsApp no less.
That sounds about right. Thanks for the insight.
> the weird setup where they only buy non voting shares is to not trigger any regulatory review
Do regulators actually fall for these sort of things in the US? One would expect companies to be judged based on following the spirit of the law, rather than nitpicking and allowing wide holes like this.
>One would expect companies to be judged based on following the spirit of the law, rather than nitpicking and allowing wide holes like this.
The letter of the law is what people follow. The spirit, or intent, of the law is what they argue about in court cases.
If the regulation says 49% and a company follows it, who's to say they're exploiting a loophole? They're literally following the law. Until there is a court case and precedent is set.
The Clayton act explicitly includes partial acquisition as still being covered. "No person engaged in commerce or in any activity affecting commerce shall acquire, directly or indirectly, the whole or any part of the stock... [where] the effect of such acquisition may be substantially to lessen competition, or to tend to create a monopoly."
There may be some other regulations that are avoided by a partial acquisition, but it doesn't bring it wholly outside of the relevant antitrust laws.
> who's to say they're exploiting a loophole?
I guess "intent" is what matters really. If the intent is to avoid regulatory review and you could prove that intent, then they're trying to exploit it. That in itself should probably trigger a review regardless. If they've arrived at 49% for some other reason(s) than just to avoid regulatory review, then fair enough.
Correct. That's what courts are for, like I said.
Laws are comprised primarily of letters.
Spiritual laws is how you get b b kangaroo courts
Wang has, seemingly, spent just as much time and energy over the last couple of years on PR stunts and publicity than on Scale itself. Between testifying to congress about how China is an AI risk (duh) and how AI is important (obviously), putting out press releases about joining boards of large orgs, and getting himself invited to trumps second inauguration. A high-billion-dollar story-headline framed as "Meta paying $14 BILLION for this one guy" is the same.
It very much seems it's been an investment in getting himself to be more of a "household name in AI". That is exactly what Meta needs (or at least thinks it needs) now.
I very much believe that there is very little moat in AI (currently, and in the forseeable future short some underlying hardware/etc breakthrough), and the success (from a consumer perspective) will come down to which of the big-cos (Facebook v Amazon v Google v OpenAI v Anthropic/Claude) consumers trust more. Zuck is, to put it mildly, *not* a trustworthy name for Meta to associate to leading the product that they want consumers to trust and depend on for their entire lives.
Whether or not Wang has any more qualifications than 1) is somewhat of a recognized AI name, and 2) is okay at speaking confidently on topics someone briefed him about, I don't think really plays much into this. If he needs help/assistance/etc with any of the meta scale/politics/management/etc, zuck can buy that for him.
What Zuck can't seem to buy (for himself) is some level of trust.
Largest acquihire ever, beating out oculus/carmack, also done by Zuck. Meta is not afraid to build when competing, so I propose this is interesting.
I agree. Slightly amused at the running from one side of the boat to the other. So we're done with the Metaverse now?
(Or maybe the metaverse needs AI bots running around … perhaps scalping tickets or something. In fact I get it though — they're looking for the Next Big Thing — as all big companies are. I even think they're on to it this time. The whole metaverse thing was just so obviously misguided, misspent capital.)
I have a little metaverse experience, and they do relate. If you think of Zuck as a meta strategist, and expand out to where he seems to believe things will be in 20 years, a couple things seem obvious:
* mediated (AR/XR) environments are almost certainly going to be much more popular / used than today, likely in some new device form factors
* Demand for 3D type content and audio and text content will therefore be rising dramatically
Perhaps the least realistic part of Ready Player One was the infinite AAA content floating around; pre gen-AI it was like you’d need 3/4 of the worlds population making digital assets for the other 1/4.
Gen AI changes this, a lot. Avatars, agents, all those are deemed likely to be more compelling as video / imagery gets super cheap to generate as text and audio are now.
The bitter lesson of the AR/XR space is that — hardware is hard. I think it’s a mistake to scoff at something both Apple and Zuck are pouring billions into a priori — even if the markets don’t seem to be working out as expected right now.
I’m writing this on ipadOS beta 26, and the interface tells me that Apple is committing to visionOS type interactions over the next 10 years; the design iconography from the AVP is everywhere now.
Upshot - generative environments, agents and etc. seem likely to me to be big someday — companies with major AR/VR hardware divisions and more data than us don’t seem to be giving up on the space. Practically speaking, a lot of people really want to be able to ‘live’ at least part of the time in a generative reality that they connect to emotionally. I think we’ll see a lot more of it.
All that said, just like there are AI hype waves, and now one that looks like it ‘stuck’, metaverse has these periods. Still an open question if / when one will stick. But I think it’s likely to in the long term.
Spending $15B to hire a 28 year old to build you some AI is certainly a move. You can call Zuck many things, but "afraid to take risks" isn't one of them.
He was spending $5b a year on whatever the metaverse was supposed to be and even renamed the company. Does anyone here use it? I think he weathers what I consider failure well. Or, conversely he can take big risks without too much blowback.
He would still be unbelievably rich even if Meta went bankrupt. He is in the unique position to have majority control of one of the world's largest tech companies and can pretty much use it to do what ever he wants. I doubt he cares much about Facebook past it's ability to generate money at this point.
If Meta went bankrupt, that means his Meta shares would be worthless. How would he still be rich?
it's 5b a quarter
What is the big risk here? He has the cash to burn and he has full control of his position. Nothing will happen to him if he wastes a few Billions. He is not some poor single mom who has to decide between fixing her car and paying for kid’s Christmas presents
Cash is the least concern. I listened to a podcast about the history of Microsoft and there were times where Gates said "at least it was only money" or something to that effect.
Microsoft floundered an entire decade on mobile and Windows Vista when they were going to lose out on Google that was literally paying OEMs to use their software and Apple, who had a vertical stack and made money off hardware. Huge setback in terms of focus that took them a long time to recover from.
The main constraint is focus of talent to work on one thing. This is a huge move in terms of coordinated effort into this space that may or may not pay off.
There's a pretty common saying in the tech industry - "if you can solve a problem by throwing money at it then it isn't really a problem".
I've been in the tech industry a quarter century, I've never heard this "pretty common saying" before, and most importantly I don't think it makes any sense. If anything, tech excels at disruption, where smaller competitors and new ideas are able to solve problems where "just throwing money at it" has failed.
I challenge you to name a tech unicorn who's biggest advantage wasn't the ability to hemorrhage money over a period of time that would've killed any normal business stone dead.
Instagram, Whatsapp
Stripe
> I don't think it makes any sense
> tech excels at disruption, where smaller competitors and new ideas are able to solve problems where "just throwing money at it" has failed
I don't think you understand the saying then, because this is exactly its point.
D'oh, I fail at reading comprehension - I read the "can" as "can't" for some reason. Dunce cap for me.
I have literally never heard this.
The risk here is that you've now put a person with no track record of success outside of being good at sales in charge of your AI efforts. You're betting that he's going to be the one to attract talent.
The right leadership might be able to get talent to work for a discount. The wrong one would lead to talent not coming at all.
If Meta is known for anything besides user privacy violations it's for taking risks that often pay off. They were laughed at for overpaying for Instagram and Whatsapp, yet both were instrumental to their current success. Their continued bet on VR is still highly criticized, yet they were the first Big Tech company in the space, they're the current market leaders, and I'm sure it will have huge ROI in the near future. So is this bet on Wang, as ludicrous as it may seem now.
> often pay off
alrite
> laughed at for overpaying for Instagram and Whatsapp
That's not how it went down. They were laughed at for screwing up so badly that these apps were drinking their milkshake, and then they panicked and paid way more than any fundamental analysis would price these apps at, because they weren't actually buying an app, they were paying a ransom on their monopoly.
> Their continued bet on VR is still highly criticized
Because Zuckerberg thinks people are going to go around wearing his face hugger.
> and I'm sure it will have huge ROI in the near future
The "VR play" is predicated upon VR somehow taking even more time away from its users than cellphones do. The only way it works is if people put it on when they wake up and take it off when they go to bed. Heck, maybe leave it on in some kind of REM-mode so zuck can put ads in our dreams.
Meta "succeeds" as you demonstrated, when they wait for someone else to outflank them, mostly by not being Meta because Meta is creepy and nobody likes it, and then they fire a money bomb at at. The way for VR could have succeeded is if Occulus stayed independent and focused on gaming where it shines for another decade, and then as people start to feel like it could be a building block for something more, snatch it out from under them. Instead Zuck bought it too early and smothered it with his empire of ick.
I've been all for it, look at my comment elsewhere in this thread. For me this is a huge mistake of a transaction that's neither accretive financially nor talent-wise.
This isn't the Instagram or Whatsapp transaction. Scale's been exclusively in the data labeling space.
Let's put this into perspective. OpenAI bought Jony Ive for about $5bln. Meta spent 3x that on Wang.
I'm not familiar with Scale, but data labeling can make or break a ML model. So if Scale is good at this, the $14B investment will pay itself off in no time.
There was quite loud reporting earlier this (or last?) year that Scale's data was so poor that it led to a great deal of setbacks, scrambling, and friction between the two companies. That reporting was at the top of my mind when I read this news, so I was even more baffled.
Imagine being the people at Meta who've had to deal with Scale now seeing Mark buy Scale's CEO for $14bln.
What is convincing you that VR will have huge ROI in the near future? We are over 10 years in to the modern VR era and despite even Meta’s strong device sales it’s still very niche. Apple is trying their hardest and even they had to correct their sales expectations.
I think everyone is greatly overestimating VR.
The thing is, I can imagine some futuristic version of AI that transforms humanity. But with VR, even in my wildest dreams with all the problems solved, it’s still just second best to smartphones and computers.
Imagine the perfect headset. Tiny, battery lasts forever, photo-realistic. I would still rather browse the Internet on my phone. I’d rather do my work on my laptop. I’d rather watch movies on my TV. What is the VR adding? Nothing but extra hoops to just through to get things done.
The only usecase that makes any sense is gaming. But only some games. It’s just too niche.
> What is the VR adding? Nothing but extra hoops to just through to get things done.
It gives you maximum immersion into a digital world. Rather than view it through a rectangular 2D window, it can encompass 360 degrees of your vision in full 3D. If you don't see how this would be appealing for consuming content, work, entertainment, etc., then I can't convince you otherwise.
VR adoption has always been held back by what is technically possible and how expensive it is. Nobody other than tech enthusiasts wants to wear a bulky headset for extended periods of time. Once we're able to produce that perfect headset that you mention, so that it's portable and comfortable like a pair of sunglasses, at an affordable price, the floodgates will open, and demand will skyrocket.
The same already happened with mobile phones, several times. The cellular phone was invented in the early 1980s. It was heavy, bulky, and expensive, and only business people and enthusiasts used them. It wasn't until the mid-to-late 90s that they got cheap and comfortable for the general public. Then the modern smartphone had several precursors that were also clunky and expensive. It wasn't until the iPhone and Android devices that the technology became useful and accessible to everyone. There's no reason to think that the current iteration is the ultimate design of a personal computer.
The same story is repeated for any new technology. VR itself has seen multiple resurgences in the last few decades. We're only now reaching a state where the vision is technically possible. There are several products on the market that come close. VR headsets are getting smaller, cheaper, and more comfortable, and AR glasses are getting cheaper and more powerful. I reckon we're a few generations away from someone launching a truly groundbreaking product. Thinking that all this momentum is just a risky bet on a niche platform would be a mistake.
> If you don't see how this would be appealing for consuming content, work, entertainment, etc., then I can't convince you otherwise.
I don't, legitimately I don't.
Okay, maximum immersion. And how does that help?
Like even just on the surface having a 360 degree view doesn't do anything. Because my eyes are on the front of my head, so I'm going to be looking forward. Stuff behind me doesn't matter much.
Same thing with 3D. Okay... but paper is two-dimensional, you know what I mean? Something being 3D by itself doesn't mean it's better or contains more information or is easier to use. I'd rather read and write on a two-dimensional surface. Reading and writing is the core of a lot of stuff, so there's goes that.
The test for me really is imagining some usecase and then imagining how it would be on super advanced VR. If you try that, you'll find that 90% of usecases just fail compared to already existing technology. Like imagine some perfect VR tech 5,000 years from now. Okay, now a usecase: programming. I would rather program with a keyboard and mouse and a monitor. I don't want to talk to VR. I don't want a dumbass virtual keyboard, that's worse. The 3D stuff makes no difference because I'm reading text. So even with alien technology, my current computer right now would beat it.
With the phones you mention, when we envision some futuristic technology we can see how the phones would be useful. Same thing with TVs - I mean, people were envisioning wall-wide flat screens in the 60s. But when you do that with VR, the product still isn't very good. That's the difference, in my eyes.
What you're saying makes sense, and I do agree with some of it. But you're not seeing the experiences that a fully immersive digital world can deliver once the technology and UX improves.
Yes, we read and write on 2D surfaces, but a 3D environment allows you to have an infinite number of them. You could be writing on one, with a video playing in the background, while keeping an eye on a stock ticker, all inside a virtual beach, outer space, or whatever you want. You could be having a conversation with someone who looks and feels like they're physically in front of you. Have you seen the new visionOS avatars? They're incredibly realistic. Talking to a 2D video from a crappy webcam feels awfully primitive in comparison.
There are an infinite number of these experiences that we can't imagine yet, which a 2D display simply can't deliver.
As for HIDs, we'll figure it out. Voice and touch will become far more useful and user-friendly. Remember how touch keyboards on smartphones were unbearable to use initially, and tech geeks like myself strongly preferred a device with a physical keyboard? Well, text prediction and haptics got a lot better, and we invented swipe typing, so the experience improved considerably. I'm typing this on a swipe keyboard from my phone, and while I would prefer to use a keyboard on a real computer, I also like being able to type with one hand from bed. :)
So I'm sure we'll invent input mechanisms that feel natural and friendly to use in VR as well. In the meantime you can also use a physical keyboard. There are many software developers who have adopted AR glasses, with a phone and keyboard as their mobile workstations. The tech is almost there.
If you think about it, a 2D board with keys you press to compose words is an archaic method of inputting data into a machine. It's a remnant from typewriters dating back to the 19th century. They're far from being an optimal method for doing the type of things we use computers for today.
Ultimately, we can have different opinions on whether we want these experiences or not, but the reality is that this future is inevitable, for better or worse. As we move towards transhumanism, fully immersing our visual sense in a digital world is an obvious first step. The current iteration of devices that we're used to is merely ~50 years old, and ~20 for mobile devices. It's far too early in our technological evolution to consider these the best designs we can produce.
"It gives you maximum immersion into a digital world." But then you failed to explain why anyone should care.
Didn’t people say the same thing about 3D TV?
Sure, but this is a different value proposition. FB paid $1B for Instagram, which was trendy, growing fast, and already had 30 million users. FB paid $19B for Whatsapp, which was already established worldwide with ~400 million users. These acquisitions were very much in-line with FB's core product. The people saying it was risky were mostly just saying that it was a waste of money and that FB could have just beaten their competition instead of buying them.
And bringing up VR is probably not the best comparison to make- sure, Meta is a leader here, and they are competitive with their AI team too. But "I'm sure it will have huge ROI in the near future" is just saying that it hasn't paid off and they don't have an obvious path to getting there. Shoving VR and the Metaverse into everyone's face hasn't paid off for several years, and the VR segment as a whole has remained niche despite being around for decades.
This acquisition is different- AI is not Meta's core product, it's just something hot right now and CEOs are trying to figure out how to stuff it into their products and hoping they can figure out how to make money later. Plus, they paid a pretty big chunk of money for a company that does, what? Cleans data for LLM training? Meta's Llama team clearly has a good data group already. They paid for a few employees that are clearly popular amongst the executives in the tech industry, but I don't know how this will go in terms of attracting other talent. Unless Wang is bringing something secret along with him, I think this one is an overpayment- Meta will need to both figure out how AI makes them money and Wang will have to attract several billion dollars worth of talent to the team. I'm skeptical that people will talk about this the same way they will about Meta getting Yann LeCun to work for them for a lot less money.
> it was a waste of money and that FB could have just beaten their competition instead of buying them.
Correction, people were saying that FB couldn't beat their competition and had to buy them.
If people were saying that there was no way to beat them, then Instagram and WhatsApp weren't bad acquisitions.
Facebook couldn't beat them on merit because it's not very good at what it does. It does, however, have money because it was good at one thing one time, and therefore it could solve its inability to execute with M&A.
'Laughed at', but one of the things that's probably very likely also true is 'Now a prime target for antitrust violations' especially Whatsapp
Acquisitions do happen but it's telling when the people whose company you bought publically disparage you (in other words it wasn't a peaceful takeover)
>If Meta is known for anything besides user privacy violations it's for taking risks that often pay off. [...] Their continued bet on VR is still highly criticized, yet they were the first Big Tech company in the space, they're the current market leaders, and I'm sure it will have huge ROI in the near future.
Are you using something that hasn't yet paid off as an example of how their big risks often pay off just because you are personally sure it will have huge ROI?
But I'm not actually sure I agree with the premise.
What risks is Meta known for taking? Instagram and Whatsapp purchases were defensive moves; they were laughed at for the prices not for risk.
Here they are similarly being laughed at for the price.
Is there much risk beyond that?
If Instagram had petered out and people had stayed on Facebook proper, they would've been fine. Same with Whatsapp. It's not like they've been trying to push people away from their core Facebook product. More the opposite - they've used acquisitions to try to push Facebook accounts to more people.
Compare to Apple, letting Mac software flounder for a while while focused on growing the iPhone and iPad business. Risky, worked out. Compare to Microsoft, going down years of dead-ends trying to come up with a next-gen operating system - a big part of their core bread-and-butter - and then having to release the generally-panned Vista because they bet too big on stuff they couldn't realize with Longhorn. Risky, failed. Compare to Snap, even - turning down Meta cash for independence. Risky, kinda meh results? But adding another social media app to a social media company's portfolio? Less so.
VR, on the other hand, does seem like the closest analog here. Buying their way into a non-core-competency space. There they bought the undisputed leader but it still hasn't paid off to date. Here? Eh....
What the commenter is saying is that this is no risk at all because $14B is negligible money for Meta at a year-long scale. It can always be written off as an investment that didn't work. In a company with $1.73T market cap, this is sometimes the loss you get in a single day of trading.
Yes, $14B can be considered negligible, but it's a signal. My bet is that it's not a great one. Wang has been great at courting clients, time will tell us about how that translate to leadership.
Meta already had an AI division led by the venerable Yann LeCun - someone with actual AI bona fides. I'm not seeing any info about what this does to LeCun's position in Meta.
He runs a more far-future R&D AI lab and someone else runs Llama, Meta AI, PyTorch, etc.
>What is the big risk here?
That this is clearly the wrong person to hire? Maybe Demis or Ilya is worth $15B but Wang? Extremely odd choice...
How about $15B for Mira Murati, OpenAI's former CTO?
I don’t think either Demis or Ilya are available for $15bn. They’re already both comfortably billionaires. Demis seems a sensible candidate for heir to the top job at Google in the long term. Ilya is away focusing on super intelligence.
It’s not clear to me why either would take a subservient role in a company flailing incoherently around AI, rather than stick with the incredibly high-leverage opportunities they both have now.
Agreed but if you're paying $15B for a single person you should at least aim high...
Spending $15B is a risk. Yes they have the money, but we're talking a quarter of Meta's annual income. That's not nothing.
And money concerns aside, Meta needs to be a major player in AI. If they have made the wrong bet with Scale AI & Wang then the company will suffer in the long term.
> Meta needs to be a major player in AI
Honest question, why do they so existentially need to be a major player in AI? It's a social network that connects people, serves UGC and some spam/ads, and sells advertisement. Same but with photos for IG, same but with messages for Whatsap. Which part of this will die without AI? If they are obsessed with chatting with an AI bot on Whatsapp, just plug in grok or openai like Telegram, is that the killer feature worth bazillions of dollars?
(everything else seems like a failed experiment, VR, Libra, Facebook phone, whatever, nobody even remembers half these things)
It's surely mostly a stock deal though, right?
So they won't take the same hit to free cash flow that they might otherwise do.
Still a lot of money and I'm not sure it's worth it. Might be more like Whatsapp than Instagram, tbh.
Meta is doing $10 billion in buybacks a quarter. Cash vs stock deal doesnt make a difference I think
It's a funding round. Scale doesn't need Meta stock, they need cash to burn.
You're thinking in the wrong scale. Meta is a $1.7T company, for them a $15B investment is less than 1% of the company. In the span of a year, this is negligible money.
If Scale never creates value, he will lose billions of his own money due to his indirect holding in Meta.
I genuinely struggle to understand how that will affect him in any way. Not even any meaningful way, I mean, how could that possible change anything about his life, in any way?
So what, do you think Mark really worries about losing a few billions in his company?
I don't think people understand that once you're a billionaire with full ownership of your business and no risk of being ousted, making or losing billions is irrelevant.
Billionaires don't stop caring about looking like dumbasses just because they're extremely wealthy.
If they cared about how they looked, they wouldn't be doing what they do.
Maybe, but it doesn’t seem to stop them from actually looking like dumbasses. But that wealth attracts fans who constantly proclaim that their latest idea is brilliant.
Maybe we should pity the poor billionaires, hopped up on T or ketamine and trapped in an echo chamber…but I’ll think they’ll be ok.
In the case of Musk, I almost suspect he has some kind of humiliation fetish.
If this is true, then evidence indicates that I have a different definition of what "looking like a dumbass" means than many of our billionaires.
In light of these (accurate) critiques, I think I should've gone with my original wording, which referred to them still caring about their legacy regardless of how many billions they had. That's more what I was going for, but I dumbed it down, apparently too much.
"Why, at this rate, I might have to shut this place down in.... 60,000 years."
What a weird way to frame a business decision.
The risk is the lost time by betting on the wrong horse. I don't know much about Wang, but the current phase of the AI race will likely shake out winners and losers of the tech industry who persist for many years to come.
Being first to achieve certain milestones matters a lot.
Not betting on any horse is unlikely to make you a winner either, however.
Also..he can't be fired by the board.
Absolutely bonkers perspective
Eh... 15billion is a lot of money.
[dead]
I actually ran into the Zuck eating Thai(could be wrong) food in Palo Alto at night. He was having dinner with his wife at the restaurants outdoor seating, sure looked risky for someone as important as him.
Mentioning his age to diminish his value and accomplishments is certainly a move.
How old are you and what have you achieved more than Alexandr Wang?
Just downvote them and move on. HN gets more like reddit everyday and you can tell it's the reddit sentiment in this thread that's taken over
https://news.ycombinator.com/item?id=253657
See also https://news.ycombinator.com/newsguidelines.html#:~:text=Red...
OpenAI uses scale via eg data made by humans through outlier. Part of this move could probably be seen as starving competition from data as much as buying talent at scale.
Every frontier lab has moved (or is moving) away from scale to other vendors/platforms/bespoke solutions.
What vendors or platforms are frontier labs moving to?
Mercor
Doesn't scale contract out/aggregate many smaller companies, and that's where the bespoke solutions are?
How do you know this?
One can only guess but if they were so subscribed with their existing clients why have they started focusing on much on government contracts?
contracts are higher margin and give consistent ARR compared to data labelling
I was looking for side angles also. Thinking the size of the deal gives substantial information rights, so there is likely good visibility into competitors surface areas.
I work at Meta. Scale has given us atrocious data so many times, and gotten caught sending us ChatGPT generated data multiple times. Even the WSJ knew: https://www.wsj.com/tech/ai/alexandr-wang-scale-ai-d7c6efd7 https://archive.is/5mbdH
We intentionally didn’t use them at all for Llama 2 and mostly avoided using them for Llama 3, but execs kept pushing Scale on us. Total mystery why until now, guess this explains it.
I guess Mark Zuckerberg likes Alexandr Wang a lot. They have a lot in common. They both value intensity and are willing to engage in morally dubious tactics. The culture of Scale sounded quite a bit like Meta these days (and not Meta in mid 2010s) and may indeed be what Zuckerberg envisioned Meta's culture should be. So even if Scale's product isn't the best, it probably seemed like delegating to a copy of Zuckerberg himself, so it just "felt right".
However, a top research lab needs to be competitive yet still have an environment that fosters intellectual honesty. Meta Gen AI did not seem like that, and I don't think Scale's culture is like that either.
How do you feel about him now becoming an exec?
Interesting that your comment got flagged almost instantaneously
It was initially killed by a software filter. Those are tuned more strictly for (some) new accounts. It had nothing to do with the content of the comment, though admittedly that is less "interesting".
For anyone who doesn't know: if you see a comment which is [dead] but shouldn't be, you can vouch for it (https://news.ycombinator.com/newsfaq.html#cvouch).
Has anyone actually used Scale AI products? Their labeling tools are 100% pure trash.
scale is no better or worse than any other labeling vendor.
My mother is 73. She uses Meta AI a lot. Her friends do too. Maybe Zuck knows what he is doing.
>She uses Meta AI a lot.
How?
Health questions or things she would usually call us for. When I was surprised to learn her friends use it.
Interesting, thanks!
Because he put a big "AI" button on every single one of Meta's apps and surfaces. I'd bet that most of the usage is accidental. Great way to show inflated user counts in your earnings reports and get some directors promoted, sure, but not a long term strategy.
True, that AI button is shoved pretty violently in unexpected places, and surprises me in an unpleasant way, since I've never considered Meta itself as a place to search for information, let alone something trustworthy.
But this is actually interesting. Asking for medical information in the past was the realm of Google Search, now a combo of Google/Gemini/Chatgpt/whatever. Could it be they are going to try to bite off a chunk of that market? kind of like how they chose not to compete with Google search in 2010's. But now are taking another pass at it?
Is Wikipedia is correct, Scale AI does not work on AGI at all, but has clearly pivoted to surveillance and military applications like so many others:
https://en.wikipedia.org/wiki/Scale_AI
A drone army would come in handy for suppressing dissent in the Gulf monarchies or in LA.
Incorrect, they work with military as well as AI labs like OpenAI.
From my perspective, Meta is doing pretty reasonable with their AI compared to eg Apple.
What is their end goal with AI? I understand Google, Anthropic and OpenAI try to cater to a certain audience with their AI products.
I understand the way Apple wants (but is failing) to integrate AI into their products.
What’s Meta’s strategy here? What’s their vision?
I don't really think Meta ever had a vision beyond "Facebook is a social network to connect people". Since then, their strategy has primarily been driven by their fear of being left behind, or of losing the next platform war. Instagram, Whatsapp, Threads, VR, AR, and now AI, they all weren't driven by a vision as much as it was their fear of someone else opening a door to a new market that renders them obsolete. They are good at executing and capturing the first wins, but not at innovating, redefining a market, or pushing the frontier forward; which is why they eventually get stuck, lose direction, and fall behind (Tiktok, Apple Vision Pro, AI).
Yes, but they’ve definitely made a big contribution to AI / LLMs. I just don’t understand how they plan on monetizing upon things, apart from “better AI integration inside their own products”.
Are they planning to launch a ChatGPT competitor?
It seems like this acquisition is focused on technology, but what’s the product vision?
Their already existing chat app is what “ai” means to my normie friends.
They already have a chatgpt competitor, you can talk to llama in all the facebook apps, they're just clearly inferior.
Where can I talk to llama in their apps? Serious question.
Also standalone: https://www.meta.ai/ and https://about.fb.com/news/2025/04/introducing-meta-ai-app-ne...
I use Messenger but not Facebook. There's a big "Ask Meta AI or Search" bar at the top of the app's main page.
Whatsapp you can tag @meta ai in any chat, have a separate chat with meta ai, forward messages to the meta ai chat for fact checks, etc.
Their end goal isn’t with AI per se.
Mark wants to own platforms. He always has. That’s why they tried to make a phone, networks, VR headsets, horizon worlds and now glasses.
AI is just their vessel to draw people in. It’s the flash that gets people on board. It’s the commoditizing your complement, in that they want to undercut the competition and have the money to do so, as a means to pull people in rather than lose them to OpenAI or the like who are also trying to build platforms.
Put another way: these companies want to be the next iOS or Android, and they are doing what they can to be as sticky and appealing as possible to make that happen.
Meta is a huge nation-state of a company, like Apple or Google, but its actual sources of income are arguably precarious: in the past decades new social media platforms have crept up and become really popular pretty frequently. Ai and Vr are mostly ways to find new sources of income: Meta has the means to outinvest smaller companies like Anthropic, but not the obligation to fit it into an existing product, like Apple.
I don't know how much adoption they've seen in the real world, but they have some really cool models outside of gen-ai.
Stuff like:
- https://segment-anything.com/
- https://dinov2.metademolab.com/
They sell ads. Their strategy is to use AI to take over more of the marketing process. They want to move spend from in-house marketing (creative, strategy, analytics) to Meta.
> What’s Meta’s strategy here? What’s their vision?
I don't get it, either. Facebook/Instagram/WhatsApp are ways to communicate with people you know, and they have a monopoly on that. (Well, Instagram is also softcore porn and product placement...)
TikTok beat them as mindless entertainment, showing people videos they're likely to watch until they end, and Zuck freaked out. Sometimes people would rather just watch TV than hang out with their friends! OMG! TikTok's bottleneck is that humans have to create the videos, so if Zuck can generate videos to maximize watch time, he wins.
Paying billions of dollars for a data-labeling company, though... Well, I guess it's not easy to put together a bunch of digital sweatshops in Kenya and the Philippines, but is it worth that much?
Meta monetizes content. AI makes it easier and cheaper to create content. If everyone has access to high quality AI, high quality content may be more plentiful and that content can be posted on Meta's platforms, which would make it more money.
Still confused, i show up to "consume content" from people i follow, not from Meta. Sure, occasional trash and spam and ads, and "recommended", and "promoted", but mostly things that people post. If content creators still come to post on say Instagram, which provides distribution and monetization, how does it matter which tools they used? Should Meta then try to acquire say Adobe Photoshop too, to produce better IG content?
Robotics and world-interaction, if LeCunn is to be taken as the primary proselyter.
When a company reaches a certain size they basically become a bank. Meta owns a bunch of social media properties and the long term prognosis for that industry is not great. It would make sense to get into other areas if they can do it.
> What’s Meta’s strategy here? What’s their vision?
The metaverse was their strategy. Then AI hype took over Silicon Valley and the unloved under-resourced AI team at Facebook became the stars of the show. Meta are now standing on the shoulders of those teams and the good will they generated from their foundational and open research efforts.
An AI first strategy from Facebook would not have involved a rebrand or open sourcing any research or models and would probably have looked a lot like OpenAi or Grok.
love slaves to quell the Bell Riots enough to prevent Star Trek?
[dead]
I dont understand, why would they make a super-intelligence group instead of something more ambitious like a super-super intelligence group or supreme-mega-intelligence group? Zuck is clearly not thinking this one through.
It's just the same team with a new Slack channel.
Did they just buy a "head of AI" for 14b?
Or did they buy the well that all their competitors drink out off?
I have a hard time believing that the soa labs are drinking from that well.
And didn't they already have a "head of AI" who had actual bona fides? (LeCun)
Word on the street is scale.ai knows which data sets/data approaches anthropic and openai used to do their RL reasoning training. Meta is paying for that know how/information.
Meta is effectively getting access to all of the training data that every other frontier Lab ever requested from scale so that they can recreate it.
unclear whether wang is bringing a copy of all the data that they previously labeled as part of this 49% stake.
scale does not own the data of most of it’s large customers.
People are saying this is an acquihire, and the article states that Scale AI's CEO will join Meta in a "top leadership role" in their new Superintelligence lab. Does this mean Lecun is stepping down?
This is a new organization, Lecun leads the FAIR team which is more focused on basic ML research than this ASI focused team.
Superintelligence, really? I'm really looking forward to their "super intelligent" stochastic parrots — or stochastic llamas, as the case may be. The only thing "super" here is the ludicrous hype. It's totally out of control.
Meta buying their way into trends generally seems to pan out (WA, Insta, Oculus). Any reason to think this will be different? I’m not familiar with Scale but the particulars of this deal seem odd to me.
The goal of AGI for these companies is to replace human workers.
Funny because Scale AI relies entirely on human workers (for data labeling).
But that's not their long-term goal.
This appears to be a psuedo-acquisition, but with a strange format to appease regulators.
Will this still be an exit event for employees or do they get screwed here?
Sounds like they're getting paid based on his note to employees:
> "The proceeds from Meta's investment will be distributed to those of you who are shareholders and vested equity holders [...] The exceptional team here has been the key to our success, so I'm thrilled to be able to return the favor with this meaningful liquidity distribution."
https://x.com/alexandr_wang/status/1933328165306577316
Yes, it is very good for employees and ex-employees.
Honestly if this acts as a liquidity event for a whole bunch of current employees, while at the same time giving off "Meta hand picked the CEO and whoever they felt were the best AI engineers and jumped ship" energy, I wouldn't be tooo surprised if current "scaliens" view this as the inflection point, and decide it's not worth staying for the other ~51% of their shares.
Sounds like meta gets the data and also anything they can scrape together about what the other labs have been doing to get better results than meta
WCGW with Mark in charge of Ai? Nothing. How could a little "Like" button end up destroying world peace? Absurd.
> end up destroying world peace
... What world peace are you speaking of?
new ai avatars for your metaverse glasses . stock will surely be up
Meta just opened up an opportunity for number two in this space to grow even if it's only to hedge against Meta.
Looks like they are distributing a dividend to shareholders (14$, well below $25), and then diluting everyone.
Has anyone heard a bull case on being a minority shareholder in Scale.ai after this deal? Seems a bit like late stake investors are getting thrown under a bus.
I hope this time they can come up with a model at least or par with open source offerings.
hey or at least not try to fake the benchmarks to fool us...
Posting for postarity, I long said everyone needed to stop everything they were doing and we all put 100% of our effort towards AI.
If AI is solved (we don't have AI yet) then many other problems get solved too.
Reminds me of "Don't dig for the gold, sell the shovels".
Could also be read:
> Meta spends 10% of last year's revenue to acquire 49% of a top AI data company and poach their leadership, to ensure they are a key player in what could be a ~5-trillion dollar industry by 2033.
Meta has a history of this. Acquiring Oculus (and leaning in on VR), Ray-Ban partnership (and leaning in on AR)... etc.
These all just seem like decisions to ensure the company's survival (and participation) in whatever this AI revolution will eventually manifest into.
What top AI company? Certainly not Scale, right? You realise that frontier labs don't really use Scale anymore exactly because they can't be trusted not to sell their secret-sauce human data collection protocols. No-one in the industry takes this guy seriously.
It's always a warning sign where the only thing I know about a CEO is how many podcasts and media events they do each week, and nothing about their business.
Bringing up Oculus and VR is quite fitting, because I think it's the same problem. Meta is attempting to find their next business, but like with social media they don't really have a plan. It worked out well with Facebook and some of the purchases surrounding social media, but it was never a clear path to profit, so they slapped ads on it.
Why does Meta want VR to work? Create the Meta-verse? We're back at why, what problem does it solve? Same with AI, what's the goal here, besides being an AI company?
Just a thought, but VR/AR is constantly recording video and audio.
It wouldn't surprise me if at least some of that data is being piped back to Meta. Data that can latter be used by LLMs to train on.
Even if this isn't enabled on consumer models, on the corporate side it can make sense. Say you're a risk adjuster for a factory. Walk around with your VR headset. In real time MetaOshaHelper can identify issues, you can tag them yourself.
Then send the video back to your on prem LLM for data processing. New hires get a VR headset which can use this data for help on boarding.
Or... Robots will use the data and replace human workers entirely.
> In real time MetaOshaHelper can identify issues
I sort of doubt that most business would want that. Sorry to latch on to one specific thing in an interesting comment. But just imagine having AI tracking in the workplace, e.g. OSHA violations, violations of building code and workplace regulations in general. You'd have shitty manufactures, builders, trucking companies, kitchens, warehouses and everything in between begging you to stop.
Does spell check make writing a book harder?
Occasionally you're going to ignore things that get flagged, but I would love an AI to say oh by the way that machine over there isn't latched on correctly and can fall over if not corrected.
It's cheaper than paying workers comp.
Sure, but have you see building inspectors on YouTube for instance? The amount of extra work would be insane and much harder to dispute in court.
The goal is to manipulate your stock price.
Meta's product is not Instagram or Facebook. It's Meta's stock.
> Create the Meta-verse? We're back at why, what problem does it solve?
theZuck doesn't have to be around other people in the -verse. For him, that's a great solve
Of course the actual shovels are GPUs in this case... so it makes your analogy even stranger.
> the actual shovels are GPUs in this case
This deal brings into focus whether the shovels are data or GPUs. Advantage to data comes, surprisingly, in perishability: a GPU fleet remains cutting edge for only one product cycle.
In the gold-rush metaphor, the data is the cyanide and dynamite.
Remember the Metaverse delusion?
People forgot about that as if Zuck wasn't walking around telling us we'd hang out with friends in virtual spaces, and do activities with goggles on.
I really have got to think about that every time people act like these overvalued companies with unlimited funds know what they're doing.
Roblox, Rec Room, Epic/Fortnite are worth about 10-20% of Meta. There is a market there, Horizon just hasn't worked out and they don't have anything like the amount of technology behind Unreal Engine/Fortnite or even Roblox, closer to Rec Room but without the game design chops.
I mean have you seen the interview he did with Theo Von? The guy is a straight up Alien in the way he talks and acts, all those memes about him being a lizard aren't exactly far off.
He was isolated from the real world starting at around age, what, 22?
I'm all for calling out his random flailing in this space for what it is, but it always strikes me as strange when people are surprised that he's weird and robotic. I'm betting he never learned how to actually interact with other professional humans.
He's lived in a golden tower surrounded by people who agree with him or want something from him since he was 21 or 22. Imagine what you would be like if you didn't have any struggles from such an early age. Imagine what your personality would be like if you didn't have substantive, non-transactional, human interactions since the age of 22.
I kind of feel bad for the guy. His wealth and fame have ensured that he would never be normal, or anything approaching normal. Think about it - how does he even know if he has a bad idea? Do you think there are a ton of people around him that want to call out whatever dumbass idea he has? I doubt it. B-b-b-illions of dollars tends to flavor conversations, I would imagine.
That being said, I don't feel that bad, because he can literally change the world and chooses not to.
'dumb fucks' https://www.businesstoday.in/technology/news/story/mark-zuck...
Their gains from ScaleAI’s next raise will pay this
Will Employees be able to gain any liquidity from their options, or is this technically another round with no tender offer?
From Wang's note to employees (https://x.com/alexandr_wang/status/1933328165306577316):
> Today's investment also allows us to give back in recognition of your hard work and dedication to Scale over the past several years. The proceeds from Meta's investment will be distributed to those of you who are shareholders and vested equity holders, while maintaining the opportunity to continue participating in our future growth as ongoing equity holders. The exceptional team here has been the key to our success, so l'm thrilled to be able to return the favor with this meaningful liquidity distribution.
Outlier isn't worth 14.3 billion...
Is this the same company that has their recruiters (or whatever the hell they're called) spamming me incessantly via all my emails, even the throwaway ones I've used literally one single time that they presumably got via some unscrupulous means, about "annotating" data for training AI? And their rate is something laughable like 20 euros an hour?
We truly live in a clown world when a casual $14B is being chucked at garbage like this, I hope those Iranian nukes turn out to be real this time and I get to be the first in line to be cleansed via nuclear fire, 'cause I'm tired boss.
So Scale needs $14.3B to run their models/etc. That's what I read into this.
so is this going to be the next big thing, like the metaverse? Werent we all supposed to be paying virtual rent?
What's up with metaverese Zuck?
Are you suggesting it has no legs?
LOL, I see what you did there ;-)
Every day for good us
From Wang's Wikipedia:
"During the height of the COVID-19 pandemic, Wang was roommates with his friend Sam Altman, the chief executive officer of OpenAI."
Two mutli-millionaires being roommates sounds pretty strange/funny/weird to me.
Facebook invests in the US Army
Good hire.
Seems like desperation to convince the industry that they're still relevant in AI after the fiasco that was Llama4. Scale doesn't create foundational models, they compile proprietary datasets that everyone has already licensed and trained on - not a lot of reoccurring value. Maybe this slows down competitors a bit but I doubt it.
Good
Get Plus You said: Usernames can only contain letters, digits, dashes and underscores, and must be between 2 and 15 characters long. Please choose another.
Create Account
username: ChatGPT said: It looks like you're trying to create a username and the system has specific rules:
Allowed characters:
Letters (A–Z, a–z)
Digits (0–9)
Dashes -
Underscores _
Not allowed:
Spaces
Symbols like @, ., !, #, etc.
Length: Must be between 2 and 15 characters.
Here are some username ideas that follow the rules:
Sky_Rider
tech-nerd23
LunaWolf
ace_92
PixelDash
Neo_Trek
JetStream7
coder_boy
Jade-Dragon
blink42
Would you like suggestions based on your name, interests, or a theme (e.g. gaming, tech, fantasy)?
You said:
Meta invests $14.3B in Scale AI to kick-start superintelligence lab (nytimes.com) 467 points by RyanShook 5 days ago | 474 comments ChatGPT said: Thanks for sharing the headline: "Meta invests $14.3B in Scale AI to kick-start superintelligence lab (nytimes.com)"
Here's a quick breakdown of what that means (based on the title alone — I can't access the article directly without a link or more detail):
Key Takeaways: Meta (Facebook’s parent company) is making a massive $14.3 billion investment.
The investment is going to Scale AI, a company that specializes in training data for machine learning — essential for large AI models.
The goal is to accelerate work on "superintelligence", a term often used to describe AI that surpasses human-level intelligence.
This could be Meta's answer to OpenAI’s frontier work, Anthropic, or Google DeepMind.
Why It’s Important: $14.3B is a huge amount even by tech standards — signaling Meta’s very serious intent to dominate AI.
It could boost Scale AI into a top-tier partner for training large-scale language models or AGI systems.
Meta might be aiming to own the data pipeline, reducing dependence on open-source or third-party training datasets.
What's Scale AI? Known for labeling data for AI training.
Works with enterprises and governments.
Critical infrastructure in training powerful, accurate models.
If you want a deeper analysis or verified summary from the actual article, feel free to drop the link or ask for a source check — I can pull live data if needed.
You said: Qya shar kron mojha pasa melga os pa ChatGPT said: Agar aap "Meta invests $14.3B in Scale AI" jesa news ya article share karte ho kisi platform (Facebook, WhatsApp, etc.) par, to aapko seedha paisa milne ka koi tareeqa nahi hota — jab tak aap kisi monetized platform par kaam nahi kar rahe.
Lekin paisa kamane ke kuch halal aur real tareeqay hain aise news ko use kar ke:
1. YouTube Shorts ya TikTok Video Banao Aise AI news par short informative videos banao.
Agar views aayein to monetize ho sakta hai.
Example: “Meta ne AI mein 14 billion dollar kyun lagaye?”
2. Blog ya Website Par Article Likho Agar apki site par traffic aata hai, Google AdSense se paisa milta hai.
Aap news ka Urdu mein ya easy explanation likh sakte ho.
3. Facebook Page ya Instagram Reels AI news daily share karo + voiceover do.
Page grow hone par sponsorships mil sakti hain.
4. Picoworkers ya Microtask Sites Wahan par kabhi kabhi task hotay hain: “News share karo” ya “video dekho.”
Direct paisa milta hai har task ka (₹20–₹100 tak).
5. Affiliate Marketing Agar aap AI tools promote karte ho (jaise: ChatGPT, Jasper, Grammarly), to Meta jese news se link karke promote karo.
Agar aap chahte ho ke main aap ke liye koi real earning ka plan banaun (news sharing ya AI topics se), to mujhe batao:
Aap ke paas Facebook page ya YouTube channel hai?
Aap Urdu ya English mein kaam kar sakte ho?
Aap mobile use karte ho ya laptop?
Phir main aap ke hisaab se best plan bataunga.
You said: To is ander kya likho ChatGPT said: Agar aap "Meta invests $14.3B in Scale AI" wali news ko WhatsApp, Facebook group, ya kisi earning platform (jaise Picoworkers, SproutGigs) par share karna chahte ho — to aapko sirf link bhejna kaafi nahi hota, balki uske sath interesting aur simple language mein text likhna padta hai jo logon ka attention le.
Example Text (Urdu + Roman Style): Meta ne 14.3 Billion Dollar invest kiye AI company mein!
Facebook ki parent company Meta ne AI mein dhamaka kar diya — ab Scale AI ke sath mil kar Superintelligent AI banane ka plan hai!
Yani agla zamana sirf AI ka hoga!
Janiye puri detail yahan: [ Link dalen yahan]
Example (English + Short Style): Meta just invested $14.3B in Scale AI!
This could change the future of superintelligent AI forever.
Read what’s happening [Your Link Here]
Tips: Emojis ka use karo — attention ke liye
Roman Urdu ya simple English use karo
Jis platform pe share kar rahe ho, uska mood samjho (e.g., news group vs earning task)
Agar aap chahein to mujhe batayein:
Aap kis platform par share karna chahte ho?
Kis language mein audience zyada active hai? Main uske mutabiq ready-made text de dunga copy-paste ke liye.
You said: Ap bana kado ChatGPT said: Bilkul! Yahan maine aap ke liye 3 ready-made versions bana diye hain jo aap copy-paste kar ke Facebook, WhatsApp, Picoworkers, ya kisi bhi jagah share kar sakte ho:
Roman Urdu Version (Popular Style) Meta ne 14.3 Billion Dollar invest kiye Scale AI mein! Facebook wali company ab Superintelligent AI banane ja rahi hai
Socho future mein AI insanon se zyada intelligent hoga!
Puri detail yahan par dekho: [Yahan link dalo]
English Version (Simple & Professional) Meta just invested $14.3 billion in Scale AI!
They're planning to build a superintelligence lab that could change the future of AI forever.
Must-read update for tech lovers! [Insert your link here]
Earning Platform Task Style (Picoworkers etc.) Task: Read & Share this breaking AI news
Meta has invested $14.3B in Scale AI to build a superintelligence lab
Check article and share it: [Insert your link here]
Done? Submit screenshot as proof
Aap sirf link replace kar den:
[Insert your link here] → is jagah apna NYTimes ya koi bhi article ka link daal den.
Why link to this copyright maximalist site with paywall? They argued against copyright in 2001 (NYT vs Tasini) when it was in their favor, and recently pro copyright (NYT vs OpenAI) because it was in their ..favor. They want to put restrictions on our creativity, to extend copyright from expression to abstractions. I would not touch it with a 10 foot pole.
https://apnews.com/article/meta-ai-superintelligence-agi-sca...
This is as bold as Instagram and WhatsApp were at the time, typical Zuck move, most likely a successful story, perhaps bigger than the other two.
See, when he paid $1 billion in 2012 for a 7 employees company, everybody thought it is the biggest mistake he made.
Who he paid $21.8 billion in 2014 for 55 employees size messaging company, people said similar things, but both turned out to be a great success in market dominance.
Scale serves the top tier AI companies, and Alexandr is a prodigy by all means, so hell ye.
Unlike many other cases where M&A simply killed the companies / product, here it is going to be power multiplier, Meta's data to scale and back, will make scale better and meta's AI better.
A few possibilities:
1. Mark no longer wants to run the company and he is picking alexander wang. 2. Mark believes that Ai is the top priority, his teams have failed, (this is all clearly true so far) and he wants completely change the org structure of his AI efforts (not recommendation but everything else). 3. Mark wants to cut off the supply of information to other labs 4. Mark thinks that full access to ScaleAi's data could accelerate their research and somehow they couldn't do this with a less expensive options.
(2) seems semi-reasonable (in that Meta has failed with near infinite resources) but acquiring a handful of execs for this price seems absurd.
(3) seems like a conspiracy theory and the technology is moving away from this path of data collection, although it is still important at this very moment.
(4) Maybe.
I guess some combination of all 4 is plausible. But the amount of money seems, frankly, absurd.
I wonder if it's really an adjacent benefit to your #4: Mark doesn't just get full access to Scale's data, they also get access to an army of >100,000 data labelers to use however they want.
(5)Retail therapy.
Zuck is depressed as he wants to be liked and the Theo Von interview recently was a disaster.
You and I may buy a new tech toy for $100 to cheer ourselves up, he spent a bit more :-)
I have been working at Scale for 2yrs now. Their data is shit, the majority of the contributions live in the 3rd world and all of them use gpt and other big models. I'm eagerly waiting for the AI hype to disappear to see all those corporates lose their money.
You want your own employer to fail?
gpt laundering as a service?
Exactly
> “…opportunities of this magnitude often come at a cost,” Wang wrote in the memo that he shared on X. “In this instance, that cost is my departure.”
Gavin Belson would be proud. Or at least steal the quote; same thing, really.
I can clearly see a connection between Gavin Belson and Wang
No personal attacks, please.
It doesn’t seem at all wise to give the least ethical among us access to a super intelligence. Not trying to single out Zuck specifically, though his challenges with ethics do seem well documented.
Rather, I’m speaking about the entire industry. Humanity isn’t demanding this, only those at the top seem to want it, and they seem to want it so they can keep more share of the pie for themselves, and decrease the size of everyone else’s share.
It feels like we’re at a very ugly crossroads.
But how else would I be able to generate highly realistic photos of shrimp Jesus? Surely that’s more important than everything else…
Sorry, can you tell me what’s new ?
Sure! It seems they have an actual chance to succeed in their anti-people crusade. That is markedly different than in the past.
Just my 2-cents. Meaningless in the face of it all :)
Alex Wangs x account for any one wanting to read the thoughts of a $14bn mind
https://x.com/alexandr_wang
Meta really love going all in with the hype tech hey!
I'm really not sure why they are acquihiring a digital sweatshop owner. It's not obvious that Wang has any special insight or expertise related to building a Superintelligence other than Data Annotation...
Scale's data annotation platform Outlier is managed with tragicomic, DOGE-style incompetence. It has been in failure mode since around January.
He knows what data cohere, openai and anthropic commission which is a major advantage and I doubt they'll continue relying on scale ai
I assume you could individually poach entire teams away from all 3 companies for much less than $100M so this is still a strange move.
Meta developers can't even make Marketplace search work properly. I can't seem them making a 'super intelligence' LOL
Isn’t that why they are paying scale?
[dead]
[dead]
These numbers are absurd
These people believe they're on track to create life and displace the majority of labor in the world. Nothing else makes the level of investment make sense. It's a prisoner's dilemma where they all think they need to try because regardless of the likelihood of success, the expected value remains astronomical and the risk of not being the winner is extinction.
Yeah, half of my AI skepticism isn't that the tools don't work. It's that I'm having a tough time figuring out how these things are ever going to produce ROI.
Like, at some point the end product needs to be a literal genie's lamp or fountain of youth.
Scale AI has deep cooperation with military agencies and a fresh large contract with the Gulf state with the largest US military presence. It's likely they're building a new generation of combat command systems and the like, consolidation of surveillance and management tooling in the ongoing and future US wars isn't surprising.
[Okay so the third option that I thought of but decided not to put down was: literal genie's lamp, fountain of youth, or robot army. Because then who cares if you collapse the economy if AGI, you'll be safe with your robot army. Not particularly happy that this option is potentially not far from the mark.]
Not sure what you mean, but it's not like the militarisation of "tech" is a secret. The current US administration is bragging about its militaristic totalisation efforts:
https://www.army.mil/article/286317/army_launches_detachment...
[dead]
He spent $45B on Metaverse.
They have reported losing $60 billion in Reality Labs since 2020:
https://www.businessinsider.com/meta-q1-2025-earnings-realit...
$45 billion so far!
Which is the future and we all use on a day-to-day basis these days.
Yeah I don't know how we all managed to survive before we were wearing clunky headsets to play our role as captive audience to advertisers :-)
You are wrong!!! You just dont get it!!! :-D
And counting
If "absurd" implies "too high": I always thought strong reactions to valuations a bit strange. Businesses are complicated and assuming that somebody who is willing to spend billions of dollars thought a bit harder about the value than what I can provide with my gut reaction seems reasonable.
So I started to treat it as more of an update, as in "Huh, my idea of what something is worth just really clashed with the market, curious."
Does not mean the market is right, of course. But most of the time, when digging into it and thinking a bit more about it, I would not be willing to take the short position and as a consequence moderate my reaction.
[dead]
Below article has interesting info but it's paywalled. Does anyone have a way to read this?
https://www.theinformation.com/articles/fame-feud-and-fortun...
Edit (as per wikipedia):
"Lucy Guo was fired two years later in 2018." She was a co-founder.
The Information's paywall seems pretty impervious these days.
And now she runs Onlyfans for minors....
Well if there's one thing the AI segment is lacking, it's funding.
Why is people letting these unelected companies reshape the world?
Honest question: Do you want elected politicians reshape the world?
I'd prefer that to companies.
Really? Interesting. What country do you live in?
Spain.
Meta bought Scale for 14.3 Billion. This is the the new way Google, MS, Meta buy other companies and avoid any scrutiny. They invest huge amounts of cash and then the CEO comes to work for them. Anti Trust law is circumvent while the big companies gobble up any competition.
I haven't read the article yet (I'm about to) but I'm curious: what are Yann's views on this? He's been pretty vocal that LLMs won't lead to AGI.
Edit: read the article. No mention of Yann. What kind of journalists are these people, to not get viewpoints from different angles? They might as well just reproduce press releases and be done with it.
I'm not sure if that's really relevant?
You can believe LLMs won't lead to AGI and still believe that spending billions to have a best in class model will allow you to make products that will recoup that investment.