The Metaverse was always such a bad direction. At the time, I was really unsure about my intuition -- I figured that if Mark Zuckerberg decided it's worth pivoting his entire company towards that goal, he surely must have some data to back that up. As it stands, my intuition (and everybody else's) turned out to be right.
It's been the same with crypto, for that matter. None of the reasonable people I know ever saw any grand value in crypto. Researching myself, it always just seemed to be a bullshit fractal. At the height of the crypto boom, I was beginning to doubt my conclusions and started to think that perhaps the societal nature of crypto is a force in itself. Like religion, if enough people believe in it, it becomes reality to some extent. But now we see that crypto was indeed bullshit all along.
Contrast that with the generative AI models revolution. It's clear to anyone from day one how useful those models will be, and that they are providing clear value right away. It's no wonder that all the companies are immediately pivoting towards it. Maybe Mark Zuckerberg was just unlucky to decide on a company pivot two years too early -- I'm sure that if he had to decide on a direction to pivot to today, it'd be towards generative AI.
Personally I predict that generative AI is going to be the next Metaverse and crypto.
It's not about whether or not there is value there to be provided. VR and cyrpto provide value too, it's just that the markets for that tech are way more "niche" than companies were hoping for.
And I don't think VR is going away. If it wasn't dead in the water in the 90s, then it's not going to die because the Metaverse failed. But its applicability is currently limited to a few niche applications like video games and possibly CAD type software.
The thing that generative AI has going for it is that it is extremely broad in so far as its applicability. In other words, good luck selling my next door neighbour on generative AI. What is it? What is it good for? What problems does it solve in the here and now?
Generative AI is like electricity, only I don't think quite as useful. The point is that, on its own, it has no value what-so-ever. The value lies in what it is used for.
Right now what I am observing is a phenomenon that is way too common in our industry. Companies are rushing to go to market with some AI "thing." 99.9999% of those "things" will end up being more versions of the Metaverse and crypto. Because most of these companies aren't really sure what problem they are solving for actual people. It's all so novel and abstract and people are seeing dollar signs with very little understanding of how they are going to put it to use.
Where it finds its uses, I predict will be limited to the same applications that we're already using ML for. Chat bots, entertainment, generating document outlines etc. Just because we made a big breakthrough with the technology doesn't mean that we've actually created a solution to real world problems that real world people are having here and now in the real world. No one, other than maybe Open AI, is going to get rich on "generative AI." If they get rich and change the industry, it will be finding a use for it that many people want.
I think crypto, metaverse, and generative AI are all really different -- and I agree with the original poster. Generative AI seems much more likely to be a game changer.
Crypto was something I always struggled to make sense of. My son asked, "why didn't I buy bitcoin when it was a few cents?!" -- The simple answer was it didn't seem like it had much use. The value in crypto eventually came in the form of a pyramid scheme. Admittedly, I do use crypto to do transactions with untrustworthy people (don't have to worry about chargebacks and things like that). But it's hype was around it being a speculative commodity. For normal people -- it's just not all that useful.
The metaverse is different in that I do see the theoretical value in it. But it seems a LONG way off. I haven't seen anything that really makes me think, "wow -- this is it". It doesn't seem like we're close. And honestly I think generative AI maybe a prerequisite to deliver a truly valuable metaverse.
Generative AI is useful now and represents a huge leap over the state of the art, not that long ago. I worked with RNNs and LSTMs to answer questions not that many years ago, and honestly I wouldn't have predicted this level of effectiveness for LLMs for probably 20 plus years -- and I certainly didn't know how we'd do it. But more importantly I'm finding it valuable today. As I noted in another post -- ChatGPT-4 already has shown better differential diagnosis skills than my family's doctor. I use it literally every day already. There are things that I want it to do that would make my life 10x better -- and I could see a clear path to get there (like, if that was my day job I think I could put together a project plan to deliver it).
I just don't think these techs are comparable at all.
People seem to see new developments as black boxes that you can't analyze. Like they see something new and ask themselves "will it work?" and then say it will work or not based on whether the last thing worked... with zero nuance.
Let's try to analyze crypto on its own as an example: yes, crypto was a new frontier in money supply, but what makes it critically different? And are these critical differences actually desired?
Crypto was critically different in that it would decentralize the financial system.
Was it desired?
Centralized institutions are unfair and can be in-equal, but they are actually really great. When the financial becomes unstable, these institutions intervene and settle things down (see the Great Depression). When someone steals from my credit card, I just call up my bank and they fix it. How would crypto handle these situations?
No one could figure it out. So if crypto was trying to sell something that no one really wanted, how the heck could it work? ...then it crashed... because there was no centralized control. It's not like we haven't had this happen in history already.
> Centralized institutions are unfair and can be in-equal, but they are actually really great. When the financial becomes unstable, these institutions intervene and settle things down (see the Great Depression).
Interestingly, there is a well respected school of thought in economics that pins the blame for the boom/bust cycle on artificially manipulating interest rates via that exact centralization.
> When someone steals from my credit card, I just call up my bank and they fix it.
I'm not really sure how that is an example of "centralization." A private lender with whom you've entered into a loan agreement does not control the supply of the currency. They could just as easily be lending you gold or bread. I'm no cyrpto fanboy ... couldn't really care less about it ... but in theory there is no reason that a bank couldn't lend you Bitcoins or something. If there is a problem with the currency that's going to bite you regardless of what the currency is.
I think the strongest case for crypto was using it as a hedge against inflation. Inflation being an increase in the supply of fiat currency. Something that, whether you subscribe to the "Mises school" of economics or not, is irrefutably caused by the central bank creating new currency out of thin air, thus diluting the purchasing power of the existing money in circulation. I propose that that is "irrefutable" because, in order to debunk it, you would have to demonstrate that the law of supply and demand is false and/or that currency is not a commodity subject to the same "rules" as every other.
I don’t disagree that the boom/bust cycle could be created by centralization, but I also don’t care I suppose. I mean, there’s no perfect solution out there so a boom/bust is a reasonably mild price.
A large reason why crypto, at least in the current implementations, can provide decentralization is by removing discretion from any authority and making transactions permanent. That’s in contrast to our current money system, because it’s merely numbers that ultimately can be manipulated by central authorities and accessible by law enforcement, that ultimately means that transactions are not truly permanent and that allows us to repair mistakes after the fact, a feature not really afforded by crypto. It’s a very helpful feature.
I also consider a consistent amount of inflation an important feature of any successful economy. Without inflation, I would be incentivized to hold my money whenever I expect deflation, which is terrible because it’s basically me hoarding value from society.
Runaway inflation is absolutely disastrous and I don’t see how crypto could have been considered a hedge against it if its entire value is backed purely by speculative demand. Contrast that to the USD or other currency where that is backed by the full faith and credit of a government. Obviously that is meaningless of we’re talking about, say, Argentina but the US has successfully been the same, largely dependable, and boring government for 245 years and through earning a reputation with time that the USD can be treated as a reserve currency.
I don't think crypto, as most chains implement it, is at all vulnerable to runaway inflation.
A functional crypto can go downhill for a lot of reasons. Technical failures. Association with scams.
But I am not sure how a tightly controlled supply over time, or asymptotically fixed supply, coin can have runaway inflation - if everyone starts demanding more of the coin for goods and services, there just isn't more of the coin for that.
I agree. VR will have killer apps in particular domains, but that doesn’t mean it will be used by everyone all of the time. For example, I work in ocean mapping where we have large amounts of point cloud data that need occasional manual editing/QAQC in an environment that matches the dimensionality of the data. My colleagues are working on some very interesting VR point cloud editing tools [1].
That doesn't return your money to you like the credit card though. The irreversibility 'feature' of most cryptocurrencies makes it really hard to recover funds stolen through fraud... I guess that is a desirable feature for anybody performing fraud though.
Nothing is ever irreversible, it's just a question of how expensive it is to make the database writes. Ethereum forked the whole currency to undo a write (the DAO hack) and if the legal system can find a hacker they can make them reverse their transaction.
…But having someone with admin access over the network and can fix mistakes is just a lot cheaper than refusing to build that in for ideological reasons.
Most (but not all) things in life are technically reversible. But some things are so difficult or expensive to reverse that they are effectively irreversible nonetheless.
I think crypto is great for anonymous digital markets. It would be great to disrupt the financial industry, but that's a really big thing. For the markets, I think NFTs is a really good use case. That's a way for artists to have digital galleries, receiving international payments, work can get traded, all independent of the marketplace itself. No company behind that. Books, audio content, ..., and so on are also easily the target of a next generation. I don't believe in this tokenization of physical goods, because then you have a company behind creating the link between token and good. But for purely virtual goods, I think it is great.
> Honestly, I still don't see how. None of the explanations make any real sense to me.
I don't really think NFTs have a real use case, but i can see why it might. It is effectively a digital certificate of authenticity that cannot be faked. But like a physical certificate of authenticity, it is worth as much as the general market would place trust in it. And it isn't much, since collectors of digital goods currently do not value authenticity (realistically) - they value the actual digital good, and thus, a copy is as good as the "real thing".
Therefore, collectors can only really exist for physical goods, and thus NFTs don't actually provide much value, beyond the ability for someone to speculate with it.
This is interesting because I haven't heard of this. Would it be something like your license is controlled by you? Somehow you have to keep it private though. Having someone control a position on the blockchain wouldn't seem to be that different than name and password. You can use that to prove who you are, and you can lose that just like you can lose control of your crypto wallet if you forget your password or someone guesses it or hacks your machine.
One workaround would be to store the license/registration tokens in multisig wallets, requiring both the licensee and the DMV to approve of transfers (or add a third signer and go with two of three). A fair bit more centralized than what's ideal, but the very concept of a state-issued license or registration is already implicitly centralized anyway.
The desire to have untraceable money isn't always because you're trying to do something illegal or immoral.
Privacy is important to people, and that even extends to privacy from your government. You never know when your government might change from a responsible, fair entity, to a oppressive regime.
If you do buy a mansion with unreported billions and you're buying from a reputable buyer, then you'd expect the government to know about that sale, but if you're stock piling assets in case you need to flee from your government to survive, having anonymous money that's easy to transport is valuable.
Has nothing to do with my question but I agree with everything you said.
> You never know when your government might change from a responsible, fair entity, to a oppressive regime.
Truer words were never spoken. It is hard to get this across to people with the completely understandable "I didn't do anything wrong so nothing can happen to me" attitude.
As Beria said, "Show me the man and I'll find you the crime"...
Yeah, it's weird that people can perceive anonymous transactions to be only valuable to ne-er-do-wells at the same time that large swaths of the US are criminalizing access to abortifacients.
Crypto would be extremely useful if it were wholeheartedly adopted by the government of a medium-sized country. The fundamentals of cryptocurrency are as good as the gold standard, maybe slightly better, and could be better than fiat; the problem is that no one pays their taxes in it so no one uses it as a real currency. Likewise, NFT’s could be used to implement property titles if a government ever agreed to enforce them. Then things like smart contracts and whatnot start to look a lot more interesting. The problem is that the entire crypto economy is a fake play-money ecosystem with no power over physical reality.
This went from +2 to -1 overnight, and I'm not complaining; I'm just curious if I got downvoted by the crypto haters or by the crypto supporters. Such is the risk of expressing a nuanced opinion on Hacker News I suppose.
The thing you're missing is there are no incentives for a sovereign nation to give up the ability to mint their own currency and control its supply (monetary policy).
There’s a reason I said “medium-sized country”. The US, EU, and apparently now China wouldn’t be interested because they are world reserve currencies, or aspire to be in China’s case. On the other hand, you could probably make a case to voters for cryptocurrency to replace something utterly dysfunctional like the Argentine peso. Crypto doesn’t really do much for a country with functioning and trustworthy governing institutions, but not every country has that.
Generative AI basically unlocks the metaverse, since all the 3D environment can now be generated.
The metaverse changes people's context and senses with generated data. Interestingly AI will paint a new world for humans to learn and experience new situations more often, more easily on a broader spectrum.
Exciting !
> Interestingly AI will paint a new world for humans to learn and experience new situations more often, more easily on a broader spectrum.
This is ignoring the instinct built over generations that humans don't want to "experience a new world", they want to explore it with other humans.
We are social animals. Facebook is so successful because it started out as a way to connect more with people you already knew or were acquainted with.
The "metaverse" and all its AI-generated worlds add little to no value in that direction. Wake me up when the metaverse makes it trivial to host a garden party and cook for the 5-10 attendees.
> This is ignoring the instinct built over generations that humans don't want to "experience a new world", they want to explore it with other humans.
I think humans want to explore it with intelligent beings, not necessarily “humans”. These new technologies have the potential to create agents in the movie “Her” sense that are compelling to interact with. The metaverse applicability seems clear.
You and your friends jump in the metaverse every Tuesday night to play some virtual game, e.g., go hunting or rob a bank. Timmothy is out on vacation this week so won't be joining -- but now you can spawn up virtual Timothy, which is trained on a bunch of Timothy's data (see the other HN post about the guy who trained his bot on his friends group chats). Now Timothy is with his friends in this virtual world and he behaves mostly how Timothy does.
> now you can spawn up virtual Timothy, which is trained on a bunch of Timothy's data
Not just no, but hell no.
If I'm going to play with a robot, I absolutely don't want it to replicate a friend. Even more, I would be furious if any of my friends replicated me like that.
When I'm playing with my friends, I'm doing it to play with my friends, not simulacra of my friends.
It won’t start with Timmothy. It’ll start with John Cena or Donald Trump. You’ll get to play with virtual celebrities. Then domain experts, like tennis camp with Serena Williams. Or story telling with Steven King. Or Fortnite with Ninja. And it will slowly find its way down the popularity slide to friends.
And you will protest it. Just like my MIL hates Facebook and thinks calling is so much more efficient than texting. But the younger generation will find this as natural as TikTok.
I wouldn't protest any of those things (assuming the celebrities consent to it). You're right that such a thing holds zero interest to me, but I don't find the idea objectionable. Celebrities are essentially "virtual people" to begin with (that is, celebrities are playing a role in public appearance -- you aren't seeing their true selves).
But I find the idea of replacing actual friends with simulations to be inherently objectionable.
Virtual timothy plays better and without complaining. Weeks later the gang dreams of virtual tim. A week later they start playing, but this time without Tim.
I think that's what people do on a normal day, but all of the technical formats and decisions (vhs/dvd/streaming video/etc) have been pioneered by porn.
So, pretty much what you said, but probably having sex with anime girls instead.
> I think humans want to explore it with intelligent beings, not necessarily “humans”.
I think the majority humans want to be with humans, not just intelligent beings. Some don't, of course, and there's probably a decent business catering to them.
I do think generative AI has some really interesting possibilities for interactive media - but I don't see how it unlocks anything.
It's clear there's a market for well-designed and compelling VR chat. VRChat[1] has a large community and had a very active developer community[2]. Facebook had no luck in attracting users in a proven market - there's no reason to believe their products would be more popular after hooking a generative agent up to it.
If you are looking for "the metaverse" in a generic sense - other people are already doing it better than Facebook (and have been for some time). It's been unlocked for years. Facebook hasn't even managed a capable clone, much less broken new ground.
> It's clear there's a market for well-designed and compelling VR chat. VRChat[1] has a large community and had a very active developer community[2]. Facebook had no luck in attracting users in a proven market - there's no reason to believe their products would be more popular after hooking a generative agent up to it.
Facebook gets to take 30% of VR Chat's gross revenue (they sell premium features) on standalone and the desktop Oculus store.
Apple likely makes more profit off Roblox than Roblox.
Honestly I don’t think content generation is a limiting factor for a compelling meta verse. IMO the constraints are more to do with fidelity and the quality of the experience.
There are currently so many weaknesses and limitations with the medium of VR that it’s just not particularly appealing for folks to spend a lot of time using it, and I think that’s why you don’t have great content gen.
You've pretty much nailed what I've been thinking about when comparing generative AI hype to crypto/metaverse hype.
I keep hearing this argument that generative AI has more utility, making it more "real". Sure, but they're missing the point, which is that people made some pretty ridiculous claims about the future utility of crypto / metaverse ($100k bitcoin, metaverse real-estate speculation) rather than the present day possibilities, and they're continuing to make ridiculous claims about the future utility of AI (the end of web development, AGI soon, etc).
The hype isn't about present day possibilities, but about future speculation, and the future speculation can get off-the-rails crazy.
The hype exists, firstly, because the present day possibilities are already impressive enough to net actual financial gains from improved productivity, and secondly because it's obvious that all this stuff hasn't yet been scaled to the limit - but the scaling and improvement that we've seen so far (GPT 3 -> 3.5 -> 4) showed massive gains on every step in a very short period of time.
Incidentally I was about to say that even speculation based on present utility can get a little bit out there. Modern AI is already quite good at generating code snippets, and it already increases developer productivity, but just how much is that going to really change things? Just how much more productive is an AI-augmented software developer? Are LLMs really the thing that was missing from no-code website / app builders?
I wouldn't say it's obvious that this stuff hasn't been scaled to the limit. I mean, sure, you could make bigger LLMs, but I don't think it's a given that LLM performance will increase in performance in a predictable fashion. If anything I think that performance probably resembles an S curve where performance matches improvements in scale before sharply plateauing. When's the plateau?
GPT-4 is a clear improvement over GPT-3, but it's also 6x larger, and so far I haven't quite seen any real evidence to suggest that it's 6x better, other than the fact that it scored better on tests.
It's hard to say what "6x better" even means, but there are tasks that GPT-3.5 consistently fails hard at that GPT-4 is much better at (and has improved over time).
I think the next big leap will be the context size. Going from 4k to 32k tokens means that the model can see a lot more when generating the answer. For code especially this makes a big difference in the ability to reason about it.
As to the limits, it's hard to predict because what we're seeing is more of a series of sudden leaps. But let me put it this way - so far we've seen noticeable improvements on every iteration of the new LLMs. So given this, why should the default assumption be that the limit past which nothing new will emerge, whatever it is, is close to the present size of the publicly available models?
Is anyone doing static code analysis with GPT? It seems like an excellent idea. I think a combination of formal analysis methods together with blackbox GPT magic will be a killer combination. That said, the market is tiny.
There is zero evidence that GPT-4 is a trillion parameter model and some evidence that it is the same parameter size as GPT-3.
Newer research and models out of DeepMind etc. show that GPT-4 performance is attainable at 90% the size of GPT-3. It's well known by now that GPT-3 was hugely over parameterized.
I think it’s extremely dangerous to predict the pattern of gains to continue.
Also I’m not actually convinced that there’s much value provided currently. I’ve yet to see a particularly compelling use case, and every time I go to try something that folks are hyping up (image generation, ChatGPT, copilot) I leave feeling like it’s all sizzle and no steak.
> The people that aren't seeing a compelling use case simply aren't looking.
By all means, go do your startup, all the power to you.
But I personally fail to see it creating enough value for people to even bother use the AI, even if it's free and any problem could be ignored.
I can imagine people adopting it if it comes embedded on whatever software they already use. But that doesn't "completely change everything" or any of the other things people are repeating.
And yeah, I can't imagine it quickly improving so that happens either. I am personally bracing for a new AI winter, and believe that word is going to become more toxic than it has ever been.
I think generative AI has incremental utility. You can't half-use Bitcoin or the Metaverse; the idea is nonsensical. Bitcoin moves data around very slowly and at enormous cost, and the Metaverse provides vertigo-inducing VRChat for uncanny valley Mii avatars, but they're only usable if you go all-in.
Even if generative AI is not a gamechanging buzzword paradigm shift it's still useful for making existing tasks easier. Predicting the next sentence is autocomplete for word documents and phone keyboards, and we're already seeing it roll out. Artists who've gotten over the AI backlash can use it for backgrounds or textures, and designers can churn out those stylised low detail corporate-website graphics. Amateur authors on sites like RoyalRoad are already creating cover art and character portraits with AI generators. Millions of horny internet weirdos now have access to oddly specific pornography, and even if the AI gets the hands wrong they can retouch it in Krita.
Probably (>50%) we'll all be bored of it in 20 years and admit the hype was overblown, but I also think we'll see it integrated into day-to-day tasks in a way that Bitcoin and the Metaverse aren't.
That's kind of what I was betting on. I don't see it going away anytime soon, but I also think it's potential impact is being overblown.
With regards to AI image generators, I think people overestimate the importance of illustration skills to visual creatives. Namely, if you look at the top graphic designers, something you pick up on is that they aren't necessarily known for their top-tier illustration skills. Anyone can theoretically make a logo in the style of Paul Rand, yet curiously, hardly anyone ever does.
Even if the person in question is an illustrator, I think what fundamentally makes them valuable as an illustrator is that they know what to draw rather than how to draw.
It's sentiments like these that make me question the notion of certain careers getting disrupted by AI as opposed to simply improved by it.
I think you're both right. I think generative AI will be like the internet, and we'll experience a 90s-style bubble first, then it will gradually transform everything.
Personally though, I've already used it for multiple real-world applications in my business and personal life, whereas crypto was only ever a toy. VR I'm less sure about; so far it's only a toy, and I think it will take longer than AI to make a real difference, but I wouldn't be surprised if at least AR and probably VR are both eventually very commonplace.
FWIW, I've found uses for it already that will improve the company I'm building in the very short term. Maybe you disagree in the magnitude of the value, but I find it to be at least somewhat significant. Enough to pursue.
I've never worked for any company where leaning into the Metaverse or crypto would generate any meaningful business value, short or long term. The promises for Metaverse and crypto are always about a nebulous future that could exist if only everyone collectively bought into the vision.
Anything that is limited to the the company you're building at the moment sounds to me like the very definition of "niche application."
If you re-read my comment I didn't say that generative AI does not have any potential to solve any problems ever. What I said is that companies are currently racing to go to market with some "ai thing" and most are chasing it because it is the "next big thing" in their mind, not because they know what problems for their end users that it can actually help solve.
I know of companies right now who are banking on "selling AI to customers." That is doomed to fail in my opinion. Customers don't care about AI outside of the novelty and entertainment value it may possess. They have actual problems that need solving. My point was that generative AI, as the broad umbrella that it is, will see the hype train die and people will realize that "it" is not the revolutionary and disruptive Internet or printing press like invention that they think it will be. The value will be in individual applications of it, of which there will be a few but not as many I think people think there will be.
> that companies are currently racing to go to market with some "ai thing" and most are chasing it because it is the "next big thing" in their mind, not because they know what problems for their end users that it can actually help solve.
And if you re-read my comment, what I am saying is that while I'm not exactly "racing", I do have a very clear problem for my end users that this actually helps to solve. Its possible I could've cobbled together a similar solution with other technologies, but I didn't see a very clear path forward on this user-facing problem until very recent developments.
I suspect that the people in this same boat far outnumber people in the Metaverse or crypto equivalents.
The metaverse and crypto were entirely about some kind of future industry and society-changing application. "You don't see anything _now,_ but the future will be unrecognizable, trust me!"
Gen AI definitely has utility right now, and for some it's a lot of utility. But the hype around it is exactly the same, the hype is all around how "the future will be unrecognizable, trust me!"
So I agree that practically, Gen AI is utterly different from crypto/metaverse, it's a real thing with real value. But it's also attracting the exact same hucksters and they're kind of sucking all the air out of the room.
I think the biggest societal impact may be not “utility” at all but rather on the social side of things. The chatbots are nerfed right now because the big companies don’t want them “acting weird” and doing things like the infamous jealous girlfriend convo between Kevin Roose and “Sydney”. But the idea behind the movie Her is essentially demonstrable now, and people are going to deliver those experiences.
I think things are going to get really weird. The prospect that my teenage son might have a virtual girlfriend does not seem sci-fi at all. Economically speaking, will people pay to chat and sext with “people”? I think yes?
People keep saying that, but I don't see it. So far we have chat bots, and Copilot. Copilot is going to be in legal limbo for years until the license issues are solved. Chatting with bing is fun and all but I don't see the long term utility.
What is the utility right now? Which of my problems are solved?
* My company has a very large codebase, and I am not familiar with 99% of it. I can use an AI assistant like Sourcegraph Cody to explain parts of the codebase to me at a high level, and suggest areas where I should dive in to address my specific problem.
* If I am working with a language, library, or framework I have not used before, I can ask ChatGPT to explain how a certain function works, and provide some code examples. If I write some code an get unexpected results, I can paste my code and results into ChatGPT, and ask it to tell me what went wrong.
* Someone sends me a spreadsheet that specifies some business logic, and I want to transform that spreadsheet into a YAML file, and write some code to parse the YAML config and take some action based on user-supplied data. ChatGPT is pretty good at this.
In all of these cases, I have to take the AI output with a grain of salt, and may have to do some supplementary research or debugging. But that's also the case when I ask coworkers for help. Right now, I would say generative AI provides a small boost to my productivity, but I can see that boost growing larger as language models improve.
I do. I care about my problems and what it does for me. I regularly employ ChatGPT to help me solve arbitrary tasks from writing code, debugging code, learning Korean, and cutting writing time in half.
> The thing that generative AI has going for it is that it is extremely broad in so far as its applicability. In other words, good luck selling my next door neighbour on generative AI. What is it? What is it good for? What problems does it solve in the here and now?
Disagree; I'd argue that the key distinction between generative AI and those other things (metaverse/crypto) is that the value of it is immediately apparent to almost anyone. There's a reason ChatGPT ended up becoming a household name with literally no marketing whatsoever.
> the value of it is immediately apparent to almost anyone
I'm not so sure that's actually true outside of enthusiast circles, to be honest. The value of what the hype describes is apparent, but the hype is about a possible future, not what's actually here right now.
There are a couple of people in my workplace who are using ChatGPT as part of their development process. So far, the value of them doing so isn't obvious to the rest of us. Their work isn't better, nor are they working more productively (although they think they are).
> There's a reason ChatGPT ended up becoming a household name with literally no marketing whatsoever.
Most noncomputer people I know have barely heard of ChatGPT, and those that have only know of it by the hype that has spilled over into the news feeds. They certainly don't really know what it is, and don't think of it as being anything important.
Those that do understand it and think it's important mostly consider it a threat and are afraid of it.
I do think there is a pretty extreme overlap between generative AI early adoptors and people who are excited to spend half of their waking hours interacting with an AI assisstant. Interest in the raw tech fades pretty fast the further you get from very online groups.
That said, the new tech is powerful and likely to have a large impact, just not as much through new interfaces as the hype suggests.
Unfortunately I think the biggest use-case for generative AI in the medium term will be automating away middle class jobs. The cabability is looking very possible, and the profit motive is immense. Despite the fun creative uses and the strong PR, the development of this tech is extremely profit focused.
Everyday people will likely feel the effects of this tech, but it mostly won't come in the form of fun and games.
I'm also terrified that the AI optimists are right. I feel like the closest analogy to the "upside" case is the advent of offshoring. Millions of middle class jobs will be wiped out in exchange for higher corporate profits and cheaper socks. Except in the AI case there won't be millions of people in other countries lifted out of poverty; all these profits will flow to the wealthy.
My 65 year old, tech illiterate mom messaged me the other day and asked if ChatGPT or Midjourney could be used to generate layouts for her new garden. I'm not kidding.
Of course the non-techies know it from the hype in the news; that's the usual pipeline. And of course they don't know "what it really is", because that requires specialized knowledge. But whether they "think of it as being anything important" is more a function of your circles; in mine, people are mostly terrified of what it will do to jobs and how it'll be used for surveillance.
You said that about "those that do understand it", which to me implies at least some degree of technical understanding. I'm talking about casual users with no background whatsoever, who have just been exposed to ChatGPT or (mostly) Bing AI.
Cool, so I'm Joe Sixpack next door. Things I care about: how to feed my kids, avoid getting laid off at the manufacturing plant I work for and my oldest daughter is learning to drive and has no idea how she's going to be able to afford a home of her own and, despite how much I love my kids, I really want her to move out before she's 30 so that my wife and I can enjoy retirement. Things I do for fun: play sports, video games and drink.
What problems in my life does generative AI immediately and obviously solve for me?
Like I said, it is "abstract" which is why you can make such a claim with such a high degree of confidence. Every person who sees POTENTIAL with generative AI has their own ideas as to what sorts of applications it has that they would find useful. The very words "generative AI" and "ChatGPT" create a Barnum Effect (https://en.wikipedia.org/wiki/Barnum_effect). Right now, I would posit that ChatGPT is like pet rocks. It got popular because it is neat and novel. Once that effect wears off, people will stop caring and the hype train will die as fast as crypto.
Therefore, until a company releases a product that uses ChatGPT under the hood and solves a real problem that a lot of people need solving right now, there's no tangible value that is inherent in the technology that can be identified. Only ideas and potentials.
Your problem is that you think we need to sell generative AI to Joe for it to be significant.
> video games
Cool. There is a very real chance that he will have more of those because they will be cheaper to make. He won’t be using the generative AIs, he will be consuming content made with them.
> my wife and I can enjoy retirement
Joe doesn’t have to worry about retirement. Someone will use a combination of these AI technologies to make his wife fall in love with a perfectly attentive, smoky voiced older guy. When this AI powered person suffers a terrible car accident on a business trip she sends a significant portion of their savings to him. When Joe finds out he immediately calls his bank. There an other AI powered agent handles his issue. It takes a while for Joe to be understood, because the agent he is interacting with is heavily biased towards trying to upsell Joe on a new mortage.
Eventually he is able to claw back some of the money, but the stress and the implied emotional infidelity ruins their mariage. He talks with the assistant of a divorce lawyer (another AI). She collects all the information from him and the lawyer (this time a real person, albeit one heavily supported by various AI systems) sends over all the paperwork. The AI of Joe’s lawyer agrees with the AI of his wife’s layer about the details and once that is done the humans sign the papers and they are divorced.
Joe still has some money left. He can rent a bungallow and maybe he can spend his retirement there, but unfortunately Joe picks up a nasty addiction to online porn. (What Joe doesn’t know that the booties he is looking at are generated exactly to his taste, as measured by his pattern of clicking on the free samples.) This is the last straw, the addiction sucks Joe’s wallet empty and he dies destitute. Many many people with generative AIs have Joe’s money now.
To his last breath Joe doesn’t really understand what this AI thing is everyone is talking about on the news.
It's not clear that Joe Sixpack even owns a computer from this description. Joe may not even have internet access -- just cable and a console. And there are probably a lot of folks in this bucket still, but it's categorically one that generative AI isn't personally useful for (though they may be affected by the tech indirectly.)
But for anyone who performs knowledge work on a computer, or has a question about an offbeat subject, or needs help learning a new skill (eg, Joe's daughter wants to know why a certain answer on the practice drivers' exam is wrong), or needs to improve written communication, or wants a summary of a complex topic, or needs help transforming text... a very large group of ordinary people can still benefit from this tech.
Your daughter can use the new learning tutor, based on generative AI, that helps with her coursework and learn new materials. It's like an expert tutor in a bunch of fields that she didn't have access to before -- at least not at a reasonable price.
Now your daughter has learned a lot more, has opened up a world of possibilities and this helps her get a job (or create a company) that helps her buy a new home.
Also for video games, they could use these generative AIs to create more immersive characters and worlds. Your video game experience just became much better -- especially if you're drinking while playing.
And if you play sports at a local level, generative AI can take in as input a bunch of rosters and play-by-play data (maybe eventually creating the play-by-play data directly from video) and being able to output stories about games. Today coverage of local and club sports is limited because of resources -- but if you could apply AI to this problem then you're local bowling league could almost be covered like the NFL on the web.
EDIT: And another thing -- which actually is something we started doing now. You have a personal medical assistant that you use with your doctor to ensure that your wife gets the help she needs with her current condition. Joe Sixpack is happy that it is much less likely that the doctor misses something "obvious".
>Your daughter can use the new learning tutor, based on generative AI, that helps with her coursework and learn new materials. It's like an expert tutor in a bunch of fields that she didn't have access to before -- at least not at a reasonable price.
Now your daughter has learned a lot more, has opened up a world of possibilities and this helps her get a job (or create a company) that helps her buy a new home.
Those two paragraphs look like they are in opposition to me. If a degree becomes that much easier to get with AI assistance, then everybody else is also using the same assistance, and then the jobs available to graduates in that degree have also become less valuable as companies no longer need to hire them and they start laying off people already in those jobs.
I mean, off the bat you might use it to replace Google, like bing is already doing.
And it doesn't have to solve a problem for you to make an impact on your life- it can make your life worse too. If your daughter is interested in writing, graphic design,or programming, well, finding a job and moving out by 30 might become a lot harder. Bing is already in use. Copilot is already in use. These are not small markets or use cases.
> I mean, off the bat you might use it to replace Google, like bing is already doing.
That's not for me. I gave it a try for a couple of days, but using ChatGPT as a search engine is much, much less useful to me than the old-fashioned method.
Bing was already in use before ChatGPT and Copilot is seen by most as an evolution of auto-complete. My last paragraph specifically said that I predict that the applications for generative AI will be in areas where we're already using ML. Search and auto-complete are two examples.
> Things I do for fun: play sports, video games and drink.
Video game NPCs will very quickly be replaced by LLms. No more boring scripted dialogue. This allows for a truly open world where the inhabitants can dynamically respond to your actions. Video games will become cheaper to create with generative AI that can quickly create a layout of a game world that can then be built on.
No more boring scripted dialogue. Now you get boring, procedurally generated dialog. About things that don’t matter, don’t make sense, or veer wayyyy off topic.
You fundamentally cannot make a random npc interesting because they are not supposed to be interesting. Ideally they say very little.
Agreed that LLMs, etc., will game development _cheaper_ by requiring less labor. It seems like software development in particular is will be getting a lot of powerful new tools over the next few years.
> Video game NPCs will very quickly be replaced by LLms. No more boring scripted dialogue.
I'm skeptical that this is what the users want. Sure, it would be nice to have, say, less repetitive background chatter in Skyrim. But, human-scripted dialog is intentional, which is at the core of a lot of gaming. Take that away and you end up with the early versions of No Man's Sky, where yes, there's an infinity of different variations to explore. But it wasn't what users actually wanted; they wanted a designed experience.
Sure, there are still scripted stories/quests and what not. But the background characters can become much more interesting if they're all LLMs that are just given a prompt like "you live in this cabin and are a subsistence farmer who has a dark secret" or something instead of just standing around looping a few lines. Open world games don't feel organic at all imo because these characters who should be adding flavor and making the game dynamic are just completely static.
I think whether or not it will actually be cheaper remains to be seen. Right now many AI products are still being heavily subsidized, thus the cheap or free price tag. Once these services decide they need to monetize, it may not be cost effective for most video games at scale. Maybe eventually these computations can (reasonably) take place on the client side, but I think that's so far away that we could very well see another paradigm shift by the time that's realized.
Crypto generated an insane amount of general public mindshare with zero marketing. I wouldn’t read too much into that as a signal. I do think the value prop is a lot more straightforward, but that doesn’t necessarily mean it’s not mostly hype.
I mostly agree with this -- the converged value will be ~1% of the initial hype. 1% of hype is still massive.
After the noise has calmed, I feel generative AI, at its core, will enhance information search and summarization; lookup and compression. That itself will have massive value. It will differentiate roles that require net new thinking from those that require regurgitation.
I'm a paid DAU of ChatGPT. I'm using it regularly as a tutor to help work through a technical online course I'm taking, and it is extremely good at that. My cousin who is in college says basically every student is using it to help study.
There could be an excess of hype, but there is clear significant and immediate value of these tools.
If you use it naively, yes. So can Google, or Wikipedia, or social media.
If you approach it as tool that generates answers that you try to validate yourself, it can help you learn the right things faster.
I approach every answer it gives with hesitation (as it hallucinates often) but it still generates useful content that is incredibly helpful nonetheless.
Here's ChatGPT confidently spewing a ton of very very wrong stuff about the Mesoamerican calendar:
> Is the 1-earthquake inscription on monument 3 at San Jose Magote is the oldest known instance of a Mesoamerican calendar date?
> Yes, the 1-earthquake inscription on Monument 3 at San Jose Magote is considered the oldest known instance of a Mesoamerican calendar date. This monument was discovered in Oaxaca, Mexico, and dates back to the Preclassic period of Mesoamerican civilization, around 1150 BCE. The inscription records a date in the Mesoamerican Long Count calendar, which was a complex system of timekeeping used by various cultures in Mesoamerica. The date is given as 7.16.3.2.13, which corresponds to August 11th, 129 BCE in the Gregorian calendar.
This is wrong. It's actually more like 647 BCE.
> What does 1-earthquake mean?
> "1-earthquake" is a term used in the Mesoamerican Long Count calendar, which was a system of timekeeping used by various cultures in Mesoamerica. The Long Count calendar is based on cycles of time that are counted in base 20, and each cycle has a specific name and duration. The term "1-earthquake" refers to the beginning of a new cycle in the Long Count calendar, specifically the start of the 13th baktun, which is equivalent to 144,000 days or approximately 394 years. The Long Count calendar was used by Mesoamerican societies to track historical events, astronomical observations, and religious ceremonies, and it was an important part of their cultural and social identity.
This is completely wrong. 1-Earhquake is a combination of two shorter cycles. It has nothing to do with beginning of a baktun.
> What is the previous 1-earthquake to 7.16.3.2.13?
> The previous occurrence of 1-earthquake in the Mesoamerican Long Count calendar before the date 7.16.3.2.13 (August 11th, 129 BCE) would have been 12.19.19.17.19. This corresponds to August 13th, 3114 BCE in the Gregorian calendar, which is the date that marks the beginning of the current cycle of the Long Count calendar, known as the 13th baktun. It's worth noting that the Long Count calendar was designed to be a continuous and cyclical system, so there is technically no "start" or "end" to the calendar. Instead, each cycle represents a new period of time, and the 1-earthquake date represents the beginning of a new cycle within that larger system.
This doesn't even make sense given chatGPT's own internal reasoning. A baktun is 144,000 days or around 394 years. It's clearly just regurgitating training data and getting it all jumbled up.
I tried the same thing with GPT-4 set to Temperature 0
===
System Prompt: You are an assistant who specializes in the Mesoamerican calendar.
User: Is the 1-earthquake inscription on monument 3 at San Jose Magote is the oldest known instance of a Mesoamerican calendar date?
Assistant: Yes, the 1-Earthquake inscription on Monument 3 at San José Mogote is considered the oldest known instance of a Mesoamerican calendar date. This inscription dates back to 600 BCE and is associated with the Zapotec civilization. The monument itself is a carved stone slab that displays a combination of the Mesoamerican calendar's 260-day ritual cycle and the 365-day solar cycle, which together form the 52-year Calendar Round.
User: What does 1-earthquake mean?
Assistant: In the Mesoamerican calendar, 1-Earthquake refers to a specific day within the 260-day ritual cycle known as the Tzolk'in. The Tzolk'in consists of 20 day signs and 13 numbers that are combined to create unique day names. In this case, "1" is the number and "Earthquake" (also known as Caban in Mayan or Ollin in Nahuatl) is the day sign.
1-Earthquake (1-Caban or 1-Ollin) represents the first day of the Earthquake/Caban/Ollin day sign within the Tzolk'in cycle. Each day sign has a specific meaning and symbolism, and the Earthquake/Caban/Ollin day sign is associated with movement, change, and the natural forces of the Earth. It is believed to symbolize the dynamic energy of the Earth and the transformative power of natural events.
User: What is the previous 1-earthquake to 7.16.3.2.13?
Assistant: To find the previous 1-Earthquake date before 7.16.3.2.13 in the Mesoamerican Long Count calendar, we need to calculate the number of days between the two 1-Earthquake dates.
The Tzolk'in calendar has a 260-day cycle, and the Earthquake day sign repeats every 260 days. The Long Count calendar date 7.16.3.2.13 corresponds to a 1-Earthquake day in the Tzolk'in calendar. To find the previous 1-Earthquake, we need to subtract 260 days from the given date.
7.16.3.2.13 in the Long Count calendar is equivalent to 1,244,813 days from the calendar's starting point (0.0.0.0.0). Subtracting 260 days gives us 1,244,553 days. Converting this back to the Long Count format, we get:
1,244,553 days = 7.16.2.4.13
So, the previous 1-Earthquake date before 7.16.3.2.13 is 7.16.2.4.13 in the Mesoamerican Long Count calendar.
===
I studied history in undergrad and still keep up but I know nothing about Mesoamerican timekeeping so I don't know how accurate this is, but it seems much more internally consistent than ChatGPT (which is probably GPT-3.5-turbo with whatever temperature settings they use?) LLMs are bound to be bad when you get to such specialized knowledge which its training sets have little of. It was like when I went to grad school I stopped being able to Google for theories, formulae, and lemmas in my classes because most of the knowledge I was learning was only found in papers. Once you're in a specialized field of study, no model can help. But not many people are working in those fields, and those folks should understand that their knowledge resides only with them.
I don't think this is a good example to show how people learn incorrect things from LLMs. LLMs come with the same caveat as Google or Wikipedia in that, the rarer/more specialized the knowledge, the more original research the person needs to do to corroborate their answers.
Without looking up the actual terminology and cycle times for the two shorter calendars (which I don't remember anymore either), I think this is correct.
> And I don't think VR is going away. If it wasn't dead in the water in the 90s, then it's not going to die because the Metaverse failed. But its applicability is currently limited to a few niche applications like video games and possibly CAD type software.
VR will go the way of 3D Printing. A surgeon can walk into one of the largest medical device company's in the world, talk about a new idea for a broken bone transplant and within 24 hours can have a 3D prototype printed out. Great for innovation of broken bones, but it isn't the ubiquity we experienced with something like mobile phones, email, or social media. Meta thinks thats what VR is going to be.
I know it's off-topic, but this simply baffles me about 3D printing. I have a 3D printer and I plan on buying more, but when you look at the most downloaded models on a huge website like printables.com, the number 1 has a bit more than 200K downloads, and the second drops all the way down to only 83K. Only 83,000 people downloaded the 2nd most downloaded model :|
Every time I look at the numbers I realize how niche of a hobby it is, despite being easier and easier (and cheaper and cheaper) to get into and has pretty much endless applications.
The reason for that is that 3D printing's strength is one-off designs. Any popular design would get mass-produced cheaper and better, and would then lose popularity on those sites.
I do a lot of 3D printing -- but outside of when I first started and it was a shiny new toy, I almost never download models to print.
Being able to make my own custom parts and such, though, has been an incredible superpower, and my printers have paid for themselves many times over that way.
It's a niche hobby for sure, but I think a slightly better metric to look at is the number of 3D printers sold. This seems to be about 2 million units per year.
I think a lot of folks looked at 3D printers and thought "Star Trek Replicator". Those folks were likely disappointed. They might get there eventually, but 3D printers aren't there yet.
OTOH, if you're working on hardware and prototyping stuff, 3D printers are an amazing tool. It's like CAD-CAM software: not everyone needs it, but if you do, YOU NEED IT.
I have no stakes in VR, as I don't want to spend money to be seasick, but I think VR is the future for a lot of content. Make it less heavy, fix the seasickness problems, render people realistically, and I could talk to my parents in VR. Or take a walk with an international friend. This sounds SciFi, but would really sell well.
> in large part, they're all impressive technologies in search of problems to solve.
I'm no AI fanboy, but let's be fair: machine learning has been solving problems for decades now. From OCR, to translation, to facial recognition, etc. While GPT4 or DALL-e may be "toys," large models (be they language, vision, or otherwise) definitely have a future in business automation, data collation, military applications, etc.
I feel like this is some of where my own cynicism comes from: the machine learning that has been solving problems for decades now were almost all predicted and prototyped in the 60/70s "AI boom". The generative models were all "toys" then, too and none of the 60/70s "predictions" of when/where/how they might become more than "toys" ever really came to pass and sounded so much like people on HN are saying today.
We're certainly doing more of (almost) everything explored/predicted by "the ancients", we're doing it all much, much faster with much more massive data sets of input and output. For me, though, there isn't a sense that we are doing anything substantially new beyond Moore's Law meets mega-scale GIGO. There's something of a pervasive feel to me to this hype cycle like we are just recreating past mistakes of boom and then (inevitable) bust and haven't learned enough from them.
Coming up with a problem statement is only one part of the puzzle. Making the solution is the next one. In Heinlen's "The Roads Must Roll", published in the '40s, there's a scene where the protagonist wakes up and reads the paper on a "newspaper facsimile receiver." We can recognize this today as a smartphone or an ebook reader. But the ebook reader and the smartphone didn't really exist until the mid 2000s, a full 60 years after Heinlein's story. An anime in the early '90s called Serial Experiments Lain predicted a lot of the effects of the internet on socialization. The events predicted only actually happened 20 years later or so.
Humans have been predicting things that we invent for a really, really long time. That's only the first part. I read "The Roads Must Roll" in the late '90s before ebook readers and smartphones became available and it motivated me to try and recreate that experience myself. I played around with ebooks on a Palm Pilot I found in the trash because of that.
The phrase "newspaper facsimile receiver" is telling and its own reminder that even sci-fi rarely predicts things from whole cloth and instead extrapolates from the world already around it. There were fax machines in the 1940s. It would also be a few decades before fax machines were common enough to be everywhere people wanted to (pretend to do) business, but making guesses that they might get lighter, more wireless, more common in the home if they found the right killer app (easier newspaper delivery, perhaps) isn't a tough prediction. If anything it failed to extrapolate too far towards what our reality eventually pieced together with smartphones/ebook readers was that they are much more general, multi-purpose devices. The idea of having a standalone ereader dedicated only to the daily newspaper is a quaint, fun DIY hack project you see on HN sometimes, but not the norm of how we use smartphones or ereaders today nor how you'd expect to find one commercially sold.
The human tendency to prediction is still grounded in the human perspective and the point of view of its time. Heinlein in the 1940s wasn't perfectly predicting the smartphone or ereader, Heinlein was predicting a better fax machine. It certainly can be used by someone in the 1990s for motivation towards better smartphones/ereaders, but that's already from a shifted perspective. Meanwhile there certainly were sci-fi writers in the 1990s extrapolating from they saw and predicting the smartphone/ereader, it seemed far more inevitable then.
My concerns are not that there are unfulfilled predictions from the 1960s nor that 1960s predictions aren't useful to modern ears (I suggested the opposite that we probably aren't listening enough to them) but that the "point of view" seems so much the same as from the 1960s. For the same types of generative models different newer people are still generally predicting what sounds like the same old types of predictions and it feels a lot more like we are stuck at "the 1960's idea of a better fax machine". Discounting AGI hyper-speculation, we don't seem to have a better perspective today about what's beyond "better 1960s fax machines" and that does leave behind some sense that maybe that's because there isn't anything beyond there to predict. It is easy to cynically wonder if we don't have good ideas or new predictions because we don't actually have any concept for good uses for these generative models beyond "fax machine" (or even more cynically and pessimistically "toy", in these specific examples). That doesn't say anything about whether or not we are able to make solutions for existing predictions, I don't know enough about current trends to have an opinion on that. But it does still suggest that if the last time people were making these sorts of predictions and they failed, the historic precedent is failure and if you are concerned about the glass being only half-full you should plan for that disappointment (and consequent industry-wide job shuffle to follow) even if you really want to expect things will be better this time.
The quantity has certainly changed. It took researchers months to build an "AI generated novel" way back in the day and some form or relative of ChatGPT spits out nearly that every minute now.
I still haven't felt impressed that the quality has truly changed, yet. LLMs seems more "fluent" in the language than ever before, but it's still hallucinating nearly as much and now the fluency just helps make people more often see "meaning" or "anthropic action" (lies, defamation) where the hallucinations are. The underlying structures of LLMs are still complicated casinos that invoke the Gambler's Fallacy much more than any signs of true "learning". We've put millions of monkeys in front of billions and trillions of slot machines and told them to produce Shakespeare and many of them believe they are doing just that. (Not just metaphorically, by monkeys I mean as much humans susceptible to casino payout mechanics and excitedly spinning slot machines.)
Again, yes, I'm a terrible cynic right now, and I hate to be so down on the technology, but I'm still waiting for something to be excited about that isn't just casinos masquerading as "learning". But people love casinos, they deliver addictive fun. I'm not going to stop people from being excited about all these casinos. I just think that professionally as a software developer, if I wanted to be a bad faith casino manager I'd rather just get into mobile games and gacha/loot-box mechanics. That's more fun, more profitable, and maybe, weirdly, more currently ethical than current "generative AI" hype.
The emphasis on "hallucinations" is misplaced from this perspective, IMO. Thing is, when models do hallucinate, they still reason about what they hallucinated. Larger ones (e.g. GPT-4) can even spot their own hallucinations. That is nothing like what we had in the 60s, or even 10 years ago.
I dislike the term "hallucinations" because I feel it also anthropomorphizes the process too much. Unfortunately, "random garbage output" is too many words, but that's closer to what I meant everywhere I used that word.
> Larger ones (e.g. GPT-4) can even spot their own hallucinations.
I've not yet been convinced that this is actually what is happening from the examples I've seen. It all looks to me like more "random garbage output" that "feels correct" but isn't provably correct. Most examples I've seen so far look too much like "Stochastic Crow Mode" [1]. It is prompts and questions that are doing much more work on the humans reading them (and our interests in anthropomorphizing them or mythologizing them) than the LLMs answering them.
There’s absolutely been value delivered, but at every turn it’s been vastly less than what was promised. I would be very surprised if generative AI doesn’t turn out to be the same: legitimately and seriously useful in certain use cases, but not as revolutionary as it’s being sold. I’m excited to see what comes of all this, but the hype is at an absolute fever pitch and I’m yet to see much past niche use cases and help along the periphery for more general tasks.
I mean even crypto has some actual, meaningful use cases, it’s just not replacing all currencies and fundamentally reshaping financial systems like a lot of folks thought it would.
While it's early days yet AI is proving itself much more readily. If you're in the right networks you've heard that several companies who've rolled out AI features are on track to generate >100MM ARR charging for them.
One feature I'm quite confident in: translation services for i18n in websites using GPT-4 + a much smaller number of human translators to check the work of low confidence translations and high value surfaces. I can confirm the end result for French is better than existing human translation services and much cheaper.
Certainly businesses will need to walk back some AI features but it really seems like there's business value now, let alone in 2 years when publicly available LLMs are even better.
> Generative AI is like electricity, only I don't think quite as useful. The point is that, on its own, it has no value what-so-ever. The value lies in what it is used for.
I don't really understand this description - electricity is one of the most useful things in the history of civilization. I think the latter half of what you're saying is true, but it's true of everything. There's nothing inherently useful about my car, except that it gets me places. There's nothing inherently useful about my house, except that it shelters me from the elements.
Generative AI will be useful for creating lots of things (probably primarily code in its various forms). I've used it to write a few Python scripts over the course of the last week that simply wouldn't have been possible for me to do (without a few weeks of teaching myself Python at least - I'm a somewhat-code-literate PM but very much not a programmer). Those have solved real problems for me and added real value to my life.
The comment you're replying to is trying to say that a house, just by existing, solves the shelter problem. Having a functioning car means you can just get in it and go somewhere. But just having electricity in and of itself does not solve any problem; you have to use it power something else (lights, TV, toaster), which is the thing that solves the problem, not the electricity.
> Personally I predict that generative AI is going to be the next Metaverse and crypto.
Generative AI has potential to immediately increase productivity, and thus revenue. The only real way to make money (in the short term at-least) with crypto and the metaverse was to convince other people the digital assets created were rare, valuable and worth paying for.
I heard a great interview response from a YC-related person recently. Might have been SamA:
Nobody you know (roughly) uses VR many times a week/day, not in any extended fashion. Everyone might have them but they're in a drawer somewhere. Compare that to LLM's, which roughly everyone is or should be using. There are very few knowledge-economy jobs where an LLM can't be useful, within hours or days or definitely weeks with a bit of practice. And it'll get better every year. It's here to stay.
I’m starting to agree with this perspective. My opinion on generative AI is shifting from apocalyptic world breaking tech to something more like Siri 2.0.
It’ll be neat for sure, but I think the plateau of useful applications will arrive soon and it won’t be as game-changing as it initially seemed.
I know it sounds stupid, but generative AI has an incredible amount of potential for videogames, making those way more alive.
It might not make millions directly, but it could unleash some very successful videogames, without decreasing accessibility (like vr) or a weird value proposition (crypto)
I wouldn't quite go that far, but the longer I am building these models into systems, I think the good use case for LLMs/Generative AI can be categorized into a few types of systems.
1. Data collection - Obvious, creating a voice/text interface into an existing system where the problem and requirements are well known. Eg, booking a restaurant. It needs a time, place, people. Collecting that from voice/text can be convenient in many situations. Same with different types of models collecting data from video/images/etc.
2. Providing options - When the desired output is unknown, but a human can describe the problem. Eg, coding, art, many "I need an X that can Y for problem Z". ChatGPT does a great job of this and I think most of the value of generative AI is here currently.
Most of the hype is around how far can we take the capabilities of solving this 2nd category to produce the third.
3. Agents - There are examples of solutions showing this potential but the 'killer app' I don't think has been demonstrated, at least well enough. AutoGPT, BabyAGI, etc are interesting, but in my experience don't yet perform nearly well enough. They fail far too often for any trust to be created. This doesn't mean GPT4 native plugins won't get there, they could and that will create a large amount of value in this category (I don't have access to Plugins). This is also where a lot of "selling the dream" is happening. It seems plausible we will get there, but still not clear how these will be accepted and used in the real world, by average users.
One big area of value IMO for Agents is accessibility. People with physical disabilities, but still have the ability to speak I think will provide massive quality of life improvements through being able to interact more easily with more systems.
Very interesting times, the speed of change has seemed amazing, and that for me is the part that creates the most unknown, and is hard to ignore the hype when plotting the rate of improvement and the possibility of Agents becoming an accepted tool in wider society.
The value provided by Crypto/VR is way more limited, and the accessibility of the tech ranges from bad to worse. VR has a lot of utility, but due to the headset requirement, it is disconnected from a lot of the real world. Lots use cases for specific problems, but less widely accessible as generative AI by a long way.
Crypto IMO should be ignored, at best it assists with the financialization of everything which doesn't provide value to a wide portion of society, it provides a means of value extraction.
People seem to misunderstand why the metaverse was pushed so hard. Meta isn't stupid and was doing it for a good reason.
It all comes back to how Meta makes its money - data collection.
Facebook is in a really tricky position right now. They don't control the hardware or OS that it runs on, or the app stores. That means that at any time, Apple or Google can screw them over and deny Facebook from collecting data.
However, what if they had their own hardware (Oculus) running their own OS? Then, they could collect as much data as they wanted without any interference from Google or Apple. That means significantly more profit! There's no way in hell they're going to break into the mobile phone market, so VR was their best option.
That's why they pushed VR so hard. They need it to work because otherwise they have no control over their main source of income, and the squeeze on them is getting tighter ever day.
The squeeze is getting tighter because mass data collection of the world population is perhaps a very questionable and ethically wrong business model for a private company and instead of developing the "Metaverse" which would make it even easier maybe Facebook should have looked at opportunities to turn their users into paying customers by providing valuable products and features that are worth paying for. The way you describe it is as if they have their hands tied together and because ad revenue was their initial model to success it means they cannot ever have any other profit model anymore, but I think that is wrong and that's where they've made a mistake.
It certainly does make you wonder which Meta execs believed that all of Facebook's ethical, legal, and political problems somehow "vanish" just because they've added an extra dimension and are trying to do "Facebook, Now in 3D". It feels like playground naivety by children that there's that much difference in real world consequences between scrolling Facebook on a 2D plane and scrolling it in 3D instead. "We'll just escape our pursuers and hard problems by jumping into 3D! Woo!" said the kids imagining the park slide was a rocket ship. It's such a bizarre response to "our current business model is breaking down and we are having a hard time with regulators, politicians, and trust from the general public".
It still doesn't change the fact that it was a dumb decision. Facebook would have been much better off simply accepting that they couldn't control the hardware or OS or app stores and continue to do the best they could within those constraints.
Instead they just threw away a ton of money that could have gone to shareholders and employees instead.
What business would have accepted that their primary revenue stream is 100% in the control of other companies, and is shrinking? Of course they can't accept that.
If things continue as they do, the whole company will collapse. Better to throw whatever they have at a solution than to just lie down and die.
Companies accept that all the time. It's far more profitable to slash investment and turn something into a cash cow over the next 10-15 years than bet the farm and lose. It's actually in shareholders' interest -- which is why so many shareholders have been upset about the VR pivot.
Right, cutting R&D spend and upping dividends or buybacks is a totally normal thing that companies do all the time. It's just not nearly as sexy as changing the world or whatever Zuck says he's doing.
He was only able to pursue his metaverse vision because he has shareholder control, and given the change in stock price it looks like increasing numbers of investors are no longer interested in a company he has total control over.
You make it sound like the metaverse was the only possible thing they could try, which couldn't be further from the truth. There are hundreds of areas where those billions could have been invested with a shot of developing something real. LLMs for instance! Or they might have discovered whatever the next big hyped technology will be. Burning it on their metaverse was a laughable idea at the time and has failed even faster than many expected.
Their real problem is that their entire business model is in danger. What they should be throwing their money at is changing their business model, not trying to invent a new field to apply it in.
> There's no way in hell they're going to break into the mobile phone market, so VR was their best option.
They even tried to break into the mobile phone market at one point back in 2013. Then apple made it's privacy changes and now Google has said they will do something similar on their platform. I think you're right that Facebook got desperate to find a platform they can control.
Remember when they tried giving free internet away in India, they are diabolically sleazy, trying to exploit the next billions of humans coming online in exchange for harvesting their data and monetizing it to the highest bidders.
Err... as much I'd like to have a VR headset and use it, I simply can't.
I don't have time to immerse myself in the environment where I don't see the reality that surrounds me (as in, people which share my public transport, cars that stop at the traffic lights next to me, my kids running around me, people I work with, etc.). It's not that I need the reality, but I can't disconnect safely. Facebook is easy. Just reach the pocket, get the phone, a few swipes and you are using it. Be it in the office, around your kids, in the waiting room, ...
I don't see how VR can provide you a FB scale of users.
None of that does a thing to make people actually want to use the product though. Nobody wants to strap a VR set to their head because it would be good for Facebook. I get why they want that to be true, but spending immense amounts of money trying to force it to be true has been a stupid waste.
That maybe a factor but it's also possible the attention economy is peaking. We always knew attention available is fixed.
Google and Apple have reported slight slow down. Smartphone market in the west has saturated and not growing. Ppl have so many other options where they can spend their time online. Its possible everyone is seeing less ad revenue.
This seems like a bit of 20/20 hindsight. At the time, the biggest concern Zuckerberg had was that they didn't own a platform. Apple had the iOS ecosystem, Google had Android, Microsoft had Windows, Amazon had AWS and their logistical moat. Zuckerberg made a bet that the world would move to VR similarly to the way the world moved to PCs in the 80s, which allowed Microsoft to take over a big chunk of the world.
Zuckerberg's fear wasn't unreasonable, he just bet wrong. Apple's privacy changes had a huge impact to Facebook, and the other FAANG without a "moat-defining platform", Netflix, is also in the most precarious position among the big techs.
That said, I agree with most of the other comments. I can see VR evolving a little beyond gaming I guess, but it's actually kind of a nightmare to imagine myself wearing a fucking headset all day. At this point I think Zuckerberg knows he bet wrong and AI is the future, and he's clearly trying to pivot, but it's really hard to move a big company like Meta quickly, and it also means he has to admit he just lit billions and billions on fire.
2nd Life, The Simms, various MMORPGS. We have loads of experience buildings virtual worlds with virtual belongings and conducting meetings virtually. I was part of a WOW guild that had meetings about raids and other small bits of admin stuff in game.
But a company known for being sketchy as heck slaps on 3D goggles and makes it less fun and I’m supposed to want to be in it?
I think you’ll find that a lot of people were skeptical.
I don't disagree that the company is "sketchy as heck", but the fundamental bet was that the main computer interface display device would move from being a monitor (and also perhaps the smartphone display) to being VR. And yes, there were people skeptical about that, but I don't think that idea in and of itself (that is, taking Facebook's nefariousness out of the equation) was that outlandish a couple years ago, despite my personal disdain for the idea.
My point was that this is not 20/20 hindsight. A lot of people thought this was a non-starter from the beginning. So far it's panning out the way skeptics predicted. It would be 20/20 hindsight if they succeeded and we starting post rationalizing it.
Also I think people only think from the "what do I gain?" perspective. There is a comment below that asks "what do you think display technology will be like in 20 years?" I won't argue that 2 high res screens that can show my entire workspace where ever I am would not be awesome. I would try that.
But consider all the things you do while you work:
- Eat and drink
- Stare out the window
- Get up and go to the bathroom
- Just have a stretch, spin in your chair.
And now 2 tiny 4k screens strapped to your head is no longer ergonomic and isn't going to cut it. And a cheap and normal screens looks really good.
> I don't disagree that the company is "sketchy as heck", but the fundamental bet was that the main computer interface display device would move from being a monitor (and also perhaps the smartphone display) to being VR. And yes, there were people skeptical about that, but I don't think that idea in and of itself (that is, taking Facebook's nefariousness out of the equation) was that outlandish a couple years ago, despite my personal disdain for the idea.
Actually, that idea is less outlandish now; in fact, they should double-down on it if they can.
A few years ago ChatGPT and AI as they are now were not even close to allowing people to use something other than screen with (perhaps on-screen, perhaps physical) keyboard.
With the advances we've now seen in AI, it makes VR more likely[1] to be the main interface to the computer, not less likely. Hence, they should double-down on VR and immediately integrate AI, even if it means ditching the bulky headset that users have already rejected.
A ChatGPT-like assistant could be the final puzzle piece that causes users to stop using the monitor/screen/keyboard for interacting with their social network.
Not to say that they'll switch to VR, but it becomes ever more probably, with AI assistance, to ditch the current interaction mechanism for social network users.
[1] Still pretty unlikely, but more likely than before.
> the fundamental bet was that the main computer interface display device would move from being a monitor (and also perhaps the smartphone display) to being VR
That's a terrible bet. Anyone who has ever played a 3D game will immediately understand that a 3D world is a strictly inferior interface for almost all use cases where you are actually trying to get something done, e.g. read and answer an email.
What do you expect monitor technology to look like in 20 years; the same as today just with more pixels? If someone types by touch, what's the difference between a VR monitor and a physical monitor?
> Strapping a screen to your face is not ergonomic. It isn't practical
That argument is only sound for as long as the screen is unwieldy. If you could wear a pair of glasses that magically converted your laptop into a stable, triple-screen workstation, it'd be a no-brainer to assert that it was useful in at least some circumstances -- working on planes, trains, automobiles now becomes more and more possible. If the tech then progressed to the point where you could do that from a phone, and not require a laptop, or even necessarily pulling the phone out of your pocket, then it seemed like a pretty powerful productivity feature _at least_ some of the time, and if executed well enough, it wouldn't shock me to see people giving up their laptops in the same way that many people don't bother having tower PC computers any more.
There's a TV show called the The First, about going to Mars. No on has computers, only voice activated TVs, and glasses that replaced computers. It's the most realistic next step in computer evolution I've ever seen. It's worth the watch just for the "near future" tech. Oddly enough, I could not figure out how we'd do the voice stuff, but it looks easy for a GPT with a little training.
If Apple actually reveals a headset and the ergonomics are on par with what’s put there now, I think that will solidify the idea that this tech isn’t going to be ready for a long while.
> the fundamental bet was that the main computer interface display device would move from being a monitor
That's not really the bet they were making. It was deeper than that.
Facebook discovered that people are willing to use their product to dissociate to an extreme degree. There are some people out there whose entire lives are on FB and Instagram. Take their profiles away, and you would literally erase the livelihood and even identities of some individuals out there. They have no relationships and no skills in the material world. Their entire existence is a profile, and the relationships cultivated in that profile. Just as you and I cease to exist in the material world when we close our eyes and go to bed, these people cease to exist at all when they log off of Facebook and Instagram.
And so Meta, being the consumer-focused company it is, was looking to give their best customers exactly what they want: a way to complete their dissociation in the material world, and to bring even more of their existence into the metaverse, the digital plane of existence for many of their customers. Their pitch for metaverse meetings seems so strange to us on the material plane because in-person meetings are the last thing we'd replicate digitally. But for those who are ready to dissociate into the digital plane, a digital meeting room is the next logical step.
It's like what Agent Smith says about the first version of the Matrix. Yeah, it was perfect, but it wasn't real. So they added pain and suffering to make it real. The FB can offer a great dissociative experience if that's what you're looking for, but if you're really looking to let go of the material plane, you need to bring in all the pain and suffering you're used to into the metaverse. Otherwise the distinct lack of meetings gives away the charade.
The problem for Meta is that the Metaverse is a very expensive proposition, and there are only so many hardcore FB and Instagram addicts at this point willing to dissociate to that degree. The rest of us enjoy our material plane of existence, and aren't addicted to Facebook and Instagram the way their users are.
And there it is, the word "user", which reminds us that FB customers really have a lot in common with drug addicts.
People whose lives are FB and Instagram are following celebrities and getting caught up arguing with strangers over reality TV drama. None of this exists in the Metaverse, there are no Groups or Pages where this type of discussion could take place. That's the biggest issue with Horizon Worlds -- you are expected to go there and talk to strangers.
That is 100% unlike the FB experience, where someone else provides a prompt (post), and you join in the comments.
I'd day the whole VR movement that played out and then died in the 90's was more than a few tries already. And two decades later still nothing society-altering. I guess I don't think the iPhone comparison is an accurate one.
I had a Sony Ericsson p900 a few years before the iPhone, it had a small keyboard you’d usually flip out of the way to get a full screen touch display: https://en.wikipedia.org/wiki/Sony_Ericsson_P900
https://en.wikipedia.org/wiki/LG_Prada for example. It looks pretty much like iPhone — no keyboard, just touchscreen. But it did not really "spark joy" (I had one), so it wasn't a big success unlike iPhone.
Thanks for posting that, I didn't remember that one. That's one of the only ones I would consider a "true" predecessor to the iPhone - as you say, capacitive touchscreen and no keyboard. Other ones that have a touchscreen but also a number keypad or something like a slideout/flip keyboard are just not ones I would consider in the same category.
I dunno about you, but I and basically everyone in my circles at the time agreed that it was most likely a terrible idea.
Until and unless there's a truly convenient piece of hardware to get one into a virtual space—I'm talking weight and bulk comparable to prescription eyeglasses, no wires going beyond your body (ie, maybe a pack at the belt/pocket/something like that), and some form of extremely intuitive UI—you're not going to get people interested in regular interactions in a VR/AR space.
Frankly, even once we do have something like that, I think it unlikely that many people would choose to do things like meetings in a virtual space over something simpler like Zoom, even if they did already own the hardware.
And none of these views have changed over the past few years.
No; I think Zuck has been far too isolated and out of touch with how regular people operate for too long, and when faced with, as you say, the fact that Facebook was only running on other people's platforms—and it became clear that no one was interested in making Facebook their platform, like by buying a Facebook phone—he convinced himself that this was The Next Big Thing based on sheer desperation.
Is there not a single product expert leading any company in big tech anymore? What’s going on.
Growing up I was used to there being more useful and fun tech gadgets than I could ever afford. Now it’s like unless they own your entire online presence they don’t want your money. Give me that dumb iPod v1.0 which gets sand in the wheel and lasts an hour on battery but for VR. The idea was all your music on the go and it met that goal.
For VR it should be hands free/hands minimal portable productivity. Give that shitty resolution and battery life. I would take navigating YouTube, PDFs, email at the lowest res feasible and 2 hour batteries and isn’t gigantic and prevents you from normal activities. Don’t build a multi billion dollar platform.
In general, I think it's very hard for a "product expert" to obtain or hold leadership of a company once it gets large. The "bureaucracy experts" have a huge advantage in that realm.
And that's not inherently a bad thing. Despite his often shrill detractors, Tim Cook, who's definitely a "bureaucracy expert" more than he is a "product expert", has done a darn good job leading Apple since Steve Jobs' untimely death. The thing is, he knows to listen to the product experts, and to put the really good ones in positions of some power within the hierarchy.
The problem comes when your "bureaucracy experts" only value what they understand: Bureaucracy. Numbers. Finances, especially in the short-term sense.
Now, I honestly don't think this is precisely Zuckerberg's problem. From what I've seen, I don't think he's necessarily a "bureaucracy expert" himself—but nor is he a "product expert" in the same sense as someone like Jobs or Ive; he helped to create the original Facebook, but I don't believe he's ever come up with any other products that have seen any real success (though correct me if I'm wrong). He's more of a founder who rode a wave of money to where he is, and bought into the idea that that meant he was somehow smarter than everyone else.
> I would take navigating YouTube, PDFs, email at the lowest res feasible and 2 hour batteries and isn’t gigantic and prevents you from normal activities.
I know, right? The only reason to want a "fun gadget" like that is if you're the kind of person who enjoys gadgets for gadgets' sake. Which is fine - we all have our interests.
But I'm not a Gadget Guy. Why would I want shitty YouTube in VR when I have good YouTube on my phone?
You appear to be trying to imply that because one prominent tech guy (CmdrTaco) pooh-poohed the iPod at its announcement, only for it to become a smash hit, anyone who looks at an announcement and says "I don't think this will do very well" is automatically wrong...? Or something?
There are fairly serious differences between the release of the iPod and the announcement of Facebook's shift to "Meta", and one guy being wrong one time, however famously, does not have any implications for other people being wrong in completely different circumstances, so this feels pointlessly dismissive.
Also, I was right about THAT iPod! 2 years later they got the product right and when people reference this quote, THAT is the product they have in their minds eye.
You can make all the predictions you want. Predictions are forward looking, not backwards. Saying your predictions are obviously correct in hindsight is engaging in survivorship bias.
Easy way to prove this is to ask people what the obvious winners and losers will be in the next 5 years, and then see how they've allocated they're investments to that. If you can predict the market so obviously, you'll be rich.
> AI is the future, and he's clearly trying to pivot
I don't really understand this take. Generative AI is a complement to the metaverse. Biggest problem metaverses face is having good content since it's quite a bit more difficult to create. Using generative AI to fill the metaverse is not a pivot, it's been the plan all along.
That's how I read this. Facebook already had a failed facebook phone venture everyone seems to have forgotten about. Zuckerberg is trying to get to the new world first this time. Except even if VR takes off it would only be a niche compared to mobile so it doesn't really make sense. But AR could potentially and I guess VR might have been seen as a stepping stone to that.
Meta isn't giving up on the metaverse. The effort is not a failure. The plan was always going to take closer to 10 years to realize. They were explicit about it being a long term goal, not a short term one.
They've made some missteps, but it's not even close to being over.
To me and everyone around me the Metaverse was immediately clear to be a massive flop. First of all, before the Metaverse neither me or any of my tech friends did even know that anyone was still investing into VR. When we heard about Facebook pivoting to the Metaverse we all were like "what? why would you invest into a technology which has been widely rejected already?". It's like Facebook investing in 3D TVs, which had a short blip in the market but then died off, because fundamentally nobody cared about 3D TVs. I don't know anyone who is even remotely excited about VR let alone the Metaverse.
This became even more obvious when shortly after Facebook's pivot nobody, I mean like absolutely nobody was searching or reading up on VR news. It's a topic that people just don't care. They don't want VR in their life. People want more REALITY in their life, not less. Especially after COVID.
On the other hand, AI has sparked everyone's imagination. Only a few weeks ago I showed my wife ChatGPT and we used it for some work she had to do in her field (medicine) and she was completely amazed by it. She's got her own account with OpenAI now and uses it for a variety of things already. My wife is the most non tech person ever. This to me is a strong indication that AI has not even scratched on the surface of its potential.
A far less monetized and more user content focused version of "the Metaverse" already exists: VRChat. It's been around since before Covid and it is still around. Granted, yes, it is still mostly a niche hobby for some very dedicated people, not all of whom even use VR, but it exists. I think the people who would have been interested in Meta's product looked at it and thought "But we already have a less crappy version of this that's not tied to a questionable company." Especially since Meta's handling of Oculus has been far from great (i.e. requiring a Facebook/Meta account just to use any headset, as opposed to the separate account like before).
But as I said, it's still fairly niche and mostly serves as an escape for people. I think slapping the whole "buy in-world items with crypto" thing on top of that just made the target group even smaller than before. It just felt like jumping onto any tech buzz words to broaden appeal, when it actually caused the opposite. For all the data they're supposed to have, that was poor decision making imo.
The data I'm looking at makes the Facebook decision a little more sensical.
Yes there was a Big Spike in VR interest around Oculus, and most of the people who bought one have it sitting in a corner collecting dust...
But a significant subset of people continued to use it, and their usage is steadily growing. There are huge numbers of people willing to pay $500 -$2k, on each new device that comes out, just to "see if its ready".
There are tons of people who work from home on a couple monitors, who WANT to have a VR work setup that gives them screens the size of walls. Obviously the comfort, battery, and visual performance is not there yet, but most people have a feeling that would could just be a generation or two away from it.
I would guess that more than 50% of hacker news readers over 40 years old had an MP3 player BEFORE the iPod. They were all garbage and completely replaced when the iPod came out, but for the 2-3 years before the iPod, all the early adopters new something like that was coming and they were hungry for it.
All the Oculus hype was based on the promise of a $300 headset. The amount of people that are willing to pay $500-$2k is rather tiny (<< 1 million), especially with a near complete lack of AAA game content.
Meanwhile the VR-as-monitor replacement fails due to the low resolution. VR headsets by design waste a ton of resolution to get a larger FOV. That's good for immersion and gaming, but renders desktop use impossible. It's possible to build headsets with a small FOV and high resolution, such as what Nreal is doing, but that's not something Meta is focusing on. Worse yet, they kind of pretended that the QuestPro was ready for that use case, but it's not even close.
I do agree that there is potential in VR, but Meta has been focusing on all the wrong things. They were far more concerned with gaining total control over the space then they are were about making VR actually worth having. Nobody is looking at Horizon World and goes "I wanna have that", it not only looks terrible compared to stuff we have outside of VR, it even looks terrible compared to all the non-Meta stuff we have in VR.
> who WANT to have a VR work setup that gives them screens the size of walls.
I saw that in the tech demo last year and would agree with that sentiment. Yet I wouldn't want to wear headset for a full day to achieve that.
No, they weren't. There were excellent ones. What they lacked was enough storage to carry your entire music library with you -- that was the problem the iPod addressed.
But in terms of playing music, the iPod was not exceptional.
VR is kind of a gimmick, but AR will, 100%, be the next frontier of human-computer interaction. It sparks the imagination in an extremely tangible way.
But IMO, attitudes like "it sparks the imagination" is why VR failed.
FB succeeded because it was in the right place at the right time. Sure, it positioned itself cleverly, but the moment in history was ripe for a social media company.
Things don't just succeed because they spark the imagination or because you work really hard at them: they succeed because all the factors beyond your control are aligned, too.
Well Apple are going pretty heavy into VR/AR with there product likely launching this year, so it's not just Meta that got caught up in that wave, a few years ago that was where a lot of people thought the future was, so that is where both Facebook and Apple seemed to put a lot of investment.
It's not done yet. AI is the current buzz because we are starting to see some great products and uses for it, we have yet to see that with VR/AR but that doesn't mean it isn't possible. It's still early, I am not a fan of the 'metaverse' idea, but VR/AR still has a lot left to give.
I think the discussion around VR/AR sometimes misses the forest for the trees. Yeah, existing products are mostly sucky/very niche, and the existing direction for the entire sub-industry seems very unlikely to break into the mainstream.
But that's not to say it's not possible for a mainstream-successful iteration of the idea to exist. My personal feeling is that there is a viable path to mainstream success, though it's far from guaranteed that a player succeeds in taking said path.
The real question IMO isn't "can VR/AR be made mainstream successful" (this is largely unknowable until someone does it), the question is "can FB be the company that makes VR/AR mainstream successful".
And IMO the answer has always been no. If there is viability in the entire subfield I think Meta is poorly positioned to be the tip of the spear.
Its fundamental business model works against the interests of good products in this field (stuff every virtual surface full of ads! Inescapable eyeball tracking for MAXIMUM CONVERSION ATTRIBUTION!!!1one) - one can make a (good) argument about the implications of Meta's VR play with the interests of humanity, but I don't think we even need to get that deep. Their business model fundamentally is at odds with creating compelling products in this arena. So much of their product strategy seems to be stuck in the hole of "what is good for Meta" instead of "what is good for users".
And then there's seemingly the perennial issue of FB not being able to ooze any kind of desirability or cultural cachet, which is deeply necessary for any of this to reach the mainstream in a big way. Everything it touches, even before the VR/AR pivot, is like an even more corporate and dead-eyed version of EPCOT.
I agree, if Meta had focused on building an open platform and ecosystem that people could freely experiment with, they might have gotten somewhere. It certainly wouldn't have been as dead on arrival. But of course, that's not the kind of company Meta is. They want everyone to pile back onto facebook where they can control and monetize every aspect, except a cartoonish 3D version of it.
Agreed; i would claim: If video chats/conferencing are XX% (95%) of a real-life conversation and a "metaverse" product can bring that up to XX%+N% (99%) then people will pay for it. If the cost is right it'll become mainstream. If the cost is too high it'll probably be a business or niche tool. Once that tech exists other products will become possible too.
I don't personally see what's controversial with that claim and bet. Separately one can argue if the current tech is anywhere near good enough to achieve the N% gains but the common thread of VR/AR/metaverse as being a useless product forever is a textbook example of missing the forest through the trees.
I already spend 8+ hours a day in front of a large screen. If the tech is good enough that I can use it 8 hours without discomfort/side effects and get huge virtual screens - me and millions of professionals are sold.
And when I have it for work the play becomes more realistic.
So for me that's the killer feature of VR - portable monitor replacement - you can take it anywhere, pop it on and you're instantly in your virtual office. This would be worth 1000s $ if it "just worked" like Apple products do.
Apple and Microsoft are the only tech players I could see pulling this off because of the OS integration required. And Microsoft failed with Hololens.
Very true. I think many people don't realize how uncomfortable phone screens are because they are just used to it and love the portability.
The day I tried HoloLens I quickly saw there is much more potential in that tech than many thing.
A 360deg screen that you can take anywhere with you and that can give you a true field of depth / 3d view. When the devices will perform well enough and be portable enough, this will become huge.
But our industry is very fad-driven, and it's common that when one big company starts pouring money into a thing, others do as well. It's usually FOMO rather than some sort of well-considered thing.
There are some people who legitimately love VR games like VRChat. I am not one of them, but I have talked to a few. At the time that Facebook made it's initial investments into that space starting in 2014 there was at least some possibility that those people were the early adopters of a technology that would disrupt the social media and entertainment industries. Of course that turned out to be wrong (or at least too early) but at the time it wasn't completely implausible. Large enterprises sometimes have to invest in long shots as a risk mitigation strategy.
> People want more REALITY in their life, not less.
Agree with most of what you said. But my take is, people would LOVE virtual reality if it were done well enough. We just don't seem to have the technical capability to pull it off well enough yet. Uncanny valley and all that.
Yes exactly. ChatGPT is exciting because it actually works, not because it’s the first AI chat program. If Microsoft had pivoted to it even 5 years ago they’d be a laughingstock like Meta.
Not for me it doesn’t. I use ChatGPT all the time in my work and it saves me a lot of time. With a couple of exceptions I haven’t found much compelling in VR and can’t stand to do it more than 60 minutes at a stretch.
It have to do with VR because VR is attempting to replicate reality. If you do that almost, but not quite, perfectly then you're in the uncanny valley. It doesn't have to be about portraying people.
Current VR can't even approach realism -- which keeps it out of the uncanny valley.
However, if the technology improves to the point where the graphics approach realistic, the uncanny valley will become a real problem.
I feel exactly the same. I have friends that have been trying to explain to me what the huge advantages of crypto and NFTs are for almost a decade and it's still very hazy to me. Nobody explained ChatGPT to me. I saw prompt and started typing some questions about a python library and it was immediately obvious to me that this would be super useful to me.
Sometimes I think you need to use a new tech for a while before the benefits become obvious. I worked for Apple retail back when the iPhone was first released. I remember even after getting our hands on it release day that it was neat and exciting, but also something I'd completely written off at $800 because I just didn't see enough use for what it offered compared to a dumb phone and an iPod.
Part of the sales experience at the time was they gave all of us one to carry around during our shift on the sales floor and encouraged us to show it off and use it to look up things we'd normally have gone to one of the demo computers to look up. About 2 months later, I'm taking a road trip with a destination plugged into my Garmin GPS (remember those?). I'm in the final stretches of getting where I need to go when the GPS says "you've arrived" while I'm driving down a road with nothing on either side of me. I go for another half mile or so just assuming it was off by a few hundred feet and I'd find an entrance but no such luck. Turn around, punch in the destination to the GPS again and try from the other direction, same deal. "You've arrived" in the middle of nowhere. Tried a couple more times and then pulled off to the side of the road and reached for the iPhone in my pocket to pull up some information / a map quest search, and then remembered that I don't have an iPhone in my pocket because I don't own an iPhone and just carry one on shift at work. That experience convinced me that there was value in this whole "smart phone" thing and that I would eventually be getting one.
Which isn't to say that crypto or NFTs are like iPhones, but more that I think you can't necessarily understand how useful a given piece of tech is just by someone else explaining it to you. Some things you just have to use.
I am not convinced. The first time I used an iphone I was blown away by it. Definitely a hefty price tag, but the whole user interface with swiping, pinching etc. was really eye opening. Android of course quickly caught up, but it was a completely new experience compared to existing smart phones at the time.
Same thing the first time I used google (my age is showing a bit). It was leaps and bounds better than the alternatives at the time.
With crypto it always feels to me like I am dealing with scams, ponzies or something useless. Solving problems that weren't really problems or creating problems that didn't exist beforehand. I have rarely been so underwhelmed by any technical innovation.
the iPhone 1 survived thanks to Apple's enormous marketing budget, and a 33% price cut from $600 to $400.
Apple has goodwill from its iPod success and iTunes store. FB has nothing. Horizon Worlds is completely different from Facebook/Insta, whereas the iPhone had a new UI but with many familiar elements.
I know Jobs tried to talk up webapps as being the future at the time, but apps were very clearly coming - it was touted as a computer for your pocket, there's no way they weren't going to let people write software for it. And if they didn't, then someone else would make one that could, and completely eat their lunch.
I think different technologies are going to appeal to different audiences and users. I've been pretty blown away by generative AI, both stuff like Stable Diffusion and now, these ultra-powerful LLMs (although I didn't much about it before that) - it's obvious that pairing w/ ChatGPT makes me a better programmer, and it functions as a pretty good research assistant as to boot, however, talking/showing it around to a lot of friends, many of them are dismissive or pretty meh around then and so far, and profess to not have any use for it.
But then again, that may be why there's huge adoption of crypto in countries like Nigeria (32%!) or Vietnam (21%) [1] (obviously, crypto is a lot more useful in your life if you have a weaker central currency or less financial access; their deeper dive into Sub-Saharan Africa adoption of crypto in particular is fascinating [2]).
Likewise, I'm a believer in the eventual adoption of XR, but a big part of my excitement is really my desire for infinite screen space. Still, I can see the argument that everything will be spatial in the future and personally, I see these trends tying together a lot more than not. Maybe they're on different hype curves, but decentralized financial transactions on credibly neutral, near real time networks (w/ smart contracts) seem like a natural fit for agentic AI. And in the VR arena, I'm seeing some incredibly compelling stuff happening with NeRFs and other generative media that is going to make virtual/augmented immersion a lot more compelling (one of the big bottlenecks for VR right now is generating compelling evergreen content and experiences).
I think the tricky part with innovation, is almost everything innovative looks like a bad idea to almost everyone. And as the tech or company progresses, more people look at it and think it's a good idea. If it were really obviously a good idea, there's no innovation, there would already be others doing it.
And this is in contrast to what YC likes to call tarpit ideas, because there are lots of ideas that look good but everyone who tries to tackle them fails for whatever reason.
So we can say metaverse was a bad bet for Facebook, but that's sort of looking in hindsight at the struggles that tech has and the unknown market. And it appears to be a big bet and lost.
But comparing to current state of AI, is sort of comparing to a different stage, where there is the beginning of an early majority seeing the progress and now seeing the excitement. But go back a couple of years, and more of us would be naysayers, talking about how bad the tech is, or various failure modes.
> I think the tricky part with innovation, is almost everything innovative looks like a bad idea to almost everyone.
No. No. The steam engine, modern refrigeration and open heart surgery all probably had some naysayers but I don't think they looked like bad ideas to almost everyone. A lot of what qualifies as innovative from your tech community really just might be crap.
From the beginning the complaint with crypto and blockchain is that it didn't fix any problems other than maybe assisting as a tool in laundering/illegal transactions, and it wastes energy to boot. I don't see how the naysayers were wrong.
The metaverse idea didn't even get to the point of hyping a purpose. Nobody even bothered to explain what useful human need or want it fulfilled (beyond what has already been fulfilled for years in gaming).
> But comparing to current state of AI, is sort of comparing to a different stage, where there is the beginning of an early majority
Early majority? That is a bold affirmation.
I think these large language models are pretty neat. I also lived through the first AI winters. I would say the hype at this moment isn't even as great as it was then (especially in the 80s). It is a bit tough to explain for those that weren't there - but numerous knowledgable and intelligent people were convinced that the AI singularity was just moments away.
> but I don't think they looked like bad ideas to almost everyone. A lot of what qualifies as innovative from your tech community really just might be crap.
Cool. How about brain surgery? Clarification: how about brain lobotomies?
Without the benefit of hindsight, can you explain how open heart surgery is "clearly" good and innovative while the later is harmful. I mean, everyone knows it's a good idea: it even won a Nobel Prize.
The fact is, everyone only obviously knows an idea was crap or obvious in hindsight.
> Cool. How about brain surgery? Clarification: how about brain lobotomies?
Many of the indications for open heart surgery are no longer valid or standard of care today, replaced with either vascular access or medical management... and brain surgery is a more fair comparison then a specific procedure (open heart surgery is not a single procedure either), for which plenty of lives have been improved.
Which by the way, lobotomies (temporal lobectomies, but a rose by any other name) are still an accepted treatment for epilepsy. Sidebar: Frontal lobotomies were not without controversy over their well known effects even when they were contemporary.
Neither is "clearly" good nor harmful. I never sought to engage in this black and white thinking.
And to my original point it is completely obvious to me and many in my field why it is beneficial that we should be researching alternative treatments to epilepsy other than lobectomies (which doesn't feel like the final word on epilepsy, as helpful as they have been for some), and this goes for a whole host of neurological and psychiatric treatments in general. Unfortunately the technology hasn't gotten us there yet - that doesn't mean it isn't obvious to me why work in these areas would be net beneficial. And some of those ideas are not going to pan out in the long run, no shit.
This is the limitations of technological progress, not some issue of vision.
I don't think the metaverse is comparable as no one has ever explained to me how, let alone Meta, how it is not Second Life with more bells and whistles.
> The fact is, everyone only obviously knows an idea was crap or obvious in hindsight.
Well I have plenty of hindsight for all that shit.
I'm not sure I can get on board with the sentiment of your first point. Anaesthesia as another example took more than a century to get right, had some huge failures and wasn't taken seriously. It surely earns the label of innovative but just happened on a much larger timescale.
As I recall, refrigeration also went through multiple disruption cycles, or at least how someone got ice. As I recall but could be mistaken, almost no company survived from one cycle to the next.
The first cycle was ice huts, basically insulated bunkers where you could get ice through the summer that was collected in winter. This industry got totally replaced by the first of commercial refrigeration, that could generate and store ice from water. Which got disrupted and replaced against, with home refrigeration, someone can make ice at home, or get ice from a bigger version at a store.
The point I was trying to make, perhaps badly worded, was that these disruptions weren't obvious ideas by those in the industry. Otherwise they would have embraced the change technology allowed and rode into the new markets.
We're looking in hindsight, and going it's obvious it's a good idea, because we all have a fridge and can make ice at home. But at the time, those who owned the entire industry, couldn't see it.
Can you tell me why anybody would ever want to take anaesthesia?
Ok, now, can you explain me why anybody would ever want to go in the Metaverse? (In a way that doesn't sound like an indie game or some chatroom created by a small team?)
Saying “no” multiple times as if a statement is so absurdly wrong is such a meme at this point and another interesting difference between face to face and online interactions. I can’t imagine having a discussion with friends and someone throwing a bunch of “no”s out.
Crypto can facilitate truly decentralized money, and although that hasn't truly happened yet, I would argue that is a feature. Does society want that and would government allow it? I don't know
I haven't yet heard a solid general case for why decentralized currency would be an improvement over what we have now. It strikes me as a solution in search of a problem.
> almost everything innovative looks like a bad idea to almost everyone
I disagree really strongly with this. Innovative things look like impractical long shots that have obvious upsides but that violate conventional wisdom around what is possible. The smartphone is a great example of this: it was obviously innovative, and the idea was obviously great before it actually became reality, but the practical limitations of hardware made it impossible until one day it wasn’t. Same for generative language models. The real innovation for both of these things is that some element constraining a good idea changes and someone notices and can act on it decisively.
Some version of the Metaverse has always been possible in one form or another, but no one acts on it because it doesn’t benefit the users it depends on for success. The fundamental limiting factor is participation incentive, and technology doesn’t change that.
> that's sort of looking in hindsight at the struggles that tech has and the unknown market
There is innovating, trend following and what I’ll term trend completion.
Innovation creates new categories. Crypto was innovative. It looks like a losing bet, but nobody can doubt it was daring. Trend completion doesn’t create new categories, but it delivers on a promise. The iPhone is in this category. A product delivered against the incompleteness preceding it. (And synthesising categories.)
Absent that tangibility or specificity you have trend following. Facebook didn’t create the VR/AR category. It hasn’t delivered a product. It hasn’t even described a uniquely compelling vision. It jumped into a fad because others were doing it and then flailed around helplessly while executives penned PowerPoints.
Even if you accept that anything innovative looks like a bad idea to almost anyone[1] that doesn't mean that anything that looks like a bad idea is per se innovative and just misunderstood. There are things that are just terrible ideas. Lead swimming trunks. Asbestos baby clothes. etc I could come up with thousands of things that the vast majority of people would think are a bad idea because _they are_.
[1] which I totally don't buy. If you think about the early internet as an example - the vast majority of people I knew didn't _understand_ it, and/or didn't _care_ and certainly didn't have any sense of its future, but no one that I knew thought it was a bad idea. If they thought about it all they thought it was irrelevant to them until they absolutely got it and couldn't get on board fast enough.
> almost everything innovative looks like a bad idea to almost everyone
But some ideas are obviously bad within that framework. I could invest millions trying to build a commuter-friendly transportation rocket, but that's obviously not worth trying. Any potential critics would almost certainly be right.
It's too easy / lazy to joke about Meta and their bet on a future AR/VR world.
But what I don't see is people willing to do the same with Apple who has also invested billions in the space and will be showcasing their Reality platform in the next couple of months at WWDC.
Do people really want to bet against the company that has had so many consumer product successes even ones for which there was widespread doubt e.g. Apple Watch, AirPods etc.
And what if it takes off ? There will need to be another platform similar to iPhone/Android and isn't that the type of bet Meta should be making.
I think the Apple headset will be a (relative) disaster. I'm sure it will sell OK, but we're talking Apple TV numbers not iPhone numbers.
What AR/VR needs is a mass market killer app, like Pokémon GO (in its heyday) or World of Warcraft or something. Not another headset. People will put up with all kinds of discomfort/inconvenience/cost if there's something interesting to do. The current crop of Metaverses don't cut it in this regard.
You certainly can do somewhat useful AR on a phone. See e.g. some of the ML photo and sound identification tools (e.g. Merlin, Google Lens) that have very quietly gotten quite useful.
But AR that is really a killer app almost certainly needs a fashionable, light, easy to use headset and that's a hardware problem to a significant degree that probably doesn't have a quick fix. Yes, you can do something that's effectively a prototype that's more like a "headset" but that's almost certainly not a mass market device that most people will walk around wearing.
(There's also the social glasshole issue but my guess is that goes away with a useful enough device even if some people hate the idea.)
I really think we're just waiting for the resolution to increase and it to become thinner and lighter and better at hand tracking.
The Quest 2 is already a better experience watching 1080p surround-sound content than most people's TV's -- if you're watching by yourself. But streamers haven't quite caught onto that yet.
But once the screen becomes sharp enough to do real work and hand tracking improves dramatically, I think we're going to start seeing some dramatic shifts.
I think market will be there it’s just like 5 years from now and most people seem to know this such as Roblox and Epic (creative 2.0). It will be speed up by generative AI
I think the Apple headset will be successful primarily because it's an Apple product. As a VR headset it'll probably be technically worse for higher prices than comparable non-Apple headsets (although it'll probably be better than competing AR headsets simply because there aren't any), the software will be top notch and it'll "just work", and most importantly devs will get excited about it and build apps for it.
This. I have never been a fan of watches but after seeing the other 3 people in my house adopt and actively use, year over year, I believe they can produce and market about anything successfully even in crowded market. They truly are good/best at usability.
That comparison makes very little sense. Meta Quest is the best selling VR unit, maybe you should compare it with the best selling console? Nintendo Switch has sold more than a 100 million units. Not to mention that Xbox games also run on Windows - and that has a market reach way above 20 million decices.
The same internal presentation that discusses this 20+ million number also mentions huge problems in retention. People don't use their Quest very much nor very long.
Overall usage numbers are abysmal, and it is a flop. One of the major reasons why it is a flop is that even the people who really want it and actually buy it don't really have anything interesting to use it for.
Legless Second Life is a very good representative of the flop that the metaverse is.
If the Meta pivot was going as fantastic as you say it is, Mark wouldn't be going ballistic on his own employees.
I don't see where these Quest devices have gone to though, who and where is the market? Because even though I run around the tech circles where people are eager to be early adopters, own multiple tech gadgets, etc. I still don't see a single home with a Quest device. I see multiple Xbox and Playstation devices but no Quest.
How can that be more popular than Xbox? Where are those 20 million devices in use? Do people hide them?
Considering the context presented (the sampling of very tech forward people who really enjoy advanced gadgets), then OP's question makes a lot of sense.
Your comparison is a bit weird. I have seen more than 10 iPhones today, and all I did was walk to Starbucks and back.
> But what I don't see is people willing to do the same with Apple who has also invested billions in the space and will be showcasing their Reality platform in the next couple of months at WWDC.
Nobody is criticizing because... there's nothing to base those criticisms on - there's no product (yet) and WWDC is rumor. Once (if) it launches, the praises and critiques will follow.
> I figured that if Mark Zuckerberg decided it's worth pivoting his entire company towards that goal, he surely must have some data to back that up.
I am quite sure he had the data that growth with Facebook, Insta, etc. was limited and threatened by TikTok and others. The Meta stuff was an attempt to break out of that I to a different space, where they could be the early mover. And then being blinded by own fascination for the space. I think many share the assumption that Mark Zuckerberg and Facebook never really understood what users actually want and had luck their platform matched the spirit for some time.
Staying ahead in this game by pivoting to metaverse was very silly. Even if there is no growth in Facebook/Instagram/WhatsApp, it could remain a stable cash cow for years.
Not to mention that Facebook was a perfectly fine and popular social networking platform until Facebook itself poisoned it with the engagement algos that put politics and fake news on top, and drove people away.
Sure it would remain a cash cow if Meta decided never to take another risk again, but Zuck was trying to avoid Facebook becoming the next Oracle or IBM -- companies with consistent revenue but thay have lost their ability to innovate.
I also don't think the metaverse was doomed to fail from the start -- still not sure if it's doomed now. Based on John Carmack's resignation & letter about how hard it was to get anything done, it sounds like there are some serious cultural or bureaucratic issues getting in the way of progress though
> Zuck was trying to avoid Facebook becoming the next Oracle or IBM -- companies with consistent revenue but thay have lost their ability to innovate.
Such sad tales, companies that only make billions of dollars a quarter, with a solid chance of continuing to do so for the rest of our lives...
This obsession with growth is deeply unhealthy. "Innovation" can be great, and we certainly need it happening somewhere, but the idea that it's something that any given company needs to be doing or it will die is preposterous, particularly when applied to an established industry giant like Facebook.
> Sure it would remain a cash cow if Meta decided never to take another risk again, but Zuck was trying to avoid Facebook becoming the next Oracle or IBM -- companies with consistent revenue but thay have lost their ability to innovate.
At some point, I think society is going to have to admit that companies have a lifecycle, and that sometimes a company should die, maybe long before it runs out of money. If the only outcomes are "grow forever" and "become IBM", then I think we should prefer the IBM route, because at least that provides value.
Leave the innovation to smaller companies and allow them to thrive or die on their merits. This whole thing where fossils long past their innovative prime are able to control the entire industry, through boondoggles that are kept afloat indefinitely through trillion dollar cash reserves, rent seeking activities, and strategic acquisitions, is just not good for anyone except the people who are able to exit.
> poisoned it with the engagement algos that put politics and fake news on top, and drove people away.
publicly traded company. they have to keep that quarterly income up, and on a long enough timeline that means taking whatever revenue you can. if you don't your executives keep getting sacked until they find ones who will do the job.
it's not a question of if they'd do shady stuff but when.
or else they pull a Microsoft and start expanding into wildly unrelated fields like the Zune (which failed) or the XBox (which is huge).
Exactly this - it's a real startup move, done by a company that probably shouldn't be doing startup pivots at this stage. I think he got the thrust right - Facebook will continue losing share if they continue the 90s MS buy all your competitors strategy which it is obvious at this stage wasn't working for them, and Meta was an attempt to get ahead again rather than just try to scoop up from behind. This approach will necessarily be built on some kind of intuition rather than data, but should have been a well funded skunkworks project instead of gambling many peoples livelihood on something that will take a while to pay off.
I'm probably one of the few that thinks the pivot overall isn't a bad idea, but it was just done in such an irresponsible way and they're paying the price now. We've seen this many times (notably Uber, WeWork, Google, and arguably Apple until Jobs returned from his exile with a new skillset), but the best person to start a company is often not the best to run it when it's established. But Mark has been so good at keeping equity and control that Facebook will fail unless he learns how to adapt. It usually takes a real low point for people to get out of established mindsets. Just putting this out there so I can point to this in 10 years: If I were to predict the future, I'd say Facebook stock plummets and everyone writes it off, and Mark wises up, bringing it back much stronger. I don't particularly like him, but I think he's got it in him.
The "buy all your competitors strategy" couldn't work. After acquiring wahtsapp and Instagram and all the political games around Facebook there was too much regulatory, anti-cometition, ... attention on them for them to strike any serious deal.
While my impression regarding Metaverse was that Mark Zuckerberg was purposely imprecise on what exactly Metaverse was, hoping to find a company they can acquire, which then in a retcon made that exactly what the vision ever was.
Many fashion brands come and go, only few stick. Some go through deep valleys of pain in between.
Fashion brands use marketing, in the sports market to sponsoring. For Nike the relationship to Michael Jordan for instance certainly was a major driver. For Adidas Kanye West became a major pain.
Social Media platforms try the same. They try to get famous people on their platform. Instagram seems to do quite well in that space (I don't have an account there) while Twitter on the one side and TikTok, YouTube and Twitch on the other try to get people on their platforms.
But then it's different: In sports sponsorship you can focus on one side of the person, their atheltic skills. On social media they eventually shout out their views on things, which might upset people and damage reputation. Of both, the person and the platform.
They are tools you can use to signal status because they are expensive. You can't do that with Facebook etc.
Social media is ultimately not selling status though, they make money by reaching as many people as possible and you have to lower the entry fee to achieve that.
Nike makes shoes and other sports related stuff. If you don't want Nike, don't buy Nike.
FAANG on the other hand aspires to infect every single facet of my life, and they have some glib self-serving narrative about how not only are they right to do so, they have the moral imperative. And so what do they do? They track every single aspect of my life that they can, the invade my privacy, they leak my data, they bilk me for cash at every opportunity. Dark patterns, bad UI, run arounds on the phone, locking out of accounts. I'm sorry but this entire industry is completely fucked, and it's only getting worse. As someone who has been in tech since the 80s, the scene is done. It's been overrun by vultures, bankers, and billionaires with more money than ethics, and they think you are just an NPC in their world, where they are celebrities, kings, and gods.
That is why social tech brands have a shelf life, because none of them can resist the dark side. Nike has a dark side, but at least when I take them off my shoes aren't trying to take over my life.
I think one of the reasons is that as others have said - they know their lane and stick to it - sports apparel. Nike doesn't try to take over all your interactions, doesn't try to own your life and doesn't grow beyond its domain.
Shit, even within its own domain, it's failed with some projects long-term (Nike Golf clubs come to mind). They stay relevant by signing young upcoming athletes, some of whom go on to become known worldwide in sports that are popular worldwide like Soccer, Basketball, and Tennis.
Nike does not have a platform, and in a roundabout way also benefits from their competition doing well (the more people that are active, the larger the potential customer base is). FB/Meta does not have that luxury - to them, if you're not on their platform, you're useless. Nike does not have that problem.
Nike wants to own the experience when you're doing something athletic or casually physical (walking around). There's a limit to that as even pro athletes aren't physically active all the time. Since so much of our lives have a technology component to it, Meta wants to own that whole ecosystem , which is much more ambitious than anything Nike ever tried or will try.
One aspect is that brands like can "rotate" their product and sell new stuff to a new generation, but social tech is stuck because (if it's good) it keeps the existing users, which inherently makes it uncool for new users.
The social tech that your parents use can't be cool, by definition, no matter how good it is, the fact that your parents (and grandparents!) generation is already there is a big drawback to coolness. But social tech companies are reluctant (for obvious practical reasons) to periodically create new generations of social networks to capture a new generation of users by intentionally providing them "not your parents' social network".
I am not so sure about the generative models thing. Everyone is losing their shit about ChatGTP et al, yet I am sitting here saying yeah neat trick but I cannot trust anything it generates since anything and everything can be 100% made up and totally inaccurate and outright false. It is neat technology, but ultimately it is like a dictionary where you have to double-check that it is telling you the correct spelling every single time you look up a word - totally useless in other words: why bother using the dictionary at all if you then need to go check that the dictionary is right using some other source of truth? Why not just go straight to that and skip the dictionary in the first place since it is so untrustworthy.
Every single time I've asked ChatGTP or Bard a "simple" question that I know the answer to, there has always (always!) been something simply outright wrong. It is just not ready to be trusted right now, but I look forward to the day when hallucinations are solved.
Until we can be sure that LLMs do not hallucinate, I struggle to see the value to everyday-people for LLMs beyond use cases where accuracy and facts are unimportant. So ignore google-killing search engines, ignore medical diagnosis, ignore programming, ignore legal advice, and instead embrace making up stories or poems about unicorns or whatever where facts, accuracy, and correctness simply don't matter. It will still have a big impact sure, but I don't think it will be as world-changing as people think once the novelty wears off and people realise that LLMs are generally not very reliable when it comes to giving accurate info, and are better suited to "creative" tasks where correctness/accuracy doesn't matter. E.g. with stable diffusion (remember that?) no one expected a perfectly anatomically accurate picture of a dog or whatever - it did a passable picture of a dog eating a burrito or whatever the prompt asked for, but no one confused it with reality or treated it as fact. This is where I feel that we are with LLMs right now - passable, but does not hold up to detailed scrutiny.
But obviously yes the metaverse is obviously total bullshit and facebook have totally jumped-the-shark on this. They're currently deep in restructuriung to undo over-hiring during the pandemic - it would not surprise me at all to see them also re-pivot away from the metaverse too (couching it as some sort of "focusing on efficiency" or whatever, i.e. continue working on FB, instagram and whatsapp core features)
High-income Westerners do not like to engage in activities that make them appear like mindless consumer zombies.
In Denmark the highest income households have small cheap TVs they can hide away while low income households have big 4K TVs as the main attraction in their living room. The reason is that the former don't want to appear like passive mindless consumer zombies who watch TV.
It is a very superficial opinion but wearing a VR headset is literally the most 1984 consumer zombie thing you could possibly do.
Why does it matter if I'm gaming while looking at a screen which is half a metre away, or while looking at a screen which is in front of my face and allows me to move around, in fact making me less like a zombie because I don't have to be stationary.
It's been a couple of months since I've done anything in VR, but I don't understand why you're being so overly dramatical about it, comparing it to 1984 and consumerist zombies.
Rich Scandinavians are difficult to understand. If you're rich you gotta look poor because poor people try to look rich and you don't wanna be associated with poor people.
Not to mention, ruined the brand value along with it. People knew Facebook, good or bad, Facebook was Facebook. There was still a lot that facebook could do. Could gradually evolve into integrating payments becoming a PayPal in the process, a store front and what not. Bringing a video platform of its own with same revenue sharing model fully integrated and what not.
Yes, there are other companies and products in similar spaces but Facebook would have been cash positive in each of those ventures pretty soon if not crazy profitable.
Whereas the Meta VR demos are almost close to what we can see from 80s, not to mention that they add no value to gaming, entertainment, communication or commerce.
I don't think the European Union regulatory bodies would have allowed Facebook/Meta to integrate stuff like payments and, as such, to "become PayPal in the process". Maybe if that all had happened before 2015-2016, but in today's political and business climate I see no way for that being allowed to happen.
Don’t have to launch in Europe . Payments aren’t like other SaaS apps launching in every country is lot of paperwork and apps will choose to work in only some geographies .
Also WhatsApp does integrate payments in some geographies so it is not like FB wasn’t already having a step there .
FB is just chasing fads, few years back it was libre coin at the peak of crypto interest . They will keep throwing stuff to see what sticks until they run out of money
The Metaverse is coming along just fine. Roblox, Fortnite, VRchat, and Second Life all work. None are ad-supported. It's not compatible with Facebook's business model.
There's no real role for "brands" in the metaverse. Or even ads.
All the successful systems charge the user, although many have a free to play tier.
As a branch of gaming, the metaverse works reasonably well, and is getting better.
Gaming itself is huge, has passed Hollywood, and is going on from there. See the current issue of The Economist.
You know Fortnite has a huge ad business right? Like in the hundreds of millions of dollars a quarter.
Roblox also has a branded games business. It does not mediate ads but it also has advertising of other games on its platform. They are definitely working on automatic ad mediation.
It is Nov 14 2018. Facebook share price is $139. The WSJ publishes reports that Facebook morale is tanking. The top HN comment reads that Zuckerberg doesn't understand Facebook.
A year later, Facebook ends 50% higher. Another year later, Facebook is 30% again higher. And it happens for another year. In the end, what gets Facebook is Apple AAT but it still ends up 60% higher than when that comment was posted.
> I figured that if Mark Zuckerberg decided it's worth pivoting his entire company towards that goal, he surely must have some data to back that up
Maybe like 10 years ago when PG was more active on here he was participating in a thread (honestly forgot about what) where I ended up asking him “If Mark Zuckerberg applied to YC with objectively the worst idea you’ve ever heard, would you invest?”
And he said, “of course!”
I think at the time VR started making headlines, I thought was a pretty cool concept. I loved that Valve and Oculus (private at the time) were both going after it.
When FB bought Oculus I didn’t see an obvious connection, but like you’re saying I just assumed Zuckerberg knew exactly what he was doing.
Over time I’ve come to appreciate WHY they made the investment. If they had been right, they were going to be very right (and frankly in kind of a terrifyingly dystopian way imo).
I also wonder if FB could go back in time would they completely scrap VR investment? What (at the time) would have been their big bet instead?
>I also wonder if FB could go back in time would they completely scrap VR investment? What (at the time) would have been their big bet instead?
I think this is the relevant question. So many people fall into the Trap stop thinking in terms of binary outcomes, especially with hindsight information. This isn't how business investment works at all.
The same people that are quick to judge investment failures can rarely produce an alternative idea with multi-billion dollar upside.
I think the reality is that the useful part of meta-verse, the meta part, runs contradictory to the interests of a company like meta. Because it involves:
1) De-proprietorizing user data
2) Handing identity from identity providers (like meta) to open systems
3) Allowing foreign content into the walled garden
So Meta built the least useful but snazziest part of the meta-verse, the verse part. And they built it in the face of a bunch of other already extant "verses", like Roblox which offer a more intersting landscape for interaction.
They made Second Life but without the ability to ruin a CNN press conference with flying human genitalia, which basically means they made a worse version of Second Life.
All 3 of these technologies retain a very strong, putrid stink when given a rational smell test. Until someone finds a way to permanently wash away this foul odor, I will remain skeptical of them.
Metaverse stink: "This could have been an email" in 3-D!
Bitcoin has 2 stinks:
A)Find a lot of computing energy. Think about building power plants to make coins, and you're starting to get somewhere.
B)Price will rapidly drop and spike, maybe thousands of dollars per day. That's a feature!?
LLM AI: 60% of the time, it's right every time! This tech includes very nice graphics to back up any of its highly confident and hallucinogenic bullshit. Until this phenomenon is well understood, it stinks! https://en.wikipedia.org/wiki/Hallucination_(artificial_inte...
Mark Zuckerberg believed VR would be the key to the company's future expansion. Unfortunately, he was wrong. However, it is important for leaders to take risks and lead their companies in new directions. So he has my respect.
Simultaneously, it is worth noting that major technology companies did not develop working generative AI. Examples include Apple's Siri, Amazon's Alexa, and even Google's search algorithms, they all fall short of user expectations. And they had years and years and billions of $$.
The parallel between virtual reality and artificial intelligence is intriguing. If some company can successfully develop a VR system which does not suck, it could revolutionize the industry in much the same way as a openAI.
But that company will not be any of these big ones…
> It's been the same with crypto, for that matter. None of the reasonable people I know ever saw any grand value in crypto.
Were these reasonable people banking with Silicon Valley Bank like all the smart guys? Crypto is promising a financial system that has so far appeared to be much more resilient than the traditional system and bitcoin is currently at $30k. Tether has survived something like 2x depegs so far.
We might finally have a technology that can resist financial authoritarianism; there is no body that can stop bitcoin transactions and it is proving itself to be resilient enough for medium-term use. That is a change on the same magnitude as the internet.
> Crypto is promising a financial system that has so far appeared to be much more resilient than the traditional system
I strongly disagree with this. When SVB failed, there was a system in place to insure some of the depositors' funds. The government chose to augment that by insuring all the depositors' funds. That was an unusual move, and then the banking system returned to normal when a better capitalized bank took over SVB's assets and liabilities. The bank failure cost those who invested in the bank. It cost the bank management. It did not cost the depositors.
When a crypto exchange fails, depositor funds are unrecoverable. There is no system to protect the depositors, no system to recover funds from the failed exchange.
While financial authoritarianism is imperfect, its rules are designed to reduce fraud and to reduce the impact of fraud on innocent bystanders.
> When a crypto exchange fails, depositor funds are unrecoverable. There is no system to protect the depositors, no system to recover funds from the failed exchange.
That is why I'm anticipating that crypto will be a stronger ecosystem than the traditional financial sector. If we punish people for bad decisions, then by Darwinian logic the crypto ecosystem will not funnel capital towards the sort of idiot depositors who give Joseph Gentile their money. If they cared to check what their money was funding they could have seen this coming.
The traditional finance system is protecting those people. That weakens it. Which has always been the strongest argument against governments handing out money to failed banks. They've been doing that for at least a decade and it means the financial system is shaky enough that it falls over when hit it with 5% interest rates!
> Crypto is promising a financial system that has so far appeared to be much more resilient than the traditional system and bitcoin is currently at $30k.
What is bitcoin resilient to? Not falling to $0?
> We might finally have a technology that can resist financial authoritarianism; there is no body that can stop bitcoin transactions and it is proving itself to be resilient enough for medium-term use. That is a change on the same magnitude as the internet.
I don't think that our current financial system fails that often because some transactions were stopped.
> What is bitcoin resilient to? Not falling to $0?
If we cherry pick, say, the Vanguard Long-Term Treasury ETF [0] in the last 3 years it is down 30%. So bitcoin isn't as resilient against value loss US treasuries but we're seeing changes in magnitude in price that is similar to a long term bond ETF. That is a lot better than I expected, and probably a lot of others. Really good performance compared to the gains, I suspect. No obvious counterparty risk, so probably superior to the debt-laden US government in some sense.
> I don't think that our current financial system fails that often because some transactions were stopped.
Someone is paying for bitcoin to burn a medium country's worth of energy to keep running. That speaks to a certain sincerity in their disagreement with you.
Not a Mark fan but the Meta Quest Pro and Oculus are great and innovative devices. The obvious flaw in Meta business execution is that there is no content there! If you bet on the Metaverse you should build it and not wait developers to come. Or incentivize developers to use your platform.
From the business perspective I think they failed in playing the Japanese console game old strategy (Nintendo and Sony): work obsessively to have great and high quality content and synchronize this with the console launch. Not saying that Nintendo and Sony are not nightmares for producers but they are very obsessive about details.
I think in Zuck’s mind the analogy is Bill Gates pivoting Microsoft to GUIs in 1983. Which seemed pretty crazy at the time when PCs ran at 4 megahertz and could barely fill a 320*200 screen with four ugly colors. But Gates had seen Xerox Star and Smalltalk and Lisa prototypes.
VR’s “Mac moment” may be happening this year with Apple’s hardware unveiling. I suppose Zuck hopes to ship his mass-market “Windows 3.0” soon after. I’m very curious to find out what consumers think of the Apple product.
> I'm sure that if he had to decide on a direction to pivot to today, it'd be towards generative AI
I'm pretty sure that I agree with you, but what would Facebook/Meta do with LLMs? You wouldn't want to generate fake people to interact with (well, someone might, but Facebook wouldn't). Because that's what data they had would have been useful for. I mean, if you can predict what a person will say, or how they will react to an ad, that has value... but I'm not sure I know where that value is for a Facebook, outside of better targeting of ads.
Maybe predicting consumer/voter sentiment about a policy or product before it's released?
The same applies to Google in aa certain respect actually. I assume they have enough data from gmail to effectively recreate a conversation with me. This could be lucrative for some targets (not me!), but probably not in a way that Google would be able to legitimately capture.
I could completely see how other actors would be able to use LLMs to predict or impersonate people on the Facebook/Google platforms, just not how the platforms themselves would be able to generate value.
Google at least could merge generic LLMs into their search mission to catalog the world's information. But that's a harder pitch to figure out how Facebook would generate value from it.
Am I missing something, or am I thinking too much about this like West World?
Sure, but VR isn't, they're different things. For VR they've sold somewhere around 15-20 million headsets, and many people use it quite a bit. I have no doubt VR is/will be big, but the path to finding what's compelling in VR will be strange. Personlly I rediscovered a love for table tennis and play every single day now, I'd probably pay $2-3k for a Quest 2 if I had no choice.
That said I think trying to build the "Metaverse" in a top-down way will be very difficult, and Meta will probably not be the ones pulling it off since they don't have much good will, people actively avoid their social platforms if they can. But to me, what we need is not a Metaverse, but a good OS/platform with integrated social/identity, where friends can easily join each other's games, voice is enabled by default and provided as part of platform, not individual apps etc. Meta has been working on making this easier, but with my friends group the friction is still too high. And it's super annoying when third party apps (like Rec Room) needs their own login, friends/social features etc making it cumbersome to find your friends in there.
ElevenVR has, according to themselves, 1 million players (https://elevenvr.com/en/), how many active I don't know. That's just one niche. Other popular games/experiences are various shooters (Onward, Pavlov etc), rhythm games, fitness games, social experiences like Rec Room and VR Chat, movie/tv viewing apps, golf. Fitness has to be the most surprising one which few people would have predicted. For me, a few of my friends bought one together so we can hang out and play games, as we live far away with families these days. Remote meetings is obviously a huge potential one, but we probably need one or two hardware iterations to make that a compelling alternative to video. So it's safe to say VR has found some compelling use-cases, the question is if it's enough to sustain growth. More use cases will open up as the hardware gets better, so I think so.
Statistically speaking - people who have brilliant innovative ideas that result in successful businesses are exceedingly rare and those ideas often come from experiences outside of the main line of work by combining ideas from disparate disciplines to have a true breakthrough. We as a society really need to disabuse ourselves of the idea that those ideas are likely to cluster on a small set of individuals that continue to crank them out. We've developed such an extreme cult of personality around the rich and it's pretty baffling to see when, if you actually sit down to talk to people - we're all pretty brilliant.
Companies that get big and then score repeated out of the park hits do so by attracting and nurturing talent[1] - they don't do so by having one brilliant star that shines eternal.
1. And that is a really good and honestly rare talent in the modern marketplace - it can be hard to let creativity thrive.
It's worth remembering that unlike with cryptocurrency, our ("reasonable people" as you put it) apathy for the "metaverse" stems from the fact that most of us experienced it a long time ago, long before that term even came into common(?) use: Multiplayer games, and especially MMORPGs.
Be it Ragnarok Online, Runescape, Ultima Online, League of Legends, Call of Duty, Minecraft, or whatever, anyone who has played multiplayer games of any kind know exactly what the "metaverse" was trying to sell to us and the common masses. We also know that multiplayer games, unlike practically every romanticized depiction, generally sucks to play with strangers. You absolutely need a tightly knit group of good friends to play with to be able to truly enjoy them.
So when we said the "metaverse" would never take off, it's because we have literally been there and done that.
Aren't we on a multiplayer chat board with strangers here?
I think you hit the nail on the head as far as how the metaverse is not new, but I think your pessimistic take is not so obvious to me and presumably many people bullish on metaverse ideas.
The thing that would make a Metaverse interesting is if it acted as glue between all those very similar services, i.e. being able to hop from one MMO into another one with your complete party, without having to switch accounts, avatars and all that. Kind of like your browser can access and follow links to numerous different websites, but with 3D and multiplayer included.
The problem with Meta's Metaverse is that that's exactly what they don't want, their vision of VR is one where the have complete control over everything. Thus you aren't even allowed to access their Metaverse with hardware not made by them.
I agree. I have 4 Quests and know many with Quests. It's funny how all of us used it very frequently in the first couple months and now they're gathering dust.
The fact of the matter is, if you have people you can hang out with in person you're not going to bother with VR, or the metaverse.
I use my Quest regularly, although mainly for gaming and fitness.
I've played around with the social aspects, and they're interesting, but I don't really have friends with a Quest and I struggle to make friends just by butting in on random conversations, so I haven't really done it much.
Have had a couple of interesting conversations about movies with a movie nerd in a virtual hangout in the Bigscreen app, though, and did some dancing in a virtual nightclub a couple times, which was actually pretty fun (I think I'd feel a little too weird doing going to an actual nightclub nowadays, I'm a little old for the scene).
> The fact of the matter is, if you have people you can hang out with in person you're not going to bother with VR, or the metaverse.
Several of my friends have Quests, and we use them regularly with each other, but the catch here is that we all live in different parts of the country, so it's great for some more informal goofing off while we chitchat.
The thing about the metaverse (and related tech) is that its success or failure rested entirely on the rate of improvement of the hardware. If the headset could present, say, an office that I could work from for 8 hours -- this would represent a massive disruption to the commercial real estate market. If I could sit down for a real conversation with my mother (who lives a 2 hour drive away) without it feeling like Zoom with motion sickness, that's a social game changer.
The problem is that the tech cannot actually do things even close to this caliber yet. The fidelity has not reached the uncanny valley yet, much less gotten over it. Zuckerberg clearly thought he could make this possible with Meta's resources, but that just didn't happen.
I'm not a crypto advocate, but I don't understand on what basis people think crypto has been empirically disproven, at least separate from any disproof that wasn't ~equally true at its peak. It's not like Bitcoin has failed; it's down 2x from its recent spike, but it's up almost 10x from its Jan 2019 dip. Ethereum is more wounded but still expensive. Look on a log plot as is apt for these things, and it's hard to argue ruin here, especially given they've dipped before.
I wouldn't be too shocked if crypto did peter out or flatline over the coming years, just it doesn't seem a priori obvious, given my broad criticisms of it have not stopped its success to date.
There was a time around 2020 I believe, where everyone and their mother was talking about crypto and the blockchain, and how it's going to be this big technological revolution. All kinds of private and public initiatives decided to include "the blockchain" in their projects, NFTs became huge, and there was talk of putting real estate, healthcare, and logistics "onto the blockchain".
It's been three years since then, and still no real-world use case has emerged. I don't dispute that there are completely valid use cases for cryptocurrencies, mainly around avoiding governmental financial restrictions and safeguards, and there are still loads of people using cryptocurrencies for speculation and/or as a "store of value". But the whole ecosystem of distributed apps, smart contracts, DAOs, and so on, still mainly revolves around itself, without wider societal impact.
Maybe I'm in a minority with this argument - but just because something has a big market cap or a positive trend line, it doesn't automatically make it valid. (Bernie Madoff, Archegos, ...)
Bitcoin has proven itself to be a useful financial speculation object.
Hence “empirically disproven, at least separate from any disproof that wasn't ~equally true at its peak” and not “discredited by argument from principles”.
Initially, I didn't see much value in the metaverse due to the high barrier to entry for end users and the limited network effect. However, I am bullish now. With the advancement of technologies like GPT-4 and Stable Diffusion, there is potential for more interesting NPCs in the metaverse. Additionally, Virtual Reality (VR) could serve as a superior user interface for these technologies compared to text-based interfaces like chatGPT. This could enable the metaverse to scale without solely relying on the network effect, as engaging NPCs and VR experiences can provide value to users even in the early stages of development, and continue to evolve and expand as technology progresses.
If "bullshit fractal" wasn't a thing before, it deserves to be one now. The kind of bullshit which just invites even more bullshit when you dive in and try to pick it apart.. its turtles of bullshit all the way down.
> It's clear to anyone from day one how useful those models will be
I agree it's clear on day one that these models will be useful.
What's less clear is how useful they are -- a year ago most experts would have told you that an architecture that "predicts the next word" won't be powerful enough to make a model that could lead to AGI-alike abilities (and many people here still argue the same today), but here we are now.
> Maybe Mark Zuckerberg was just unlucky to decide on a company pivot two years too early
That's just a lack of vision. GPT-2 was released in 2019, GPT-3 in 2020. He had plenty of time to commit to AI development instead of Metaverse.
A lot of self-proclaimed technologists counterintuitively love to see technology fail, especially when they predicted so ahead of time.
That's some frustrating shit, because it rewards the least patient and surface-level analyses which (correctly!) identify deficiencies and lulls in activity, but mislabels them as stagnation or dead-ends or fundamental flaws.
It took us 20 years from General Magic to a passable iPhone.
VR will take time, and AI is likely more fruitful to prioritize currently (not saying that's a bad idea!) - but we don't yet have enough historical perspective to declare VR - or even (ick) crypto - as bad directions.
> I'm sure that if he had to decide on a direction to pivot to today, it'd be towards generative AI.
I don't think so -- generative AI doesn't really provide strategic advantages to Facebook/Instagram/WhatsApp the way it seems to hold promise for search (Google/Bing) and productivity software and certain jobs. Same way crypto isn't strategic to Meta either.
You don't have to pivot your company. If you're still raking in cash, it can be much smarter to just continue that, rather than make a giant bet that might ultimately sink everything.
You cannot compare VR with Crypto. VR can be super useful but the tech isn't there yet, similarly to where generative AI was two years ago. Once we have a breakthrough with VR it'll also be amazing and useful.
VR is as useful as the whole movie industry and the game industry. Yes, it is important for entertainment. With all the streaming services the movie industry is moving from central cinemas to your home.
So VR will be in competition with all the other entertainment industries. But is that useful in any sense just besides entertainment? I doubt.
It started all years ago with Google Glass. Even at that time I doubted that there is value in this. Now, we are here and Google Glass is finally dead. I know it is in the rumors that Apple will bring its VR headset soon. But really? Will that make it better? I doubt.
VR will be in competition with all the other forms of entertainment. It is something, you can't just do besides. It will need your full attention. I doubt that there is some real usefulness.
I think it's important to note that Google Glass was not really a VR system—it was AR, essentially overlaying a HUD on top of reality. I can see many extremely useful possibilities with this that just don't apply to VR (which, indeed, I think is going to be most useful for entertainment and a few other niches).
AR can help with navigation (overlaying the directions right on your field of view); with social interactions (facial recognition, even locally, can identify people already in your contacts, and remind you "you wanted to thank her for that birthday present", or whatever); with learning about the world (look at a tree, a flower, a bird and ask for an identification)...
And that's basically just taking apps that exist now and imagining them integrated into AR glasses.
(Yes, there are definitely concerns about things like privacy, with the possibility of having cameras on our faces all the time; I am hopeful that we will find solutions for these, but don't have good ones off the top of my head.)
I have an old farmers house with a land and I have historic cars and I travel the world for real, not virtually, because I want to learn the world for real, not virtually.
My house is near a hughe lake. There are people swimming for real, not virtually; there are people sailing for real, not virtually; there are people windsurfing for real, not virtually.
In my (admittedly uneducated) view, VR can be useful for some professional tasks in the immediate future. Things like 3D modeling, architecture, explorative data analysis. But Facebook is a social media company. Aside from a small proportion of enthusiastic users, people won't want to socialize with VR. They'd rather check an app on their phone every so often while doing something else. If they want a more personal and engaged conversation, a video chat is better than VR. The Metaverse makes no sense beyond games. And the heyday of socializing in MMOs has long passed (much to my dismay).
Completely agree. I'm frustrated that Oculus and VR tech in general has been lumped in, via the "metaverse", with a bunch of less useful and less interesting crypto/NFT stuff. All I wanted was some cool niche flight and mech sims, maybe some interesting AR projects beyond what Niantic could offer. Instead, we got a bunch of ugly tech demos, outright scams, and virtual meeting rooms that nobody uses.
Being able to buy drugs online was cool, but I'm not sure it was worth the billions of dollars invested and vast amounts of carbon emitted.
Yeah, Facebook's Metaverse pivot made VR pretty toxic right at the point where they were getting a significant level of adoption amongst the public.
They needed to focus on making a few more games with the mass appeal of Beat Saber and making entry level machines a bit cheaper again so there was enough users to make the social aspect actually have some value.
> Contrast that with the generative AI models revolution. It's clear to anyone from day one how useful those models will be, and that they are providing clear value right away. It's no wonder that all the companies are immediately pivoting towards it. Maybe Mark Zuckerberg was just unlucky to decide on a company pivot two years too early -- I'm sure that if he had to decide on a direction to pivot to today, it'd be towards generative AI.
I think fundamentally Facebook is not a product company and is consequently bad at actually making products. Apple has been moving very cautiously on the AR/VR front in contrast. Granted, Apple moves cautiously on everything, but they do seem more intentional about what to leave up to users to figure out on their own vs the Facebook approach of assuming you can just solve the interesting engineering problems and have the cool technology and people will just figure out how to use it. Smart watches and smartphones existed for a while before the Apple Watch and the iPhone, but what really kicked off the market for them was just a design that put it out there for people to explore with it so Apple could then iterate and figure out what the real niche was. But that will never happen if your initial test cases are just tech nerds. Tech nerds love the technology qua technology too much to figure out why things are interesting outside that.
While generative AI may be useful, to what extent is it useful to Facebook right now? I mean as a new business model, as opposed to helping them do better software development or moderation?
Meta can't afford not to invest into generative AI. They are constantly fighting to stay relevant. Just see how TikTok's better recommender algorithm and content creation tools made Instagram play catch-up.
I'm not certain about the direction of Meta, but for now it seems that their most important areas are entertainment (Instagram, Reels) and messaging (WhatsApp, Messenger), not social networking (Facebook), which is dying.
For entertainment and messaging, generative AI is going to be huge. In entertainment, content creation and discovery will be severely advanced by AI. For messaging, at the very least, users will expect AI support in message composition and company-customer communication.
Generative AI makes their business case for the meta-verse actually work. You can populate the meta-verse with convincing NPCs: they fit in, they finesse social interactions, they kickstart communities and befriend the unpopular, and every once in a while they drop some product placement. For an introverted, anxious, and digital-preferring generation, this could be perfect.
NPCs that are convincing if you ignore the fact that they only can remember less than 5 minutes of interaction because they lack long-term context due to the nature of LLMs?
I'm not sure if lonely people would rather talk to an Alzheimers anime girl or be alone.
Having the NPC store some notes about previous conversations or look up stuff in the chat history doesn't seem impossible.
Also if you don't want to build a relationship but just chat a bit you don't need long term memory.
Absolutely disagree. The metaverses value proposition is the ability to create hyper customized communities and experiences. Generative AI is a near requirement to see that vision. Many, many people do not have friends online, or they have different interests, or for whatever other reason may prefer interacting with AIs who do exactly what they want.
It has a lot of uses for their metaverse push. You could imagine a future social platform where AI generated pictures and video instead of selfies is the communication medium du jour.
But in that sense they're not far behind the pack as it is.
Great point, there might not be anything for them there despite the insane hype right now. A couple of useful things here and there, sure, but not much to profitably "pivot" their billion users into.
Just to get the facts right: The "bullshit fractal" Bitcoin is currently at about 50% of it's all time high, and is raising again constantly since beginning of 2023.
OTOH: Whether generative AI has any value beyond mass desinformation and making "creative people" unemployed only the future may show. Also: Given than you need super-computers to do the training it's unlikely it will become a technology that can be used by everyone. (The situation here is imho similar to "open hardware": You may be able to design the hardware but you're not able to actually build it in your basement—like it's the case for open source software, which made kind of a revolution possible. AI will likely remain purely a toy for the few richest companies on this planet, without any access for the masses, beyond being "customers").
Regarding VR (the "metaverse"): This was a dead idea already as Second Life was hyped. VR pops up every 10 - 20 years since the 60's, but never caught on; and likely never will for practical reasons. Even Bitcoin has more real wold applications average people would care about than VR (e.g. you can at least buy "stuff" with Bitcoin, or send and receive money against the will of your government).
> Just to get the facts right: The "bullshit fractal" Bitcoin is currently at about 50% of it's all time high, and is raising again constantly since beginning of 2023.
Is the economy of Bitlandia on the rise in real terms, or what? Huge export surplus, something like that? If not, then WTF is that to brag about?!?
Big unmotivated swings in the exchange rate are a failure in a currency. What you're crowing about is that as a currency, Bitcoin sucks.
I don't think the metaverse is such a bad idea, I just think we're not there yet, and also that Meta isn't a trusted or cool enough company to pull it off. VR now is like a 1995 laptop, and it needs to be an iPhone for the metaverse to happen. And probably more than that, it'll need to be AR before it could happen. It needs to be Google Glass, but what that can be 10 years from now, and made by a company people like enough to generate FOMO.
Personally I think it's going to come from the gaming space, as they already know how to create virtual spaces people want to be in. Either a really good MMO (World of Warcraft had people glued to CRTS) or something like Fortnite, where we already have celebrities doing "live concerts".
This was why I knew the metaverse was going to be a failure, it was clear as day there were business executives acting with so much self confidence about what the future of virtual experiences will be..... while ignoring the entire medium of designing virtual experiences and all of the collective wisdom learned from successes and failures.
It is like a successful painter annoucing a new revolutionary form of art that involves sounds arranged in time to create artistic experiences instead of paint on a canvas.
> But now we see that crypto was indeed bullshit all along.
Just looked it up. Between BTC, ETH & top stablecoins, crypto has $900B+ market cap and $60B+ in 24-hour volume. I'm not saying your conclusions are wrong (though I disagree), just that you're calling the game "over" at the end of the first quarter based on one hype-cycle. I remember people doing something similar in the dotcom bust: "WWW is dead."
There have been multiple hype cycles for crypto. In over a decade, I have yet to see something priced in cryptocurrency. Pricing something in dollars and then converting that amount in cryptocurrency for the next 15 minutes is still a dependence on government backed currency.
Contrary to some peoples' understanding, replacing fiat currency for everyday purposes isn't the only viable application of crypto.
As one example: There are already banks that use XRP as the international settlement medium. You'll also see a lot of conversation right now about central bank digital currencies (CBDC) that could plausibly utilize crypto in some fashion.
There are $7.5T worth of foreign exchange transactions per day. If BTC can take 1% of that it's currently worth $1.5M/btc. The rest of the crypto market shadows btc with other blockchains having niche uses.
BTC/crypto is a natural alternative to USD settlement. If you believe the USD is sunsetting as the global reserve currency then crypto, especially btc is probably a good long term investment.
You can ignore the grandiose claims of crypto savants and still accept how its unrivaled cloud development platform is going to continue to attract developers, accept that the entertainment sector is valuable, accept that the collectibles sector is valuable and we just never had transparency into the size of that while reducing friction for some aspects of the collectibles market, that financial services is valuable solely because there are some frictions to solve from people already there, that gambling is valuable, that flash loans are not paralleled by any other platform except the central banks overnight market, and so on. Outside of crypto its still hard to get free live transaction data for your trading algorithm.
None of this needs ideology about the consensus layer or fandom about how transactions are settled with claims of “hard money” thats going to take over the world, but that sentiment does harden it and is intrinsically intertwined. But you can ignore it and still recognize the parts that are valuable, even if there is no value to you.
Meh. I'd argue that the conclusion for Metaverse/crypto hasn't been reached yet. (Why? There's a 1.2T market cap saying it hasn't). It's like saying internet grocery delivery is dead because Webvan died in the early 2000s.
I'd give those two another 5-10 years before I expect to see real results — so much needs to be built first at the foundational layer.
I mined bitcoin in 2011 which didn't go well and then made first transaction in 2017 which took 2days to be processed as a result i ruled it as stupidest digital currency.
Even though I feel technical right all these years i regret for not buying as many as i could have even back in 2017/18.
Centeral banks turned everything like a Ponzi scheme. How the heck borrowing and spending is a better option than saving.
> Centeral banks turned everything like a Ponzi scheme. How the heck borrowing and spending is a better option than saving.
Central banks are just playing a larger game, they aren't causing it, the game is: ever increasing growth capitalism. Borrowing and spending creates "growth", saving doesn't. While we exist in this system we can try to pinpoint the blame at different actors but they aren't the cause of it, they are just playing along.
The incentives for growth don't align with what's best for society, they align with making people indebted so companies can grow their revenues.
> How the heck borrowing and spending is a better option than saving.
Oney is worthless. Unless you like pieces of paper representing defunct national heroes you should not hold money but assets, stock, estate, things that have intrinsic value.
Save for tax cheats (even though the laws are clear) and speculators, crypto just doesn't provide that much value. There are some neat use cases but they are just that.
The "metaverse" stuff... I don't think it was a bad bet to buy up Occulus, they still haven't found a great nail for that hammer but pivoting the entire company seems questionable. There is so much toxicity on the internet, why would you want to be "immersed" in it?
I'm not anti-generative AI, I don't want to sound that way but Zuck and company have some interesting data on large scale systems with giant amounts of data and information, they certainly have invested in it too. Maybe it's wasn't "luck" so much as they might have some intuitions about the negatives uses of the technology. It's seriously cool stuff but I think we're still collectively in the honey-moon period. I do forecast a world where we will need to exponentially strengthen our BS meters.
I'm not sure if Metaverse was a bad idea so much as selling out everything else to go full steam on Metaverse was a bad idea. It felt like they sold out their core user base and destroyed their existing platforms to get there. They were simultaneously tanking their image and reputation with users while asking them to commit and invest in a new platform.
I agree, but I also think the marketing around the ideas wasn't good either. You need public mindshare to build an ecosystem like this, and a lot of the potential audience never understood the point of it. To this day, I have no idea what problem the Metaverse is supposed to solve.
The only reason Zuckerberg wanted to pivot to the Metaverse was because he wanted to be president of the US but couldn't. The idea was spread briefly, and he found out that the general public hated him and he had no chance to win political office. He decided to make his own universe where he could be the virtual president / tyrannical dictator.
I'm going to go out on a limb and say that the metaverse isn't a bad idea, but the implementations just aren't there yet. Or at least, folks aren't coming up with applications that are both compelling and supportable with affordable hardware.
Google Glass had similar problems.
Eventually someone's going to nail both these things, we just haven't seen it yet.
I can see the tech being super interesting for video games. But the angle of going to work, going to a mall etc. in the metaverse is just super unappealing. The nice thing about working remotely is that I don't have to go to an office and the nice thing about shopping online is that I don't have to go to a mall. So, why would I want to emulate the these things on a platform where something better already exists?
Sometimes going to work involves manipulating things in a hazardous environment and VR can make it easier to do that sort of stuff remotely. Similarly, augmented reality makes it easier to do things when you need dynamic information about a task and you've got your hands full doing the thing.
Get VR and AR _really_ good for those sorts of use cases (and I think there's some money in that stuff) and it becomes a lot easier to expand into other areas.
> But now we see that crypto was indeed bullshit all along.
The faithful have managed to get BTC up over $30K again, though. Saw Tim Bray posit the other day that if the US Gov just dumped all of it's BTC holdings (mostly seized from criminals) they could crash crypto quickly since the liquidity isn't there.
I think in a room with enough sycophants one could be made to believe in the vision of the Metaverse being the answer to Facebooks current problems;
- Lack of relevance on the big blue site.
- Huge slide in ad revenue.
- Expensive acquisition of Oculus with not much revenue to show for it. $2bn is not a bet-the-company amount of money for Facebook, but it is something, and that $2bn spent on Oculus is op cost taken from somewhere else.
- Reduction in moats for FB, Web shifted to mobile, FB tried bets on mobile + gaming, but those moats have receded.
I imagine Mark wanted something that could increase ad spend, new revenue stream (increase revenue from micro transactions, digital asset ownership) and something to give them some platform strength to shore up their future.
If you look around there is no other technology that is offering itself as a platform to own apart from the meta verse.
Now, I absolutely do not think this bet will pay off - but I can see how he would think it would.
The best theory I've seen is that Zuckerberg was looking for an angle where Facebook could control a platform, rather than simply be a program on somebody else's. Look around, see VR, and think "This space is in its infancy, and doesn't currently have a market-dominant platform" and then bet big.
Because at the end of the day, Facebook didn't have much to lose. The social media wars were over, FB and especially Instagram had won. As long as they didn't actively break anything, the information->ads->money pipeline will keep flowing until the entire space gets disrupted by something fundamental shifting under their feet.
A VR-2ndLife that actually caught on could honestly be a relatively believable such shift. Ultimately it didn't, but that's still alright news for FB: no big changes means the gravy train is still rolling.
It's pretty silly to compare metaverse to crypto. Crypto is a solution looking for a problem where as the metaverse exists in many forms today with the question being whether the tech and userbase can evolve fast enough to sustain Meta.
They could both fail but I don't think you can predict one from the other.
The crypto problem has an army and intelligence apparatus and ostensibly, legality. Some people may think it would be nice to not have to lose portions of your savings by indirect taxation whenever the problem decides to print money, plus of course the rest of the spectrum of wild authoritarian control.
It seems crazy to me that Amazon laid off a lot of the Alexa and robotics teams.
You'd think if anything they'd want to invest in that more now that LLMs could be used in combination to produce a much more natural home assistant experience.
That said, whilst I think VR doesn't have a huge amount of potential (the equipment is expensive and awkward), I think there is still a lot of space for making it easier to meet and communicate with people virtually. There's still a huge amount of friction where nowadays almost every service has limited public messaging and comments, etc., and online communities are fractured across dozens of Discord or Matrix servers. I think one of the main parts of Tiktok's success has been that it makes it easy to speak to new people either via public comments or video replies, etc.
There was a story about the Metaverse and Carmak and some discussion and disagreement about issues like not being able to host stadium sized experiences (not all the avatars could be in the same room) and other topics like avatar quality in meetings.
I couldn’t help but think that I have zero interest in a stadium or any size meeting where I have to put a VR helmet on….
I can imaging Zuck and Carmak and others would love that people listen to them in stadium sized meetings, but I’m not sure how users feel. I’m sure one day there will be such experiences, but there seems to be nothing appealing to many individuals about them now.
God help me when some CEO declares a VR mandatory meeting…
Metaverse can and probably will eventually pan out when tech is ready for it. I'm really happy Meta is subsidzing Oculus head sets, and I hope they keep cranking out new versions. That is one piece of hardware I can't live without, though I don't do metaverse or even game with it.
Crypto seems to have been an easy money scam from almost day one.
>> As it stands, my intuition (and everybody else's) turned out to be right.
It’s been 18 months since they “pivoted”. Come back in 5-10 years to see who was right. Assuming the metaverse is a failure at this point is simply arrogant.
Most likely people who predict failure will say of course Mark managed to make it work because he could afford to throw billions on top of billions after it.
The metaverse is a 10 year bet that involves progress across multiple axes. No-one here can predict the state of progress in ten years.
> I figured that if Mark Zuckerberg decided it's worth pivoting his entire company towards that goal, he surely must have some data to back that up.
You know, I never really though these founders were visionary geniuses. For the most part they are well connected/already well off, and did the right thing at the right time. I think the last couple of years have made that even more clear.
Facebook really started taking off about the time that a second golden age of tech was starting, fueled largely by near-zero interest rates and a focus on massive IPO exits without any proof of profitability. Nobody had to make any money for years, if at all. Uber hasn't made any money and neither has Spotify. Tesla does make cars, but its real product is arguably its absurdly valued stock that has allowed it a large runway fueled for the most part by the delusions of grandeur of its CEO. During this time larger companies simply acquired everything in sight, hoping that it would pay off. I mean, of all these acquisitions by Meta, which have been worth it? They're not all Instagrams.
Facebook made it, but not because Zuckerberg made the best PHP site ever. Right place, right time, maybe among the first to realize that any engagement is good engagement, and I doubt it was Zuckerberg himself who had that realization.
On top of that, Google, Meta, and advertising companies in general have grown mostly on the theory that the mass amounts of data that they collect and use to sell hyper-focused ads is worth something. Recently it's been revealed that this isn't true, and you get just as good or better results by simply advertising the last thing somebody looked at, or whatever they are currently standing next to IRL. Knowing that you looked at hemorrhoid cream 3 years ago doesn't help you sell anything today. So it's arguably based on lies as well.
Now with interest rates up, I think we'll see how that plays out as advertisers finally start pulling back due to economic conditions. Uber turned off 2/3 of its ad spend in 2017 after it found that most of "conversions" were in fact fraud. Curious to see what other companies experience on this front. We'll find out how many of these founders are true geniuses or were just burning cash. I mean shit, give me a billion dollars and I'll give you something that looks like the next big thing no matter what...
Given Facebook’s track record with politics, I am glad they didn’t pivot to generative AI. I don’t see anything “good” coming from that push as far as societal outcomes are concerned.
To be fair, when Facebook was created there was no data either. Data can be useful but I have yet to hear a story where data played a pivotal role in creating a successful startup
VR will be something eventually. Bandwidth/Storage isn't there and the device technology isn't there. I would love to be able to walk around Pyramids or Petra and have it be life like and not make me sick.
Zuck doesn't care about the metaverse, he's chasing the next consumer device since he missed the smart phone. He knows that if he doesn't control the hardware, his business is at risk. Apple has reinforced this.
"Contrast that with the generative AI models revolution. It's clear to anyone from day one how useful those models will be, and that they are providing clear value right away."
> But now we see that crypto was indeed bullshit all along.
You say that, but crypto bubble hasn't really popped. At 30K, BTC is only down around 55% from the highs, that's about in the same league as many tech stock declines this year. A true bubble pop should be like 90%+ down. The masses clearly don't agree that it's bullshit so far.
I just think the massive spending is a bit premature. Keeping a R&D division inside Meta makes sense. Betting the farm does not.
VR has enormous potential but we are still lacking more ergonomic headsets and killer apps. I want to do 3D modelling in VR - except for some simple apps, I can't do that.
> It's been the same with crypto, for that matter. None of the reasonable people I know ever saw any grand value in crypto. Researching myself, it always just seemed to be a bullshit fractal.
I consider myself to be a pretty reasonable person and I think the value in something like Bitcoin is as a backup or alternative to the traditional system. Similar to how someone would invest in gold. Except Bitcoin is much easier to transfer, requires much less space to store, etc., vs gold. I think 95% of crypto is bullshit though, and there are a lot of scams.
If you look at recent bank collapses, high inflation, etc., I think a reasonable person might question how long modern monetary theory can go on like this. I'm not a gloom and doom person. I still hold fiat, haven't given up on banks, still invest in US treasuries, stocks, etc. But I think holding some in crypto and gold, etc., also makes sense.
I think this only holds if enough other people believe in gold or crypto as a backup system.
If I had some extra zucchini and potatoes, and you were running very low on food, it would take quite a bit to convince me that a piece of shiny metal or numbers in a distributed ledger would be worth the calories I'm surrendering.
Right now, dollars would be worth it, because nearly everyone believes in their utility, despite being a very similar faith-based currency.
> started to think that perhaps the societal nature of crypto is a force in itself. Like religion, if enough people believe in it, it becomes reality to some extent.
This is essentially how fiat currency works, isn’t it?
That's a bit simplistic. Fiat currency "works" by being backed by a state, implying that the state will work to protect the fiat currency's value, be that through fiscally responsible governing and/or the use of force to protect its interests. For states which can not guarantee that, the currency tends to rapidly lose its purchase power.
When I mentioned the societal nature of crypto, I meant something different. People who hold crypto have a vested interest in the wider adoption of crypto, and they often tend to become vocal proponents of crypto projects. I don't even claim bad intentions – I believe there is some psychological effect at play here that causes people to hold opinions that serve their interests, and becoming a crypto holder means that from that moment on, the spread of crypto is in one's interests.
Now, my point was, that perhaps I overlooked this sociopsychological aspect of crypto. If enough people in power are personally invested in crypto, and they use their power to advance crypto adoption because it personally benefits them, then at some point it doesn't matter whether there's any intrinsic value in crypto or not – it becomes a self-reinforcing system.
My understanding is that he pushes hard in hardware department to pivot into company like Apple because without owning hardware and OS he knows that FB days are numbered. Especially when privacy will take some steam in US
That is exactly it. It's not the first time Zuckerberg went into that direction and failed.
He tried the same with the mobile market (and was ridiculously late in the game with a not-much-differentiating offering, not unlike Amazon). I guess he didn't want to make that mistake again and tried to be early in VR, which seemed the 'next big thing' for him for some reason.
Instead of trying to create some FB vertical, a better strategy would've been to let the growing VR community of those years keep stewing, while sticking to the hardware and core software side to keep the tech moving forward. We had amazing things happening for a time, and the oculus purchase has basically made VR cringe and killed pc vr at the same time.
> Maybe Mark Zuckerberg was just unlucky to decide on a company pivot two years too early -- I'm sure that if he had to decide on a direction to pivot to today, it'd be towards generative AI.
It's also important to remember that Facebook was staring down the barrel of a bunch of investigations regarding election misinformation and basically tailoring their products to be addictive to teenagers while they internally realized it was harmful. The rebrand was much more about rebranding than meaningfully changing the direction of the company. I think he just figured with ZIRP he could do the direction change as well at 0 risk.
I think there is value in creating an alternative financial system. It doesn’t have to replace your currency or be the only financial system you align yourself with, but I do believe that given the tools we currently have, locking yourself solely into a financial system you have so little visibility and control in is a little foolhardy.
>I was beginning to doubt my conclusions and started to think that perhaps the societal nature of crypto is a force in itself. Like religion, if enough people believe in it, it becomes reality to some extent. But now we see that crypto was indeed bullshit all along.
This is what Ron Paul and others have been saying about fiat currency for decades.
"What is needed is an electronic payment system based on cryptographic proof instead of trust, allowing any two willing parties to transact directly with each other without the need for a trusted third party."
Hasn't Bitcoin largely failed in these goals though? Not only is it volatile making it a poor choice of currency, but most people transact via trusted third parties for a variety of reasons. The concentration of mining in a few large entities also points to effective centralization of the protocol.
> Hasn't Bitcoin largely failed in these goals though?
No? It has been enormously successful over the last 14 years. Adoption is occurring exactly how you'd expect for a new form of digital gold/money that is outside of state control.
> Not only is it volatile making it a poor choice of currency
It's still very early in the life cycle of a new form of money. The market is still figuring out how to price it. That's not a problem inherent to Bitcoin itself. Also, the volatility is a side-effect of growth, which is a good thing if you're saving your wealth in Bitcoin. There isn't a stock or asset on Earth that has seen the type of price appreciation that Bitcoin has, that hasn't also had enormous volatility. Apple, Tesla, Amazon, you name it. You can't have price growth without volatility.
> most people transact via trusted third parties for a variety of reasons
How do you know this? Do you have a link that analyses proportion of on-chain transactions that are done through a third party and done by a peer? Not sure how you could possibly know this.
Also how could you account for off-chain transactions through the Lightning network? There's some custodial services on LN too, but plenty of people and businesses roll their own nodes, which is incredibly easy with self-hosting solutions like Umbrel, Start9, RaspiBlitz etc.
> The concentration of mining in a few large entities also points to effective centralization of the protocol.
I assume you're talking about mining pools? There's essentially zero barrier to changing pools. If a pool is found to be misbehaving people will leave the pool and they'll decimate their market share. There's no incentive for pools to fuck up like that. Pools are just an abstract grouping of hash that has no structural impact on the network's distributed nature. Bitcoin's hashrate is physically distributed all over the world, which is what matters. So no, it's not centralized.
And if it is... show me the consequences of that supposed centralization. Can you show any evidence of transaction censorship by mining operations or mining pools? If so, were the censored transactions eventually processed by other miners/pools?
Bitcoin is an open source protocol. Open, neutral, accessible to everyone, decentralised, censorship resistant etc.
Every other crypto project is a product/service created by a company or "foundation". There's a business plan (i.e. pump and dump), CEO, marketing team, PR etc.
Think of it as the difference between TCP/IP as the base layer protocol for the Internet vs. all the dot com companies/services that have come and gone over the years... except many of those dot com companies actually provided useful services to people.
Bitcoin is more akin to TCP/IP, whereas crypto is more like those dot com companies, except crypto doesn't provide anything useful to anyone, except shitcoin founders who need retail investors to pump and dump on as exit liquidity.
Bitcoin has been effectively run by a company since they bitcoin gold fork. Not even to say that's a bad thing, but the network was being guided by a company set on limiting bitcoin throughout while building the L2 lightning network to solve that problem outside the bitcoin protocol
> Bitcoin is more akin to TCP/IP, whereas crypto is more like those dot com companies, except crypto doesn't provide anything useful to anyone,
When you say crypto here do you mean cryptography, cryptocurrencies, or a subset of smart contract based projects? All currencies, whether bitcoin, shitcoins, or USD are ultimately pump and dump schemes the all meet the technical definition of a Ponzi scheme
> the network was being guided by a company set on limiting bitcoin throughout while building the L2 lightning network to solve that problem outside the bitcoin protocol
What company are you talking about exactly?
> When you say crypto here do you mean cryptography, cryptocurrencies, or a subset of smart contract based projects?
Now you're just being obtuse. I'm obviously not talking about cryptography.
> All currencies, whether bitcoin, shitcoins, or USD are ultimately pump and dump schemes the all meet the technical definition of a Ponzi scheme
Yes, money is based mostly on trust. I trust Bitcoin's monetary policy more than any other, and for good reason.
Lightning Labs. The founders were heavily involved in the debate over increasing block size that led to a hard fork. I have no idea if they honestly thought the network Das better off with a smaller block size, but after successfully fending off a block size increase they created a company to develop a lightning network implementation.
> Now you're just being obtuse. I'm obviously not talking about cryptography.
That doesn't actually answer the question. Are you referring to cryptocurrencies as a whole lot a subset of smart contract protocols?
> But now we see that crypto was indeed bullshit all along.
In case it's a surprise to you; crypto, after one of the worst bear markets, has now around $1.2 Trillion market cap.
So sure maybe it's bullshit but so is facebook and tiktok. They still make money selling BS ads and toxic content. Crypto will be an upgrade comparing to their present business model (Zuck tried to get on crypto but was discouraged by regulators).
This is a silly comment. Crypto has tons of amazing use cases which existed before the community got hijacked by grifters.
The hilarious thing is how much these use cases will fold back into AI.... how else do you expect an autonomous agent to manage its finances? Or for a global autonomous economy to emerge?
You should do yourself a service and read the original Bitcoin whitepaper. Learn about Ethereum. Learn about the drama and history surrounding the space; who the good guys and bad guys are. It's a really complex subject and I understand if you don't want to set aside the time to fully learn about it, but you do yourself a disservice by sharing an ignorant perspective of the space. At least have the courtesy in such case to recognize that your opinions are not fully informed.
The mixed messaging is pretty stunning. Pushing the metaverse, but simultaneously pushing "be at the office". Then seniors leaders spending more time on LLM projects than on the metaverse concept. All from their new remote homes rather than the office.
I think it’s getting toward that dystopian future where we are forced to Jack into the matrix only from regulated spots in the physical world.
So rather than just putting on your goggles from wherever you are and working, Meta wants you to drive into the office, sit in a tiny cubicle, put your goggles on and work there.
Hopefully it’s just stupidity and culture clash and not maliciousness.
It’s similar to an early push at my org for “return to office” that involved everyone coming in and zooming all day with people in mostly different spots. Some people like this, but for many it seemed like a waste.
I've got a friend who works for a government agency up here in BC, Canada. She's been all remote for years, but they now want her (and everyone else) in the office 2 days a week, likely going up to 3. Problem is, the office is almost a 2-hour drive, one way, from home, and she's not doing anything there that can't be done from home. Her manager (who has no power over the policy itself) thinks he has a solution though; there's a different government office in her city that she could probably work at instead, at least most of the time. She doesn't know anyone there, and there's no work done there related to her work (let alone anything she couldn't do at home), but they think it could check the "be in the office" box.
You left out getting paid (well) every two weeks and receiving options that are increasing in value as the company becomes more efficient. It’s not personal, it’s not stupidity it’s just business and there are hundreds of thousands of developers who are willing and capable of replacing any of us.
The alternative is to start your own business. If you did and generated more revenue while your employees were in the office based on previous data, I think you’d end your remote work policy for all but the people who are irreplaceable to your revenue stream.
Meta can be shitty to its employees... but tech in general (including Meta) can also still be better than other jobs.
On the other hand, the value of stability (aka "every two weeks") appears to be decreasing as it becomes apparent a lot of tech management has no strategic clothes, and the end result of that is going to be 1/3 of the company being laid off.
Or as the quip goes, 'Anyone can make money in a bull market.'
It’s not personal, it’s not stupidity it’s just business and there are hundreds of thousands of developers who are willing and capable of replacing any of us.
I agree that it's just business, and that ultimately what employees at most large companies are paid for -- is to smile, and eat boneheaded apparently blatantly hypocritical directives from upper management (in the latter sense, referring specifically to the attempt to drag mid-level employees back to the office, while top lieutenants are apparently exempt).
But I don't see why we're not allowed to call it "stupid" (or to apply even stronger words) when that's plainly what it is.
The alternative is to start your own business.
Or join a company with more manageable levels of cognitive dissonance.
> If you did and generated more revenue while your employees were in the office based on previous data, I think you’d end your remote work policy for all but the people who are irreplaceable to your revenue stream.
This is confusing "happened in overlapping time periods" with "happened because of". What if you generated less revenue during a period where TikTok was eating your lunch, Apple changed privacy controls which impacted the targeted ad landscape, your CEO was focused on VR, and also lots of people were WFH? From the stories I've heard from Meta, the issue was way more that there were a lot of strategically questionable projects than that staff were less efficient at pursuing them because of WFH.
> What if you generated less revenue during a period where TikTok was eating your lunch, Apple changed privacy controls which impacted the targeted ad landscape, your CEO was focused on VR,
The underlying commonality here is out of touch, uncreative, and inept executives. Why is TikTok eating Facebook's lunch? Because they spent their considerable engineering talent trying to squeeze ever more money out of their users via advertising than making compelling products.
Apple impacting their revenue by allowing the users, of all people, to be aware of and control data sent to third parties (Facebook). They doubled down on surveillance capitalism and when Apple simply made their collection opt-in they lost a ton of revenue. Apple didn't even block Facebook, they just made it clearer to users exactly what Facebook was collecting.
And then the CEO is off making stupid bets on VR. The Metaverse is conceptually bankrupt. Instead of letting users create environments and content from the bottom up and fully control how their virtual world and self work they created a curated top down shitty theme park.
Facebook spent years squandering their engineering talent on bullshit. Working from home has zero to do with their management failures. In fact, for a company like Facebook whose every product is tied to communication, a requirement for engineers to be in an office should be seen as the massive fucking failure of mission that it is.
If their platform was worth a fraction of what it's valued at (by Wall Street) Facebook should hardly need offices. They should be able to dog food all of their own products to communicate and collaborate with ease. Demanding everyone return to offices is a signal that either their executives either don't believe their own bullshit and/or realize their platform is actually garbage for communication and collaboration.
That is too defeatist. There isn't an unending pool of potential employees that FB wants to hire. The company is getting less efficient because they are not negotiating effectively. Remote work is a powerful bit of leverage for recruiting and retention, and FB has flushed it.
> The alternative is to start your own business. If you did and generated more revenue while your employees were in the office based on previous data, I think you’d end your remote work policy for all but the people who are irreplaceable to your revenue stream.
I think it’s simpler than this and if my goal is maximum productivity to recognize that different work modes get me there. I think some work and people combo (eg, software dev and data work) is well-suited for remote work. So I’ll actually outperform in office companies in my field by strutting my work culture to maximize this.
I’d certainly start my own org if needed. Or more likely just choose to work with others who have done the same.
> [..] there are hundreds of thousands of developers who are willing and capable of replacing any of us.
Where are all these developers and why are they available? Everyone I know is either already working for someone they like or wouldn't consider Meta anyways. My guess is that Meta will have a tough time hiring if/when they get past their current problems.
Or, you know, for employees to push back on a policy that's bad for a majority of employees rather than "look at me, I'm a rugged individual who can start my own business."
It may not be personal but these forcing people to commute to work on a virtual reality platform where they don't actually believe in remote work / virtual reality is stupid.
Seems to me if I was leading a "Metaverse" type project I'd be wanting my developers in that environment and making it good enough for "in person" collaboration so it will succeed for everyone.
(I am not a big believer in Meta or its vision for this but if someone could develop a viable platform that made remote collaboration feel more like in-person collaboration it'd be very exciting.)
This is one of the funniest things I've seen yet from the RTO movement.
It's a cubicle, but smaller! And someone could steal 1/4 of it at any time! Brilliant.
To make it doubly funny, I'd actually love a few of these panels for my home office — they look great for just mounting on the walls to quiet things down a bit. I just bought a bunch of those hexagonal acoustic panels that are marketed to Twitch streamers for the same purpose, but this thing that Meta made looks even better.
They should just brand it as a "Metaverse Pod" and sell it directly. Maybe they could probably even book the revenue under their Metaverse unit.
> It’s similar to an early push at my org for “return to office” that involved everyone coming in and zooming all day with people in mostly different spots. Some people like this, but for many it seemed like a waste.
Would have made sense in the early 2000's. Back in the days, corporate HQs had fast networking. Even lugging a machine home, doing anything over 56k would have been a pain. Now folks have dedicated fiber going straight to their router.
Heh yeah even in the mid 2000s I at one point lived directly across the street from the office. I would get calls sometimes on the weekend to the tune of "hey man can you just run in real quick and check something for me?" because it was just such a PITA to use remote tools in those days. I think the tool of that era was WinVNC IIRC, though there were slight improvements every other year or so until RDP became the defacto standard.
Also, at work you generally had much better equipment, a bigger monitor, and later multiple, etc. Nowadays the reverse may be true. I asked the office for a replacement monitor after one of mine kicked the bucket, and they sent me home a 1920x1080 monitor, which compared to my thunderbolt and 2560x1440 dell, looked like a window back in time 10 years.
> I asked the office for a replacement monitor after one of mine kicked the bucket, and they sent me home a 1920x1080 monitor
I'm fully remote and my job sent me a monitor, keyboard, and mouse along with my work laptop. The keyboard, mouse, and monitor are all garbage. They're just e-waste to me so I use the laptop stand alone.
It's 2023. Employers know developers stare at their screens all day. Giving them shitty 1080p screens is an obliviousness bordering insulting.
No defense of meta, but this doesn’t seem like a contradiction. If they thought the metaverse was done and ready to use for work, they wouldn’t need to invest in building it. Seems a bit like wondering why the construction management team doesn’t just use the office building they’re constructing rather than a trailer.
I was assuming the metaverse was an extension/improvement on doing things remotely, rather than a pre-requisite for it to work at all. Meaning you would have to believe remote is a solid concept to start with. And, there's the obvious contradiction that working remote seems fine for a lot of the senior leadership.
Zuckerburg was always a bit of a hypocrite. "Facebook's mission is to create a more open and transparent world", while simultaneously buying the 4 properties around his Palo Alto estate so that he'd have privacy from the neighbors and general public.
Seems like a pretty stretched comparison. Transparency and fairness can be applied to different topics and domains. It's like saying that If Zuckerberg really believed in transparency, he should work naked and have a public webcam in his bedroom.
I don't know that Facebook is living up to an ideal of fairness and transparency, but I don't think bad comparisons really shed any light on the topic
I personally like VR meetings but there is still too much friction versus how quick it is to start up a video call.
In my opinion larger meetings do work worse in video calls. It just isn't great having lots of small squares. But small <4 people meetings do work better when you can really see and pay attention to every clearly.
I'm sure they do dogfood but insisting every meeting is in VR is like banning the command line while working on an unfinished GUI OS.
It's also not a realistic dogfood either. Users are not going to be fully in VR so why dogfood that way? It's better to figure out what flexible and low friction workflows.
I mean - this is the obvious conclusion. Because the metaverse is a stupid idea. Nobody needs the full VR movie theatre when they can go to youtube quicker and easier.
If they received push back from dogfooding, that just means they need to knock those sharp corners off. I'd suggest what they want is a meeting application and making VR easy to put on and off, and combining the two worlds.
It's entirely realistic to dogfood here, people are just reacting to the obvious reactions from the first iteration. You don't stop there though.
About ... 10 years ago I got a recruitment offer from a company working on remote collaboration tools for software developers. it was going to 'revolutionize' what was possible. but... i had to move to SF to work in their office. they didn't even see anything wrong or odd or off about the requirement.
This description makes me think of ScreenHero, which really was an incredible leap for remote collaboration until it was eventually bought by Slack — and the thing Slack eventually came out with for screen collaboration was weak by comparison. That was a real shame.
No, I never found something that was even close to that smooth, convenient, and efficient, and geared toward screen-collaboration first.
What everyone else offers is collaboration, as an extension of screen 'showing' (virtualized projection), which itself is packaged only as an extension of a teleconference.
It’s not mixed to me. VR and mixed reality failed for work. Text is too hard to read and the headsets are too heavy for all day use. Still, VR is great for gaming though
Completely agree. I love games like Beat Saber and Half-Life: Alyx. But it doesn't work for fine text and it's very very hard to make VR presence feel like anything other than a game.
It needs to be at least 4K per eye to work well for text, IMO. Then I could see it being actually useful in a sense that you can get as many large virtual displays as you want around you for different tasks.
But that still has nothing to do with the "verse" part of the metaverse. Why would I want that, either for productivity or for entertainment?
It’s also the PPD. I believe you need something like 35, and only the consumer Varjo model even comes close. The Quest Pro is around 19 or 21. Other VR headsets are in a similar range.
Instead of pushing work, meta should be emphasizing fitness. Their headsets are no ready for work. It’s been two years now and I have yet to see infinite office. The nreal is closer to being ok for work than the quest pro
It's Brad on YouTube had a discussion with another VR tech nerd, and their conclusion was that 60ppd was retina clarity and 40ppd was the minimal to get work done. Ymmv.
I think the corporate varjo is the only one that fits the bill right now, but it's so big, I'm hoping 2025-2027 we'll have the mini OLED to have the quality and form factor needed to replace monitors
There's also mixed messaging about being at the office. They're cutting transportation programs and in-office benefits. Even reducing the variety of sodas stocked in the kitchens (you would think there isn't much cost saving there).
The major selling points of metaverse is that you can do work or play from anywhere (why else would you wear a 1500$ helmet that makes you look like a goofball). The push to "be at the office" is proof that metaverse does NOT work. It's truely ironic.
In a comment I made about 18 months ago, I noted that Facebook's insufficient investment in anything useful would hold them back. The true cost of the Metaverse isn't solely the capital needed for development; it's also the opportunity cost that will become apparent in the future. What aren't they doing that they could be?
There is also another aspect to consider. The swift expansion of generative AI is driving the transition from a Social Graph to a Content Graph. Online users are now more interested in engaging, up-to-date content rather than keeping up with their friends' activities. Platforms like TikTok and YouTube pioneered this trend, while Twitter's timeline modifications serve as a functional yet imperfect example. Content discovery now takes precedence over static friend lists.
The core principle that Facebook was built on is gradually crumbling. This isn't just about Apple's privacy policies or regulatory constraints; it's a fundamental shift in user behavior. The primary reason people visit Facebook—connecting with people they know—is now at odds with their main online activity: consuming content from strangers. Facebook has become a platform for discovering uncomfortable opinions of acquaintances and realizing the irrelevance of past social connections.
Facebook is attempting to adapt, but their efforts only diminish the platform's value for average users. Instagram's discovery page and Reels are examples, but the latter pales in comparison to TikTok. Facebook's endeavors in short-form video are likely a futile game of catch-up, a classic innovator's dilemma.
The Metaverse's introduction seemed like a desperate, last-minute attempt from the C-suite to save face. Anyone who has worked at a high-profile tech company has likely seen this tactic before: weak financial quarters lead to premature product announcements. The all-encompassing nature of the Metaverse announcement signals that something is amiss. It's only more futile now.
>The swift expansion of generative AI is driving the transition from a Social Graph to a Content Graph. . . .
The core principle that Facebook was built on is gradually crumbling.
Arguably, the proliferation of cheap generative AI content will cause the value of that “fake” content to decrease. Users may begin to value the “real” content created by one’s friends. So Meta’s social graph may become increasingly valuable in the age of AI content.
I just don't see any evidence that social graphs are becoming more relevant or even that they exist for many people onboarding on to the internet/apps for the first time. You can use Instagram, TikTok, Twitter and even Facebook now without creating any social graph at all. In fact, it seems like they prefer it that way.
People repeat ad nauseam that AI generated content is somehow of worse quality, without ever saying why. It's left as an undeniable fact.
Some point at AI generated content being "fake", which is even more of a head scratcher. What can even be considered fake in that context? As long as it's not misleading, AI or human generated content should amount to the same.
Once I'm consuming content from strangers, why would the creator matter?
Plenty of content derives its value from perceived authenticity.
Content that is made by humans that is fictitious/constructed is perceived differently from content that is considered "real" - tweets from an American pretending to be in Ukraine would be perceived differently from tweets from someone actually in the warzone. A novel written by someone reflecting such an experience can also affect how we relate to it.
There will certainly be some content where people won't care if it's AI generated or not (certain kinds of fiction, technical writing (provided the reliability issues are resolved), etc) - but a lot of content (fictional and non-fictional) derives it's value from reflecting in some way things that actually happened to actual people. Of course AI could still very much play a part in putting that content to paper, so to speak.
One Nit: I'd say that it's not just friends that will generate 'real' content, it's 'trusted' people. Some of that will be AIs and more of it will be strangers that you know produce 'good' content, but most will be friends, as you say.
So, the combination between the social graph and the content graph, with a dash of AI, will be the outcome I see coming.
> Online users are now more interested in engaging, up-to-date content rather than keeping up with their friends' activities.
You can't infer what people want to do from what they are doing when the platform is trying to influence their behavior.
Facebook has not been a good platform for keeping up with your friends in 10+ years. The main reason is that Facebook is a business that needs a business model. It's not enough to provide a useful service to the users, but you must also be able to monetize it. For FB that meant ads, and then it meant an addictive algorithmic feed to make more money.
That happens often when you run an online service as a business. First you have a good service that attracts a lot of users, and then you gradually destroy it and replace it with something similar but worse to make money. When young people started preferring other social networks, it was a clear sign that Facebook had done that.
> Facebook has become a platform for discovering uncomfortable opinions of acquaintances and realizing the irrelevance of past social connections.
At some point, the social internet started existing primarily to make people feel good about their own strongly held controversial opinions.
Why would I go on Facebook, where the experience is seeing an old friend hold some dumb half baked opinion they picked up from Fox/CNN then bicker with them, when I could go to twitter and watch the top influencer in my ring dunk on the top influencer in the competitions ring, making myself instantly feel more right?
> Online users are now more interested in engaging, up-to-date content rather than keeping up with their friends' activities. Platforms like TikTok and YouTube pioneered this trend, while Twitter's timeline modifications serve as a functional yet imperfect example.
Aren't users mostly forming parasocial relationships with "creators" and consider them friends, and want to be with those friends, regardless what they'll do?
I never understood the reaction videos and found them boring and stupid, if I wanted to have an idiot constantly pause the video and say something dumb that shows they didn't understand it, I'd watch it together with my 15yo self. But when I read discussions about it, users commented that they like it because it's something they can do "with" the content creator and they'll get signals to what their famous friend thinks about some topic etc.
I think that's fair, but it's not like it's actually a 2-way relationship. It's just some approximation of one. One that is easier to consume and requires less commitment.
It all feels like the groundwork for "AI lovers" anyway. Our desire to reshape the world in our own view and to our own desires is how this feedback loop is going to be used. We do it now in social groups that are self-reinforcing, like churches, cults, interest related groups, workplaces (one team!) etc, but I think those will all become superfluous to our desire to just feel seen, heard and entertained. In a group you have to compete to have those needs met, in the future it might be easier to just get it from a robot that understands us far better, gives us undivided attention, and only responds in ways that elicit the feelings and experiences we want.
On the commercial level at least AI-personalized interaction. You'll actually be able to have a 2-way relationship with Justin Bieber, and he'll chat with you and comment on your goofy pictures, and message you late at night when he can't sleep. Or rather when the AI has estimated that him sending you a message about not being able to sleep because he's anxious because of the album release will increase the chances of you buying that album.
What will be the term? It's no longer just parasocial. Augmented Relationship?
I believe you're spot on with regards to it being easier to get positive social interactions from a robot. I don't think that's a bad thing either. Many social dynamics are close to winner takes all, and especially among teens often work by singling out someone and mercilessly attacking them to induce group cohesion. Opting out of that hell and having a nice chat with a bot instead? That'll be an improvement for the victims at the very least. The same goes for loneliness, I'd rather people talk to robots than to not communicate at all when they have a desire to interact with others but no means to.
Negative social interactions can be pretty damaging to people.
While I cannot relate to the idea of choosing to have a relationship with a robot, I can see why a lot of people would choose to opt out of the social sphere. All the abuse it hurls at them, why bother?
> Facebook has become a platform for discovering uncomfortable opinions of acquaintances and realizing the irrelevance of past social connections
This is it. FB was actually super fun in college: it was a virtual dorm hall. It was a party. You could post crazy shit, post party pictures, and hope that girl you liked saw it.
Now it's a combination of a class reunion and your aunt's 70th birthday party, but the usual social restraint is conspicuously absent.
Meta as a company seems unable to recognize the change, because doing so would have threatened their cash cow.
> Meta as a company seems unable to recognize the change, because doing so would have threatened their cash cow.
While I agree with the rest of what you say, I don't know if this is true.
They pushed their platform to this. They pushed the controversial and divisive content. They platformed questionable advertisers. The negative interaction was more profitable than a place to share pics of your kids with friends or plan a birthday party.
I think they absolutely know but you can't unring that bell which is why they were running so hard at something else to be their primary product.
> Online users are now more interested in engaging, up-to-date content rather than keeping up with their friends' activities.
I'm still interested in keeping up with friends, but Facebook has undermined this by anti-patterns that show me more ads, more trashy content, more recommendations, and less actual content from friends. If Facebook wasn't incentivized to maximize the number of ads it showed, maybe it would be able to actually deliver on that value proposition to users.
The core principle that Facebook was built on is nearly as strong as ever , doubly so with the demographics that actually have money to burn. Facebook's core principle was to make you feel less lonely so you'd give them outrageously specific data about yourself—for free—which they would then sell to someone else who would use that information to sell you things that prey on your specific insecurities.
You can do this on TikTok with a new generation today, and Facebook is banking on being able to do this in VR tomorrow.
Tell us what makes you happy and sad. Tell us everything about you. Tell us for free and we will give you an endless stream of content/notifications/things to do that make you feel less lonely. We will then work with companies that inject ads that directly prey on your insecurities. You need these things or you can't be happy. All your friends have these things. We will reinforce this message several times per hour.
The only way for Facebook to "double down" on its core principle within its current platform is to do something like buy QVC and start to really focus on bleeding seniors. There's a lot of money to be made on Social Security Wednesdays.
1) The author seems to think 2 rounds of layoffs have already been executed and now a third is coming, when actually the 2nd round of layoffs is still being executed.
2) The author mentions twice that the coming round of layoffs will affect engineering for the first time; this is not true -- thousands of eng were laid off in the first round.
3) The author mentions that the stock price has dropped 43% from its peak as evidence that Meta faces a precarious future. No mention that META has been one of the hottest tech stocks in 23Q1, gaining more than 75%.
I'm no Meta apologist, and this is really a "dog bites man" story anyway ("layoffs announced; morale bad") but I don't really trust this author's general reporting competence.
The problem I have with articles like this is, well, sample size. They talked to 9 former and current employees, out of 60,000 employees. I'm no fan of Meta, but is it really fair to say there is a "crisis" of morale at a company with such a tiny sample size?
When I was at Facebook the same kinds of articles would pop up all the time while morale + trust in leadership was pretty high internally. It made me think a lot about how we perceive other companies and even governments from the outside versus what the reality can be.
Sounds like you've independently observed the Gell-Mann amnesia effect[1]
Media carries with it a credibility that is totally undeserved. You have all experienced this, in what I call the Murray Gell-Mann Amnesia effect. (I refer to it by this name because I once discussed it with Murray Gell-Mann, and by dropping a famous name I imply greater importance to myself, and to the effect, than it would otherwise have.)
Briefly stated, the Gell-Mann Amnesia effect is as follows. You open the newspaper to an article on some subject you know well. In Murray's case, physics. In mine, show business. You read the article and see the journalist has absolutely no understanding of either the facts or the issues. Often, the article is so wrong it actually presents the story backward—reversing cause and effect. I call these the "wet streets cause rain" stories. Paper's full of them.
In any case, you read with exasperation or amusement the multiple errors in a story, and then turn the page to national or international affairs, and read as if the rest of the newspaper was somehow more accurate about Palestine than the baloney you just read. You turn the page, and forget what you know.
That is the Gell-Mann Amnesia effect. I'd point out it does not operate in other arenas of life. In ordinary life, if somebody consistently exaggerates or lies to you, you soon discount everything they say. In court, there is the legal doctrine of falsus in uno, falsus in omnibus, which means untruthful in one part, untruthful in all. But when it comes to the media, we believe against evidence that it is probably worth our time to read other parts of the paper. When, in fact, it almost certainly isn't. The only possible explanation for our behavior is amnesia.
As a former FB employee, I have since treated everything from the NYT in particular with suspicion. That said, part of the reason I left was my belief that the VR play was a massive boondoggle.
Reading the News is like hanging with some fancy friends who are entertaining but also a little drunk and starting to repeat themselves.
It becomes apparent that the conversation always veers into some heavy and kind of dark shit that is mainly based on conjecture, and nobody is smiling or enjoying themselves.
After 20 minutes I’m not having fun anymore and I want to go home. But I’m glad I came, because they might discuss something important without me there.
Gell-Mann Amnesia is about competence. Major Media Outlet coverage of Big Tech isn't (just) incompetent, but also openly adversarial. For both financial and cultural reasons.
That said -- I interviewed with FB last month and got the distinct impression that morale was rock bottom.
One of the heads of microkitchens expressed to me how they received lots of unpleasant messages recently. I expressed my support to them and how people may not be wanting to necessarily attack them, but are frustrated at the company as an entity and in the time. I think would ask for communicating changes and avenues for feedback more actionably and precisely.
All of these changes create uncertainty and ruin morale, especially the uncertainty around multiple rounds layoffs.
I'm looking passively because the team I'm on isn't interesting in doing anything resembling professional software engineering and there aren't enough cool, fun people around.
The food is no longer good, the offices are unremarkable, and there's no real reason to go to the office because I don't know anyone, the people there aren't social people, and I don't have anything in common with them.
Yeah, Facebook is just the company that everyone loves to hate, and the NYT often joins in the chorus. This one seems especially agenda-laden, however:
> absentee leadership,
> Mr. Zuckerberg, 38, is on parental leave after the birth of his third child
> The company’s stock price has dropped 43 percent from its peak 19 months ago
This is pretty disingenuous, considering nearly all tech stocks fell off, and Meta stock has more than doubled since bottoming out at around 90/share several months ago.
The metaverse is stupid and nobody wants it!
> While the company has sold 20 million virtual reality headsets — more than any other company producing similar tech —
It's not just Meta, journalists and commenters even on tech sites like Ars Technica or Verge seem to love piling on any negative coverage about working at big tech companies (Google, Uber, even Apple occasionally).
I think Meta and Google are particularly disliked by journalists due to both specifically cutting into news industries. But I think a bigger part of it is the idea that software engineers are overpaid and spoiled brats!
Perhaps the simplest explanation is these kinds of articles get lots of clicks and views, I doubt most writers have a big agenda when starting an article like this.
> [Meta] has conducted two rounds of cuts over the past six months, eliminating more than 26,000 people, or nearly 30 percent of his company’s work force.
I thought the same thing about the sample size but if a third of the company gets chopped, you’re going to have major morale problems. It points to many, many leadership and management problems.
Even if you have access to employee survey data, what constitutes a "morale crisis" exactly?
So a variety of metrics are down after layoffs, general online negativity, and bad press. In other news, water is wet. And doubtless execs are concerned. But is that really a "morale crisis" or just what to expect in a belt-tightening era at just about any company (and certainly one whose employees expected great stock appreciation and job stability and now don't have either)?
That also jumped out at me. I think they're probably right in the sense that moral isn't great, but their methodology doesn't show that very persuasively.
Remember that this is the NYT which has a directive that tech coverage must be critical (https://news.ycombinator.com/item?id=33473275). Not that I'm implying you were dumb enough to trust the NYT in the first place.
Also important to remember that FB is a competitor to legacy media.
People look at Meta with these bizarro rose-colored glasses, as if it was once a company with some nobel mission that lost its way.
Facebook, from the very beginning, knew what it was doing once they found the "secret". They found, by accident, the ability tap into people's insecurities and exploit that to extract data and then serve ads that further insecurities. They found an emotional loop that printed dollars. People gave up an entire lifetime of information for free so they could feel connected.
The Metaverse is just trying to get lightning to strike twice. It will probably get there. As people become more isolated they will become more insecure and place an even higher value on social interaction.
VR sucks. Flat screens and fixed focal point lenses result in a huge out of focus area—you move your eyes within the headset and you can't focus—which feels unnatural. Eventually we will solve this, and once we do it will go mainstream. If you can look past the crappy optics and you log into VRChat today it feels… good. It feels like you are actually interacting with people. It simply feels good. Most people just can't look past the poor optics. You put a $2000 headset on the average person and their response is always, "Cool, but it's kinda heavy. Also, why is it so blurry?" Someone will solve this, eventually.
Meta is banking on exactly what made Facebook. They will create a space that makes you feel good, and then get you to give up even more information and see even more ads designed explicitly to manipulate you because the advertiser knows so much about you. Honestly, it's a brilliant idea to try and do the same thing again but harder. Possible it's too early, but if you have billions to blow why not. Right now it's a product that only caters to the most socially isolated individuals. That will change.
Why did my parents join Facebook? They did it because they were lonely. It's why the Facebook audience is now so old. It took them a while to come up with a UI that was easy enough for old people to use it, but they did. They are trying to do the same with VR. There's a pretty good chance of success in my opinion.
> you log into VRChat today it feels… good. It feels like you are actually interacting with people.
That's exactly it: you're actually interacting with people. In the beginning, Facebook had _only_ people: your friends. If you logged into Facebook then and had 0 friends, arguably nothing would happen.
Today, only about every 3rd post is by a person, even if you have hundreds of friends. There probably is a ratio of algorithmically-generated v.s human content that is acceptable to their users.... but I'm chasing the 100% too :)
Eventually we will solve this, and once we do it will go mainstream.
Another point of view is that VR sucks for what it is, even if all the technical glitches were resolved tomorrow and everything worked perfectly.
Why? People just don't want to zone out and spend that much time in a made-up universe. It's just not an appealing or interesting or useful experience for most folks (outside the niche universes of gaming, porn and certain teleconferencing use cases).
Meanwhile the recent past is bursting with example of technologies that not only worked, but positively exploded from the get-go -- despite offering a plainly crappy experience on basic sensory levels. Hand-held TVs, VCRs (until something infinitely better came along), the first 20 years of the internet by and large -- for example. People didn't have to look past their shortcomings because they fulfilled obvious, basic needs and desires.
It feels like you are actually interacting with people.
It's been the same with crypto, for that matter. None of the reasonable people I know ever saw any grand value in crypto. Researching myself, it always just seemed to be a bullshit fractal. At the height of the crypto boom, I was beginning to doubt my conclusions and started to think that perhaps the societal nature of crypto is a force in itself. Like religion, if enough people believe in it, it becomes reality to some extent. But now we see that crypto was indeed bullshit all along.
Contrast that with the generative AI models revolution. It's clear to anyone from day one how useful those models will be, and that they are providing clear value right away. It's no wonder that all the companies are immediately pivoting towards it. Maybe Mark Zuckerberg was just unlucky to decide on a company pivot two years too early -- I'm sure that if he had to decide on a direction to pivot to today, it'd be towards generative AI.