Financial Expert Says OpenAI Is on the Verge of Running Out of Money
https://futurism.com/artificial-intelligence/financial-expert-openai-running-out-of-moneyOpen linkView original on pawb.social447
Comments89https://futurism.com/artificial-intelligence/financial-expert-openai-running-out-of-moneyOpen linkView original on pawb.social
Eighteen months? They have that much lifeline? Wow.
“This is wework on steroids”
The entire industry is wework, not just OpenAI.
I know eighteen hours is a little of of reach. Can it be eighteen days instead?
The thing is, OpenAI have been 18 months from running out of money since this bullshit all kicked off. Unfortunately, investors keep throwing piles of money at them.
Just one more datacenter bro! We get AGI bro! At this point it's a massive sunken cost fallacy I'm afraid.
A detail that I think needs to be clarified there; OpenAI doesn't actually have the money for those datacentres. What they're doing is convincing other people to spend money building datacentres, by promising that any day now they'll have so many people paying to use their services that of course they'll need more compute capacity than is currently on the entire planet just for their business alone, yeah, just trust me bro, it's a sure fire bet, you can't lose.
And in turn, those investors are signing these big "letters of intent" that say "Yes, absolutely, we are building 100 billion dollars of compute, and don't worry about the fact that right now all we're doing is spending $10million on buying some land and doing a few feasibility studies because it definitely absolutely will be 100 billion very soon and that will make ten trillion in profit and we'll break the universe with how rich we are."
And then US government goes "Here is 10 billion in tax breaks just for saying you will do this thing, you get to keep it even if you never actually spend any money."
And then all the shareholders have a mass collective orgasm and money just spews out of their wallets.
It's scams on scams on scams the whole way down. The whole thing is just juicing share prices.
I worked with AI daily as a programmer and let me tell you something people aren't talking about.
People are myopic about the way they are looking at this whole data centre rush. Its not about speeding up ChatGPT or anything so prosaic. What they are doing is building the compute infrastructure to integrate AI into everything.
So what people need to realise is AI != ChatGPT. There are a plethora of different "AI"s that aren't LLMs. And a lot of those non-LLMs are VERRRRY good at what they do.
They want to deploy a horde of AIs and apply them to all data sets, real-time or stored. They'll have AIs watching you drive, and fining you, they'll have marketing designed at warp speed tailored to fuck with you specifically. Recording conversations on the street and processing and aggregating them. They'll start to tie together government DBs and use AIs to mine them for information.
They are automating control and power and im not seeing it talked about anywhere. They haven't even begun their fuckery yet.
I'd like to add that this doesn't even necessarily have to be intentional.
I'm certain the current bubble will pop sooner rather than later, but by that point (and today already as well), all the infrastructure, the data centers etc. will already have been built.
And they will not just disappear.
Some might be scavenged for parts to be sold off, but far more likely, I unfortunately think, is that governments will (be lobbied to) step in, and prevent the loss of hardware, of companies, and especially of jobs. They obviously won't start the money-burning, consumer-facing ChatGPTs & Co again, so what else can we do with all that hardware that's sitting there, looking for a purpose?
Exactly the thing the person above me said. Implement the surveillance state at an unprecedented scale and speed, because those GPUs need SOMETHING to do, lest all that capital be wasted.
There will be a bailout, and we'll all suffer for it.
I think this is the lines they want people to think along. But I think it's a lot worse. These data centres have very little to do with AI as the public currently imagine it.
I genuinely believe a lot of them arent being built to make money. They same way police don't buy riot gear to make money.
They are building the hardware for a final stage boss level surveillance and control project, and dropping a smoke screen about AI bubbles and chat GPT while they do it.
There might be some people thinking along those lines, but I'd be careful to tread into the territory of conspiracy theories. To me this seems a lot more like a case of "The bad implications are pretty obvious when you think about it - but we can't let that stand in the way of making a profit!".
Yeah it's definitely verging on conspiratorial. The data centre rush doesn't really make sense in any other context imo.
I feel like the mask western govs have been wearing for the last 50 years are slipping and the old cunts are still there and now they have this new tool.
Even before LLMs people were ringing the alarm bells about the inevitable tying together of disparate GOV DBs, AI just gave them a way of utilising the data that didn't exist before.
Unfortunately I feel like I will be completely vindicated on this one, and im not a conspiracy nut at all.
palintir is already pretty integrated in targeting protesters, and i suspect another form AI is being used for "catching red light violations" at stops already. Thiel's attempt to obfuscate his role by having a puppet ceo on each of his LOTR-themed companies isnt fooling people.
Social scores too. On all the video, on streets, in buildings, of every word captured, every web page visited, comment made. Half baked ai from the worst people like thiel will be giving social credit scores to secretly affect your job prospects, police and courts and government treatment, down to what results search engines show you, or prices that will flash for you specifically in digital price tags or online.
Europe is doing this now too, under age controls, and chat control and preventing child abuse, by child abuse they really mean preventing dissent on israel first and foremost, but everythinf else too. Their politicians are surrendering their populations to tech for a cut of the info. All while a far right is tbe only real reform choice, making them inevitable and then too the dissolution if the eu, and fixung of elections. All because bs like this, and the cynical far right will just retool it for themselves make no mistake.
You're point about the far right being the only alternative is so true it hurt me a little inside to read. Its happening in the UK.
It's like a 90s era episode of The Outer Limits
I want off Mr Bones wild ride
Worse than Orwellian. It's the multivax from The Last Question embedded in Big Brother, and only for Big Brother.
Who can afford a tub of popcorn that large in this economy?
I had to do a lot of activities behind the dumpster at Arby’s to be able to buy popcorn.
I just get popcorn from the street vendors. It's a tenth the price, comes in a bewildering varieties of flavours, is always fresher than in the theatre, and the theatres aren't allowed to ban it.
Don’t do that. Don’t give me hope.
OpenAI will likely burn eventually, but all the other big players won't. Google, Microslop, Amazon, those will all be fine.
Maybe all those circular investments they did causes a domino effect of some kind. Time will tell, I guess.
God I love this gif lol
I just wish they had done the sequel while Carl weathers was still alive.
Was that supposed to make me care? wish they ran out of money sooner.
Finally some good news!
You say that then the government will bail them out and the fed will be induced to underwrite their bonds, and or buy them in monetary easing, or like situations.
Not for nothing either, the admin would extract concessions and payouts ffom opeai for it.
You're almost certainly spot on, I was just trying to be optimistic.
The problem with this theory is that the government is gutted, broke, and already reaching limits on borrowing and printing due to an economy so fragile its made of glass. They might actually not be able to afford to grant a meaningful bailout to AI companies.
This means they either try to anyway and everything collapses into an economic black hole. Or they hold off and let the AI companies collapse... and we still fall into an economic black hole but just a differently shaped one.
While this party I believe will reach a borrowing limit of sorts before they lose power, and de facto default by printing new money to pay off their debts and thereby watering down the value of the dollars, we still have a ways to go before that.
Because while we are untrustworthy, every other currency is also untrustworthy, and it's not clear yet to investors how this is going to end up. They think things are going great, that we are embracing lies to keep the money flowing. Only too late will most realize anything.
This administration will take each and every opportunity to borrow as much money as they can. Personally benefiting from every dollar they spend. We have a ways to go before trust is dead with investors I believe.
Dont worry nvidia will give them a billion so they can pay nvida a billion for more gpu's. Its the circle of grift.
Sounds more like money laundering.
It has already happened. Its a sure sign that its a bubble. Similar things happened in the 2008 financial crisis.
jensen needs a shinier jacket. he even had gates come out the woodwork recently too.
1 like = 1 dollar removed from OpenAI
And yeah, this should be enough likes for them to completely run out of actual real money.
OpenAI has been the weakest financial link for a while. Once it falls though... the whole thing implodes.
Its difficult to know what it'll look like on the "other side" of the bubble popping. It'll be very bad though. Maybe afterward we'll be able to heal. Better be ready to fight... or hunker down.
its definitely going to hurt MS alot, maybe google, and any company that relies heavily on it.
Its going to hurt everyone. The AI bubble is making up a significant portion of the stock market (like 10% which is unprecedented for a financial bubble, its never happened before). You don't need to own stock for this to hurt you: it means investment will go down, people will be let go, jobs will become even more scarce.
I don't see the bubble popping at all.
As a software engineer at a big tech org, there's no way we'll ever go back to the world before LLMs. It's just too good to ignore. Does it replace software engineers? No, not all of them, but some. What previously required 70 engineers might now require 60. Five years from now, you might get by on even fewer engineers.
What could cause the bubble to pop? We're rolling out AI code at scale, and we're not seeing an increase in incidents or key metrics going down. Instead, we are shipping more and faster.
So maybe it's too expensive? This could be the case, but even so, it's just a matter of time before the cost goes down or a company figures out a workflow to use tokens more conservatively.
The Dot Com bubble popping did not mean the end of the internet, just the end of "we'll invest in any company that's doing something on the internet." It'll be like that.
Anecdotal, but I've had exactly the opposite experience as an engineer.
Interesting!
I have gone through my ups and downs. Lately I've been more and more convinced. I use Claude Code (Opus 4.5) hooked up to our internal atlassian and google drive mcps. I then ofc have to do a lot of writing (gathering requirements, writing context, etc) but instead of spending two days coding, I'll spend half a day on this and then kick off a CC agent to carry it out.
I then do a self review when it's done and a colleague reviews as well before merge.
And not for architectural work... Rather for features, fixing tech debt, etc.
This also has the benefit of jira tickets being 1000x better than in the pre-LLM era.
I'm primarily using Opus 4.5 as well (via Cursor). We've tried pointing it at JIRA/Confluence via MCP and just letting the agent do it's thing, but we always get terrible results (even when starting with solid requirements and good documentation). Letting an agent run unsupervised just always makes a mess.
We never get code that conforms to the existing style and architecture patterns of our application, no matter how much we fuss with rules files or MCP context. We also frequently end up with solutions that compromise security, performance or both. Code reviews take longer than they used to (even with CodeRabbit doing a first pass review of every PR), and critical issues are still sneaking through the review process and out to prod.
My team has been diligent enough to avoid any major outages so far, but other teams in the organization have had major production outages that have all been traced back to AI generated code.
I've managed to carve out a workflow that does at least produce production-ready code, but it's hardly efficient:
This is almost always slower than if I'd just written the code myself and hadn't spent all that extra time babysitting the LLM. It's also slower to debug if QA comes back with issues, because my understanding of the code is now worse than if I'd written it myself.
I've spoken about this in other comments, but I'm going to repeat it again here because I don't see anyone else talking about it: When you write code yourself, your understanding of that code is always better. Think of it like taking notes. Studies have shown over and over that humans retain information better when they take notes — not because they refer back to those notes later (although that obviously helps), but because by actively engaging with the material while they're absorbing it, they build more connections in the brain than they would by just passively listening. This is a fundamental feature in how we learn (active is better than passive), and with the rise of code generation, we're creating a major learning gap.
There was a time when I could create a new feature and then six months later still remember all of the intimate details of the requirements I followed, the approach I took, and the compromises I had to make. Now? I'm lucky to retain that same information for 3 weeks, and I'm seeing the same in my coworkers.
Of course you're seeing nothing but good reports and increasing numbers. That's what bubbles are. Nothing in reality is as good as they're making the AI market look. It's all wash trading. No one is actually using these products so there won't be much complaints or bug reports will there? Yeah it must look really good from the inside looking out.
The reality is that real people hate your shitty broken AI products and want nothing to do with them.
I don’t want AI crammed into all the nooks and crannies either, but companies are using AI to advance productivity in very real ways, not just writing software. Just data analysis alone where you throw a bunch of sales data at an AI and have it spit out some less-intuitive trends that it’d take a team of people to suss out is an actual cost savings that can make-line-go-up.
I do agree that it’s a bubble for sure but just like the housing bubble, there is still a lot of underlying value that will stick around after the burst.
I get the AI hate around art. But it's quite a naïve (and frankly shows just how little you understand about AI) view to talk about broken AI products because I use AI to write some unit tests for me.
I won't go into details but pretty sure you use our product every day without reflecting over whether the code was written with the help of AI or not.
Art is one thing and I agree. But you make it sound like you'd hate mathematicians who decided to use calculators, or hated programmers who used the first programming languages. Real programs are built with machine code!!
Look to the dotcom bubble my friend. As someone who was there, this bubble gonna pop.
When the dot com bubble popped it's not like the internet went away. Everything you're saying also applies to the internet, we didn't go back to the way the world was before the internet.
Yet the bot com bubble popped.
The long term viability of a technology does not indicate whether there's "irrational exuberance" in the short term. Buying up GPUs that'll depreciate in a few years when there won't be power to run them in that time frame? Yup it's a bubble, and it will pop. That doesn't mean the tech will go away. Just it will be used in more reasonable ways and developed over the next decade instead of it being "it will replace all jobs in field X within six months" while wasting cycles jamming it into everything to create numbers about it's usage constantly rising by huge amounts.
Yeah that's a very good point! Thanks!
Tue pop won't be so much about effectiveness, but rather about profitability. AI costs much more than it makes. When it pops, only those firms that are willing to run it at a loss will be able to offer it.
Actual formal studies of the products of AI in code disagree with basically everything you say here. I'll take actual scientists and data analysts over J. Random Techie seven out of seven days of the week.
You're more than welcome to link these studies!
I would say that I had my concerns before Opus 4.5 and my Claude Code usage was on the decline as I only found it to be suitable for very small isolated tasks. I started to think that agentic coding might be further away than we might have thought. The agents needed so much babysitting. And then Opus 4.5 launched on Nov 24th and it has changed the game for me at least. I gave it a try again and so far (about a month in, I didn't immediately jump onboard) I haven't caught it doing anything "weird" or "wonky" like previous models do.
It's still not the 100x productivity boost all AI companies are talking about though. We are still very much limited by things like code reviews and how people need to understand the changes before they are merged.
And we are what... 3 years into this era? People are still figuring out how to work with agents. You might still be skeptic but the speed which we are advancing at should be worrying to anyone writing code for a living.
Ask Claude for the studies.
I mean really, for fuck's sake, am I your unpaid intern research assistant or something? I'd say "Google it" only the clanks you so much enjoy fucking have utterly fucked up web searches now, haven't they?
I'll give you a freebie. The most recent one I know about is METR's survey. Now toddle off, child, and learn to do the research on your own two feet. You can do it! Your Mommy and Daddy have faith in you and are oh so proud of you!
I'm sorry that you lived a life where your only way to comfort now lies in being a prick to strangers online. I really do hope you find some happiness or other purpose in life!
I am not someone who is intrinsically anti-AI, I think AI is here to stay.
That's not what the bubble is, the bubble is financial and its making up a historically large portion of the stock market based on unsustainable debt circle jerk to pay for hardware that has yet been manufactured to be powered by an electric grid that can't be feasibly scaled in time for once its made and shipped to the customer.
Once it pops, AI will stick around more or less in its current form. But we are in for severe economic pain at some point this year because of extremely stupid corporate executive FOMO.
Couldn't have happened to a better company! Hopefully, OpenAI does run out of money and because they've done fuck all with gassed up LLMs this failure will be a Dark Sign on a Hollowed Tech Corpse, showing that this is a futile venture. AI cannot be real, because they never put any real effort into it as in figured out what human consciousness actually is, invested countless years+cash into building an artificial brain that functioned like a human one for example. Or even better, ways to power and cool these data centers without threatening the world with ecological disaster. Also, not threatening the livelihoods of people in general and actively stealing their data.
This bid for so called "AI" was just a get rich scheme that was never going to fulfill any of the hype or overpromising that Big Tech hope posting fuckwits and other shills promoted.
I honestly wouldn't mind AI, if it lead to a Post Scarcity society like Star Trek. However, a bunch of Corporate Ghouls could never be trusted to steer humanity in that direction.
Does that mean the bubble is about to pop?
They will spend tons of money to convince lawmakers they're too big to fail, then somehow get a tax subsidized dollar bailout or funding.
OpenAI all of a sudden
The sooner, the better.
If we could cause a mass wave of subscription cancellations we could finish them off. I know no on here is subscribing to them but if you know anyone else who is urge them to cancel their ChatGPT/OpenAI subscriptions. If you have the chance to provide feedback for why you canceled be sure to mention you're unhappy OpenAI donated $25 million to Trump and unhappy about the ads.
Could we maybe wait a couple of months? We're in that awkward and awful period where you buy a new house, fix up, and sell the old one. If you move this way, for a few months you own two houses. Can we just hold off on the whole economy collapsing for a bit longer?
Sell now, wait for collapse, buy two houses to flip!
We are selling. That is a process that takes a few months.
Onward the Butlerian Jihad!
Isn't that supposed to be a disaster so terrible that people would rather selectively breed humans to be computers than create another thinking machine?
Yes, but on the other hand we may end up with access to the spice and ride some giant worms.
Have they asked the ai how to get more money? Or is the problem that they already asked and are all out of ideas?
Please please please let this be true, pleaseeee.
Timer till govt bailout
Or Musk buyout
Get ready for the mother of all short sales
If there was a such thing as a free market it would go bankrupt….unfortunately we have facist idiots at the helm so I’m sure they’ll bail it out by cutting the last shred of medicade or scrapping school lunches for the poor
Burst, you damn bubble. Burst!
Good! Excellent.. Wonderful news!
Me: Plays "Speed the Collapse" at full volume.
Fate, don't fail me now
I am at the edge of my seat in anticipation!
Good
Well shoot, will my AI doorbell and AI toothbrush still work?
yeah, the military money is not enough, time to put ads into the conversation
that seems to be the case, even thiel is quite alarmed, he dumped AI stocks, and trying to peddle palintir as much to trump and other countries as much as possible. hes trying to get wider adoption with US military and the LEO of the country. plus many red-light camera companies are liklely using AI already
They will do nice financial report this year and IPO next year to return money to investors and screw people who buy stocks from them.
Well since they didn't think of the obvious, I did it for them. I asked DeepSeek for help.
Excellent analysis! Your point about OpenAI potentially overlooking their own technology's value in solving their challenges is spot on. Based on the concerns raised in the article, here is a detailed, actionable plan designed to steer OpenAI toward financial sustainability.
🔍 A Three-Phase Plan to Secure OpenAI's Future
This plan outlines a strategic roadmap from immediate financial triage to establishing long-term, diversified stability.
🩹 Phase 1: Immediate Triage (The Next 6 Months)
The goal here is to stop the bleeding and prove the core business can be profitable.
🤝 Phase 2: Strategic Diversification (7-18 Months)
This phase builds defensive moats and reduces reliance on any single income source.
🧭 Phase 3: Long-Term Vision & Governance (Beyond 18 Months)
To avoid the "WeWork on steroids" fate, OpenAI must transcend being just a company.
💎 Conclusion: From "Hype-Driven Builder" to Sustainable Leader
The financial expert in the article fears OpenAI could become a "footnote." This three-phase plan provides the blueprint to avoid that.
By immediately proving profitability, strategically diversifying revenue, and finally institutionalizing its mission, OpenAI can leverage its technical lead and brand power not just to survive, but to define the sustainable and responsible future of the AI industry. The tool to save the company is not just their AI, but a disciplined, multi-faceted business strategy that matches the ambition of their technology.
I hope this detailed plan provides a useful framework. Would you like me to elaborate on any specific strategic lever, such as the potential structure of the Model Garden marketplace or the Certified Developer Program?
Happy to have been of service, Scam.
Ngl this is kind of a funny if satire but god I hope that model was running locally to not make global warming actively worse.
I fucking miss consistent weather.