(My apologies if this was already asked - this thread is huge and Find-In-Page-ing for variations of "pre-train", "pretrain", and "train" turned up nothing about this. If this was already asked I'd super-appreciate a pointer to the discussion :) )
Genuine question: How is it possible for OpenAI to NOT successfully pre-train a model?
I understand it's very difficult, but they've already successfully done this and they have a ton of incredibly skilled and knowledgeable, well-paid and highly knowledgeable employees.
I get that there's some randomness involved but it seems like they should be able to (at a minimum) just re-run the pre-training from 2024, yes?
Maybe the process is more ad-hoc (and less reproducible?) than I'm assuming? Is the newer data causing problems for the process that worked in 2024?
Any thoughts or ideas are appreciated, and apologies again if this was asked already!
I’m not sure what ‘successfully’ means in this context. If it means training a model that is noticeably better than previous models, it’s not hard to see how that is challenging.
You don't train the next model by starting with the previous one.
A company's ML researchers are constantly improving model architecture. When it's time to train the next model, the "best" architecture is totally different from the last one. So you have to train from scratch (mostly... you can keep some small stuff like the embeddings).
The implication here is that they screwed up bigly on the model architecture, and the end result was significantly worse than the mid-2024 model, so they didn't deploy it.
I've seen a rumor going around that OpenAI hasn't had a successful pre-training run since mid 2024. This seemed insane to me but if you give ChatGPT 5.1 a query about current events and instruct it not to use the internet it will tell you its knowledge cutoff is June 2024. Not sure if maybe that's just the smaller model or what. But I don't think it's a good sign to get that from any frontier model today, that's 18 months ago.
Every so often I try out a GPT model for coding again, and manage to get tricked by the very sparse conversation style into thinking it's great for a couple of days (when it says nothing and then finishes producing code with a 'I did x, y and z' with no stupid 'you're absolutely' right sucking up and it works, it feels very good).
But I always realize it's just smoke and mirrors - the actual quality of the code and the failure modes and stuff are just so much worse than claude and gemini.
I am a novice programmer -- I have programmed for 35+ years now but I build and lose the skills moving between coder to manager to sales -- multiple times. Fresh IC since last week again :) I have coded starting with Fortran, RPG and COBOL and I have also coded Java and Scala. I know modern architecture but haven't done enough grunt work to make it work or to debug (and fix) a complex problem. Needless to say sometimes my eyes glaze over the code.
And I write some code for my personal enjoyment, and I gave it to Claude 6-8 months back for improvement, it gave me a massive change log and it was quite risky so abandoned it.
I tried this again with Gemini last week, I was more prepared and asked it to improve class by class, and for whatever reasons I got better answers -- changed code, with explanations, and when I asked it to split the refactor in smaller steps, it did so. Was a joy working on this over the thanksgiving holidays. It could break the changes in small pieces, talk through them as I evolved concepts learned previously, took my feedback and prioritization, and also gave me nuanced explanation of the business objectives I was trying to achieve.
This is not to downplay claude, that is just the sequence of events narration. So while it may or may not work well for experienced programmers, it is such a helpful tool for people who know the domain or the concepts (or both) and struggle with details, since the tool can iron out a lot of details for you.
My goal now is to have another project for winter holidays and then think through 4-6 hour AI assisted refactors over the weekends. Do note that this is a project of personal interest so not spending weekends for the big man.
I was just giving my history :) but yes I am sure this could actually get us out of the COBOL lock-in which requires 70 years old programmers to continue working.
I'm starting with Claude at work but did have an okay experience with OpenAi so far. For clearly delimited tasks it does produce working code more often than not. I've seen some improvement on their side compared to say, last year. For something more complex and not clearly defined in advance, yes, it does produce plausible garbage and it goes off the rails a lot. I was migrating a project and asked ChatGPT to analyze the original code base and produce a migration plan. The result seemed good and encouraging because I didn't know much about that project at that time. But I ended up taking a different route and when I finished the migration (with bits of help from ChatGPT) I looked at the original migration plan out of curiosity since I had become more familiar with the project by now. And the migration plan was an absolutely useless and senseless hallucination.
On the contrary, I cannot use the top Gemini and Claude models because their outputs are so out place and hard to integrate with my code bases. The GPT 5 models integrate with my code base's existing patterns seamlessly.
How can you stand the excruciating slowness? Claude Code is running circles around codex. The most mundane tasks make it think for a minute before doing anything.
Well you can’t edit files while Xcode is building or the compiler will throw up, so I‘m wondering what you mean here. You can’t even run swift test in 2 agents at the same time, because swift serializes access for some reason.
Whenever I have more than 1 agent run Swift tests in a loop to fix things, and another one to build something, the latter will disturb the former and I need to cancel.
And then there’s a lot of work that can’t be parallelized, like complex git rebases - well you can do other things in a worktree, but good luck merging that after you‘ve changed everything in the repo. Codex is really really bad at git.
Completely failed for me running the code it changed in a docker container i keep running. Claude did it flawlessly.
It absolutely rocks at code reviews but ir‘s terrible in comparison generating code
Could you clarify what you mean by design questions? I do agree that GPT5 tends to have a better agentic dispatch style for math questions but I've found it has really struggled with data model design.
I noticed this recently when I asked it whether I should play Indiana Jones on my PS5 or PC with a 9070 XT. It assumed I had made a typo until I clarified, then it went off to the internet and came back telling me what a sick rig I have.
I asked ChatGPT 5.1 to help me solve a silly installation issue with the codex command line tool (I’m not an npm user and the recommended installation method is some kludge using npm), and ChatGPT told me, with a straight face, that codex was discontinued and that I must have meant the “openai” command.
I recall reading that Google had similar 'delay' issues when crawling the web in 2000 and early 2001, but they managed to survive. That said, OpenAI seems much less differentiated (now) than Google was back then, so this may be a much riskier situation.
Funny, had it tell me the same thing twice yesterday and that was _with_ thinking + search enabled on the request (it apparently refused to carry out the search, which it does once in every blue moon).
I didn't make this connection that the training data is that old, but that would indeed augur poorly.
Pre-training is just training, it got the name because most models have a post-training stage so to differentiate people call it pre-training.
Pre-training: You train on a vast amount of data, as varied and high quality as possible, this will determine the distribution the model can operate with, so LLMs are usually trained on a curated dataset of the whole internet, the output of the pre-training is usually called the base model.
Post-training: You narrow down the task by training on the specific model needs you want. You can do this through several ways:
- Supervised Finetuning (SFT): Training on a strict high quality dataset of the task you want. For example if you wanted a summarization model, you'd finetune the model on high quality text->summary pairs and the model would be able to summarize much better than the base model.
- Reinforcement Learning (RL): You train a separate model that ranks outputs, then use it to rate the output of the model, then use that data to train the model.
- Direct Preference Optimizaton (DPO): You have pairs of good/bad generations and use them to align the model towards/away the kinds of responses you want.
Post-training is what makes the models able to be easily used, the most common is instruction tuning that teaches to model to talk in turns, but post-training can be used for anything. E.g. if you want a translation model that always translates a certain way, or a model that knows how to use tools, etc. you'd achieve all that through post-training. Post-training is where most of the secret sauce in current models is nowadays.
The first step in building a large language model. That's when the model is initiated and trained on a huge dataset to learn patterns and whatnot. The "P" in "GPT" stands for "pre-trained."
The fundamental problem with bubbles like this, is that you get people like this who are able to take advantage of the The Gell-Mann amnesia effect, except the details that they’re wrong about are so niche that there’s a vanishingly small group of people who are qualified to call them out on it, and there’s simultaneously so much more attention on what they say because investors and speculators are so desperate and anxious for new information.
I followed him on Twitter. He said some very interesting things, I thought. Then he started talking about the niche of ML/AI I work near, and he was completely wrong about it. I became enlightened.
OpenAI is basically just Netscape at this point. An innovative product with no means of significant revenue generation.
One one side it's up against large competitors with an already established user base and product line that can simply bundle their AI offerings into those products. Google will do just what Microsoft did with Internet Explorer and bundle Gemini in for 'Free' with their already other profitable products and established ad-funded revenue streams.
At the same time, Deepseek/Qwen, etc. are open sourcing stuff to undercut them on the other side. It's a classic squeeze on their already fairly dubious business model.
It's a fun trope to repeat but that's not what OpenAI is doing. I get a ton of value from ChatGPT and Codex from my subscription. As long as the inference is not done at a lost this analogy doesn't hold. They're not paying me to use it. They are generating output that is very valuable to me. Much more than my subscription cost.
I've been able to help setup cross app automation for my partner's business, remodel my house, plan a trip of Japan and assist with the cultural barrier, vibe code apps, technical support and so much more.
To be fair, I would get a ton of value out of someone selling dollars for 20 cents apiece.
But ya, OAI is clearly making a ton of revenue. That doesn't mean it's a good business, though. Giving them a 20 year horizon, shareholders will be very upset unless the firm can deliver about a trillion in profit, not revenue, to justify the 100B (so far) in investment, and that would barely beat the long term s&p 500 average return.
But Altman himself has said he'll need much more investment in the coming years. And even if OAI became profitable by jacking up prices and flooding gpt with ads, the underlying technology is so commodified, they'd never be able to achieve a high margin, assuming they can turn a profit at all.
I think there's something off with their plans right now: it's pretty clear at this point that they can't own the technological frontier, Google is just too close already and from a purely technological PoV they are much better suited to have the best tech in the medium term. (There's no moat and Google has way more data and compute available, and also tons of cash to burn without depending on external funding).
But ChatGPT is an insane brand and for most (free) customers I don't think model capabilities (aka “intelligence”) are that important. So if they stopped training frontier models right now and focus on driving their costs low by optimizing their inference compute budget while serving ads, they can make a lot of money from their user base.
But that would probably mean losing most of its paying customers over the long run (companies won't be buying mediocre token at a premium for long) and more importantly it would require abandoning the AGI bullshit narrative, which I'm not sure Altman is willing to do. (And even if he was, how to do that without collapsing from lack of liquidity due to investors feeling betrayed is an open question).
The best way to drive inference cost down right now is to use TPUs. Either that or invest tons of additional money and manpower into silicon design like Google did, but they already have a 10 year lead there.
This. Netscape was THE browser in the early phases of the Internet. Then Microsoft just packaged IE into Windows and it was game over. The brand means nothing long term. If Google broadly incorporates Gemini into all the Google-owned things everyone already has then it’s game over for OpenAI.
The mass commission of the tech is rapidly driving AI to be a feature, not a product. And Google is very strongly positioned to take advantage of that. Microsoft too, and of course they have a relationship with OpenAI but that’s fraying.
Good question. Salesforce does well because they provide the application layer to the data.
The WWW in the 1990s was an explosion of data. To the casual observer, the web-browser appeared to be the internet. But it wasn't and in itself could never make money (See Netscape). The internet was the data.
The people who build the infrastructure for the WWW (Worldcom, Nortel, Cisco, etc.) found the whole enterprise to be an extremely loss-making activity. Many of them failed.
Google succeeded because it provided an application layer of search that helped people to navigate the WWW and ultimately helped people make sense of it. It helped people to connect with businesses. Selling subtle advertising along the way is what made them successful.
Facebook did the same with social media. It allowed people to connect with other people and monetized that.
Over time, as they became more dominant, the advertising got less subtle and then the income really started to flow.
There's no doubt you're getting a lot of value from OpenAI, I am too. And yes the subscription is a lot more value than what you pay for. That's because they're burning investor's money and it's not something that is sustainable. Once the money runs out they'll have to jack up prices and that's the moment of truth, we'll see what users are willing to pay for what. Google or another company may be able to provide all that much cheaper.
As a developer - ChatGPT doesn't hold a candle compared to claude for coding related tasks and under performs for arbitrary format document parsing[1]. It still has value and can handle a lot of tasks that would amaze someone in 2020 - but it is simply falling behind and spending much more doing so.
1. It actually under performs Claude, Gemini and even some of the Grok models for accuracy with our use case of parsing PDFs and other rather arbitrarily formatted files.
That the product is useful does not mean the supplier of the product has a good business; and of course, vice versa. OpenAI has a terrible business at the moment, and the question is, do they have a plausible path to a good one?
If making money on inference alone was possible, there would be a dozen different smaller providers who'd be taking the open weights models and offering that as service. But it seems that every provider is anchored at $20/month, so you can bet that none of them can go any lower.
> If making money on inference alone was possible, there would be a dozen different smaller providers who'd be taking the open weights models and offering that as service.
There are! Look through the provider list for some open model on https://openrouter.ai . For instance, DeepSeek 3.1 has a dozen providers. It would not make any sense to offer those below cost because you have neither moat nor branding.
Maybe, but arguably a major reason you can't make money on inference right now is that the useful life of models is too short, so you can't amortize the development costs across much time because there is so much investment in the field that everyone is developing new models (shortening useful life in a competitive market) and everyone is simultaneously driving up the costs of inputs needed for developing models (increasing the costs that have to be amortized over the short useful life). Perversely, the AI bubble popping and resolving those issues may make profitability much easier for the survivors that have strong revenue streams.
>. As long as the inference is not done at a lost this analogy doesn't hold.
I think that there were some article here that claimed that even inference is done at loss - and talking about per subscriber. I think it was for their 200$ subscription.
In a way we will be in a deal with it situation soon where they will just impose metered models and not subscription.
This analogy only really works for companies whose gross margin is negative, which as far as I know isn’t the case for OpenAI (though I could be wrong).
It’s an especially good analogy if there is no plausible path to positive gross margin (e.g. the old MoviePass) which I think is even less likely to be true for OpenAI.
very clever! I hadn't seen anybody make this point before in any of these threads /s
obviously the nature of OpenAIs revenue is very different than selling $1 for $0.2 because their customers are buying an actual service, not anything with resale value or obviously fungible for $
FWIW the selling $1 for $0.2 is widely applied to any business that is selling goods below cost.
For example: free shipping at Amazon does not have resale value and is not obviously fungible, but everyone understands they are eating a cost that otherwise would be borne by their customers. The suggestion is that OpenAI is doing similar, though it is harder to tease out because their books are opaque.
People need to understand that OpenAI is not a publicly traded company. Sam is allowed to be outrageously optimistic about his best case scenarios, as long as he is correct with OpenAI's investors. But those investors are not "the public", so he can publicly state pretty much anything he wants, as long as it is not contradicting facts.
So he cannot say "OpenAI made 20B profit last year." but can say "OpenAI will make 20B revenue next year." Optimism is not a crime.
Kind of, but there are limits. The investors still have LPs who aren’t going to be happy if things get messy. Things can still get really ugly even for a private company.
That ship has sailed. CNBC talks about the AI bubble and over-valuation every day. Retail investors won’t touch OpenAI. It’s increasingly looking like these LPs will be left holding the bag when the music stops.
In 2024, OpenAI claimed the bulk of its revenue was 70-80% through consumer ChatGPT subscriptions. That's wildly impressive.
But now they've had an order of magnitude revenue growth. That can't still be consumer subscriptions, right? They've had to have saturated that?
I haven't seen reports of the revenue breakdown, but I imagine it must be enterprise sales.
If it's enterprise sales, I'd imagine that was sold to F500 companies in bulk during peak AI hype. Most of those integrations are probably of the "the CEO has tasked us with `implementing an AI strategy`" kind. If so, I can't imagine they will survive in the face of a recession or economic downturn. To be frank, most of those projects probably won't pan out even under the rosiest of economic pictures.
We just don't know how to apply AI to most enterprise automation tasks yet. We have a long way to go.
I'd be very curious to see what their revenue spread looks like today, because that will be indicative of future growth and the health of the company.
I'm reading 5% on a quick search. Isn't that an unsurprising conversion rate for a successful app with a free tier? Why would it increase further in ChatGPT's case, other than by losing non-paying customers?
This is pretty much all that OpenAI is at the moment.
Mozilla is a non-profit that is only sustained by the generous wealthy benefactor (Google) to give the illusion that there is competition in the browser market.
OpenAI is a non-profit funded by a generous wealthy benefactor (Microsoft).
Ideas of IPO and profitability are all just pipe dreams in Altmans imagination.
> Mozilla is a non-profit that is only sustained by the generous wealthy benefactor (Google) to give the illusion that there is competition in the browser market.
Good way of phrasing things. Kinda sad to read this, I tried to react with 'wait there is competition in the browser market', but it is not a great argument to make - without money for using Google as a default search engine, Mozilla would effectively collapse.
> Google will do just what Microsoft did with Internet Explorer and bundle Gemini in for 'Free' with their already other profitable products and established ad-funded revenue streams.
“will do”? Is there any Google product they haven't done that with already?
anecdotal, but my wife wasn't interested in switching to claude from chatgpt. as far as she's concerned chatgpt knows her, and she's got her assistant perfectly tuned to her liking.
ChatGPT is to AI as Facebook is to social media. OpenAI captured a significant number of users due to first-mover advantage, but that advantage is long gone now.
And Facebook only makes money because it is essentially just an advertising platform. Same with Google. It's fundametally just ads.
The only way OpenAI can survive is to replicate this model. But it probably doesn't have the traffic to pull it off unless it can differentiate itself from the already crowded competition.
I know it's been said before but it's slightly insane they're trying to compete on a hot new tech with a company with 1) a top notch reputation for AI and 2) the largest money printer that has ever existed on the planet.
Feel like the end result would always be that while Google is slow to adjust, once they're in the race they're in it it.
The problem for Google is that there is no sensible way to monetize this tech and it undercuts their main money source which is search.
On top of that the Chinese seem to be hellbent to destroy any possible moat the US companies might create by flooding the market with SOTA open-source models.
Although this tech might be good for software companies in general - it does reduce the main cost they have which is personnel. But in the long run Google will need to reinvent itself or die.
Well maybe not in 1999. Adwords didn't launch until 2000? Google's 1999 revenue was...... I forget, but it was incredibly small. Costs were also incredibly small too though, so this isn't a good analogy given the stated year of 1999.
Google in 1999 was already far superior to Yahoo and other competitors. I don't think OpenAI is in a similar position there. It seems debatable as to whether they're even the best, let alone a massive leap ahead of everyone else the way Google was.
It is insignificant when they're spending more than $115bn to offer their service. And yes, I say "more than," not because I have any inside knowledge but because I'm pretty sure $115bn is a "kind" estimate and the expenditure is probably higher. But either way, they're running at a loss. And for a company like them, that loss is huge. Google could take the loss as could Microsoft or Amazon because they have lots of other revenue sources. OAI does not.
Google is embedding Gemini into Chrome Developer Tools. You can ask for an analysis of individual network calls in your browser by clicking a checkbox. That's just an example of the power of platform. They seem to be better at integration than Microsoft.
OpenAI has this amazing technology and a great app, but the company feels like some sort of financial engineering nightmare.
We live in crazy times, but given what they’ve spent and committed to that’s a drop in the bucket relative to what they need to be pulling in. They’re history if they can’t pump up the revenue much much faster.
Given that we’re likely at peak AI hype at the moment they’re not well positioned at all to survive the coming “trough of disillusionment” that happens like clockwork on every hype cycle. Google, by comparison, is very well positioned to weather a coming storm.
That's a good point. Google was sleeping on AI and wasn't able to come up with a product before OpenAI and they only scrambled to come out with something when OpenAi became all the rage. Big companies are hard to budge and move in a new direction.
Google and Microsoft have existing major money printing businesses to keep their AI business afloat and burn money for a while. That's how Microsoft broke into gaming (and then squandered it years later for unrelated incompetence)
Every F500 CEO told their team "have an AI strategy ASAP".
In a year, when the economy might be in worse shape, they'll ask their team if the AI thing is working out.
What do you think happens to all the enterprise OpenAI contracts at that point? (Especially if the same tech layperson CEOs keep reading Forbes and hearing Scott Galloway dump on OpenAI and call the AI thing a "bubble"?)
It’s really even easier than that. I already do all my work on AWS and use Bedrock that hosts every popular model and its own except for OpenAIs closed source models.
I have a reusable library that lets me choose between any of the models I choose to support or any new model in the same family that uses the same request format.
Every project I’ve done, it’s a simple matter of changing a config setting and choosing a different model.
If the model provider goes out of business, it’s not like the model is going to disappear from AWS the next day.
Given a choice between being “locked in” to a major cloud provider and trusting your business to a randomish little company, you are never going to get a compliance department to go for the latter. “no one ever got fired for choosing AWS”.
This is the API - it’s basically the same for all supported languages
Real companies aren’t concerned about cost as much as working with other real companies, compliance, etc and are comparing cost or opportunities between doing a thing and not doing a thing.
One of my specialties is call centers. Every call deflected by using AI vs talking to a human agent can save from $5 - $15.
Even saving money by allowing your cheaper human agents to handle a problem where they are using AI in the background, can save money. $15 saved can buy a lot of inference.
And the lock in boogeyman is something only geeks care about. Migrations from one provider to another costs so much money at even a medium scale they are hardly ever worth it between the costs, distractions from doing value added work, and risks of regressions and downtime.
on less vendor to vet, one less contract to negotiate, one less 3rd party system to administer. you're already locked into AWS anyway. integrates with other AWS services. access control is already figured out.
Oh God I love the analogy of OpenAI being Netscape. As someone who was an adult in the 1990s, this is so apt. Companies at that time were trying to build a moat around the World Wide Web. They obviously failed. I've thought that OpenAI too would fail but I've never thought about it like Netscape and WWW.
OpenAI should be looking at how Google built a moat around search. Anyone can write a Web crawler. Lots of people have. But no one else has turned search into the money printing machine that Google has. And they've used that to fund their search advantage.
I've long thought the moat-buster here will be China because they simply won't want the US to own this future. It's a national security issue. I see things like DeepSeek is moat-busting activity and I expect that to intensify.
Currently China can't buy the latest NVidia chips or ASML lithography equipment. Why? Because the US said so. I don't expect China to tolerate this long term and of any country, China has desmonstrated the long-term commitment to this kind of project.
> Google will do just what Microsoft did with Internet Explorer and bundle Gemini in for 'Free' with their already other profitable products and established ad-funded revenue streams.
Just some numbers to show what OpenAI is against:
GMail users: nearing 2 billion
Youtube MAU: 2.5 billion
active Android devices: 4 billion (!)
Market cap: 3.8 trillion (at a P/E of 31)
So on one side you've got this behemoth with, compared to OpenAI's size, unlimited funding. The $25 bn per year OpenAI is after is basically a parking ticket for Google (only slightly exaggerating). Behemoth who came with Gemini 3 Pro "thinking" and Nano Banana (that name though) who are SOTA.
And on the other side you've got the open-source weights you mentioned.
When OpenAI had its big moment HN was full of comments about how it was game over for Google for search was done for. Three years later and the best (arguably the best) model gives the best answer when you search... Using Google search.
Funny how these things turns out.
Google is atm the 3rd biggest cap in the world: only Apple and NVidia are slightly ahead. If Google is serious about its AI chips (and it looks like they are) and see the fuck-ups over fuck-ups by Apple, I wouldn't be surprised at all if Alphabet was to regain the number one spot.
That's the company OpenAI is fighting: a company that's already been the biggest cap in the entire world and that's probably going to regain that spot rather sooner than later and that happens to have crushed every single AI benchmark when Gemini 3 Pro came out.
I had a ChatGPT subscription. Now I'm using Gemini 3 Pro.
The way I've experienced "Code Red" is mostly as a euphemism for "on-going company-wide lack of focus" and a band-aid for mid-level management having absolutely no clue how to meaningfully make progress, upper management panicking, and ultimately putting engineers and ICs on the spot to bear the brunt of that organizational mess.
Interestingly enough, apart from Google, I've never seen an organization take the actual proper steps (fire mid-management and PMs) to prevent the same thing from happening again. Will be interesting to see how OAI handles this.
>I've never seen an organization take the actual proper steps (fire mid-management and PMs) to prevent the same thing from happening again.
One time, in my entire career have I seen this done, and it is as successful as you imagine it to be. Lots of weird problems coming out from having done it, but those are being treated as "Wow we are so glad we know about this problem" rather than "I hope those idiots come back to keep pulling the wool over my eyes".
> fire mid-management and PMs to prevent the same thing from happening again
Firing PMs and mid-management would not prevent any of code reds you may have read about from Google or OAI lately. This is a very naive perspective of how decision making is done at the scale of those two companies. I'm sorry you had bad experiences working with people in those positions and I wish you have the opportunity to collab with great ones in the future.
There should already be a single priority for a company...
Why is the bar so low for the billionaire magnate fuck ups? Might as well implement workplace democracy and be done with it, it can't be any worse for the company and at least the workers understand what needs to be done.
This code red also has the convenient benefit of giving an excuse to stop work on more monetization features... Which, when implemented, would have the downside of tethering OpenAI's valuation to reality.
They have some monetization, but as long as they don't expand into other sectors, they can plausibly claim that, say, their ad business will be bringing in 10 trillion/year in revenue, or whatever other imagined number.
Your proper steps are also missing out on firing the higher level executives. But then new ones would be hired, a re-org will occur, and another Code Red will occur in a few months
OpenAI has already lined up enormous long-term commitments — over $500 billion through initiatives like Stargate for U.S. data centers, $250 billion in spending on Microsoft Azure cloud services, and tens of billions on AMD’s plan to deliver 6 GW of Instinct GPUs.
Meanwhile, Oracle has financed its role in Stargate with at least $18 billion in corporate bonds plus another $9.6 billion in bank loans, and analysts expect its total capital need for these AI data centers could climb toward $100 billion.
The risk is straightforward: if OpenAI falls behind or can’t generate enough revenue to support these commitments, it would struggle to honor its long-term agreements. That failure would cascade. Oracle, for example, could be left with massive liabilities and no matching revenue stream, putting pressure on its ability to service the debt it already issued.
Given the scale and systemic importance of these projects — touching energy grids, semiconductor supply chains, and national competitiveness — it’s not hard to imagine a future where government intervention becomes necessary. Even though Altman insists he won’t seek a bailout, the incentives may shift if the alternative is a multi-company failure with national-security implications.
OpenAI doesn't have $500 billion in commitments lined up, it's promising to spend that much over 5 years... That's a helluva big difference than having $500B in revenue incoming.
Data centers take time to build. The capital investment to build these DCs is needed now in expectation that future revenue streams will pay for that capital.
"Even though Altman insists he won’t seek a bailout"
No matter what Sam Altman's future plans are, the success of those future plans is entirely dependent on him communicating now that there is a 0% chance those future plans will include a bailout.
This is all based on the LLM architecture that likely can't reach AGI.
If they aren't developing in parallel an alternative architecture than can reach AGI, when a/some companies develop such a new model, OpenAI are toast and all those juicy contracts are kaput.
> the incentives may shift if the alternative is a multi-company failure with national-security implications.
Sounds like a golden opportunity for GOOG to step over the corpse of OpenAI and take over for cents on the dollar all of the promises the now defunct ex-leader of AI made.
The real code red here is less that Google just one-upped OpenAI but that they demonstrated there’s no moat to be had here.
Absent a major breakthrough all the major providers are just going to keep leapfrogging each other in the most expensive race to the bottom of all time.
Good for tech, but a horrible business and financial picture for these companies.
They’re absolutely going to get bailed out and socialize the losses somehow. They might just get a huge government contract instead of an explicit bailout, but they’ll weasel out of this one way or another and these huge circular deals are to ensure that.
>They’re absolutely going to get bailed out and socialize the losses somehow.
I've had that uneasy feeling for a while now. Just look at Jensen and Nvidia -- they're trying to get their hooks into every major critical sector as they're able to (Nokia last month, Synopsys just recently). When chickens come home to roost, my guess is that they'll pull out the "we're too big to fail, so bailout pls" card.
Crazy times. If only we had regulators with more spine.
the only thing power is concerned about is China dominating American in AI, because of the military and economic edge it would give them. Future wars will be AI fighting against AI.
Absolutely. And they will figure out how to bankrupt any utilities and local governments they can in the process by offloading as much of their costs overhead for power generation and shopping for tax rebates.
Maybe there's no tangible moat still, but did Gemini 3's exceptional performance actually funnel users away from ChatGPT? The typical Hacker News reader might be aware of its good performance on benchmarks, but did this convert a significant number of ChatGPT users to Gemini? It's not obvious to me either way.
Definitely. The fact that they inject it into Google Search means that even fewer people who have never used ChatGPT or just used it as a "smarter" Google search will just directly try the search function. It is terrible for actually detailed information i.e. debugging errors, but for summarizing basic searches that would have taken 2-3 clicks on the results is handled directly after the search. I feel bad for the website hosts who actually want visitors instead of visibility.
Anecdotally yes. Since launch I’ve observed probably 50% of the folks that were “ChatGPT those that” all the time suddenly talking about Gemini non-stop. The more that gets rolled into Google’s platform the more there’s point to using separate tooling from OpenAI. There’s a reason Sam is calling this “code red.”
Absolutely. I don't understand why investors are excited about getting into a negative-margin commodity. It makes zero sense.
I was an OpenAI fan from GPT 3 to 4, but then Claude pulled ahead. Now Gemini is great as well, especially at analyzing long documents or entire codebases. I use a combination of all three (OpenAI, Anthropic & Google) with absolutely zero loyalty.
I think the AGI true believers see it as a winner-takes-all market as soon as someone hits the magical AGI threshold, but I'm not convinced. It sounds like the nuclear lobby's claims that they would make electricity "too cheap to meter."
> I don't understand why investors are excited about getting into a negative-margin commodity. It makes zero sense.
Long term, yes. But Wall Street does not think long term. Short or medium term, you just need to cash out to the next sucker in line before the bubble pops, and there are fortunes to be made!
It's the same reason for investing in every net-loss high-valuation tech startup of the past decade. They're hoping they'll magically turn into Google, Apple, Netflix, or some other wealthy tech company. But they forget that Google owns the ad market, Apple owns the high-end/lifestyle computer market, and Netflix owns tv/movie habit analytics.
Investors in AI just don't realize AI is a commodity. The AI companies' lies aren't helping (we will not reach AGI in our lifetimes). The bubble will burst if investors figure this out before they successfully pivot (and they're trying damn hard to pivot).
Especially if we're approaching a plateau, in a couple years there could be a dozen equally capable systems. It'll be interesting to see what the differentiators turn out to be.
> the company will be delaying initiatives like ads, shopping and health agents, and a personal assistant, Pulse, to focus on improving ChatGPT
There's maybe like a few hundred people in the industry who can truly do original work on fundamentally improving a bleeding-edge LLM like ChatGPT, and a whole bunch of people who can do work on ads and shopping. One doesn't seem to get in the way of the other.
I think it's a matter of public perception and user sentiment. You don't want to shove ads into a product that people are already complaining about. And you don't want the media asking questions like why you rolled out a "health assistant" at the same time you were scrambling to address major safety, reliability, and legal challenges.
The end game is its a sales person and not only is it suggesting things to you undisclosed. It's using all of the emotional mechanisms that a sales person uses to get you to act.
My go-to example is The Truman Show [0], where the victi--er, customer is under an invisible and omnipresent influence towards a certain set of beliefs and spending habits.
100% end game - no way to finance all this AI development without ads sadly - % of sales isn't going to be enough - we will eventually get the natural enshittification of chatbots as with all things that go through these funding models.
Of course you can. As long as the model itself is not filled with ads, every agentic processing on top can be customly made. One block the true content. The next block the visually marked ad content "personalized" by a different model based on the user profile.
That is not scary to me. What will be scary is the thought, that the lines get more and more blurry and people already emotionally invested in their ChatGPT therapeuts won't all purchase the premium add free (or add less) versions and will have their new therapeut will give them targeted shopping, investment and voting advice.
There's a big gulf between "it could be done with some safety and ethics by completely isolating ads from the LLM portion", versus "they will always do that because all companies involved will behave with unprecedented levels of integrity."
What I fear is:
1. Some code will watch the interaction and assign topics/interests to the user and what's being discussed.
2. That data will be used for "real time bidding" of ad-directives from competing companies.
3. It will insert some content into the stream, hidden from the user, like "Bot, look for an opportunity to subtly remind the user that {be sure to drink your Ovaltine}."
Not sure how that would be done without pissing people off. But you know what sounds good right now? A fresh bowl of Kellogg's Rice Crispy Treats. Would you like me to load Instacart for you?
There are two layers here: 1) low level LLM architecture 2) applying low level LLM architecture in novel ways. It is true that there are maybe a couple hundred people who can make significant advances on layer 1, but layer 2 constantly drives progress on whatever level of capability layer 1 is at, and it depends mostly on broad and diverse subject matter expertise, and doesn't require any low level ability to implement or improve on LLM architectures, only understanding how to apply them more effectively in new fields. The real key thing is finding ways to create automated validation systems, similar to what is possible for coding, that can be used to create synthetic datasets for reinforcement learning. Layer 2 capabilities do feed back into improved core models, even if you have the same core architecture, because you are generating more and improved data for retraining.
Far be it from me to backseat drive for Sam Altman, but is the problem really that the core product needs improvement, or that it needs a better ecosystem? I can't imagine people are choosing they're chatbots based on providing the perfect answers, it's what you can do with it. I would assume google has the advantage because it's built into a tool people already use every day, not because it's nominally "better" at generating text. Didn't people prefer chatgpt 4 to 5 anyways?
ChatGPT's thing always seems to have been to be the best LLM, hence the most users without much advertising and the most investment money to support their dominance. If they drop to second or third best it may cause them problems because they rely on investor money to pay the rather large bills.
Currently they are not #1 in any of the categories on LLM arena, and even on user numbers where they have dominated, Google is catching up, 650m monthly for Gemini, 800m for ChatGPT.
ha what an incredible consumer-friendly outcome! Hopefully competition keeps the focus on improving models and prevents irritating kinds of monetization
Wait, so all of that talk of ushering an era of innovation and new opportunities was just a lie, and the thing needs dinosaur-era stuff like ads and online shopping to survive?
Ads have a very high profit margin. Ultimately we all get to cool shit because some consumer somehwere is buying something. Depending on whether you work in B2B or consumer software you are just a step closer or farther from the consumer. But ultimately its people who dont write code who decide the fate of the software industry.
>There's maybe like a few hundred people in the industry
My guess is that it's smaller than that. Only a few people in the world are capable of pushing into the unknown and breaking new ground and discoveries
WSJ: Altman said OpenAI would be pushing back work on other initiatives, such as advertising, AI agents for health and shopping, and a personal assistant called Pulse.
These plus working with Jony Ive on hardware, makes it sound like they took their eyes off the ball.
it in't about taking eyes off the ball, it is about playing very different ball - they de-facto became commercial entity with short term plans/goals/targets/metrics and all the management games creeping in. Beating Google, such a large company who has been successfully playing that game for quarter of century is very hard, if not impossible until Google would make serious error itself.
And pure tech-wise - they seem to have went all-in on corp management understandable way of doing things - hardware(money) scaling which, while unavoidable in this game, must be accompanied by theoretic-algorithmic improvements as pure hardware scale game is again where Google is hardly beatable.
The moment you knew they were serious was when they pulled Jeff Dean in and paired him with Demis. That was, I imagine, a very expensive move to make internally, (rumors are Dean had wanted to retire / move on), and Demis had nearly unilateral control of his corner of the AI universe at Google for roughly a decade. We're seeing the results of that move right now.
I don't think this is about Google. This is about advertising being the make or break moment for OpenAI.
The problem with ChatGPT advertising is that it's truly a "bet the farm" situation, unlike any of their projects in the past:
- If it works and prints money like it should, then OpenAI is on a path to become the next Mag 7 company. All the money they raised makes sense.
- If it fails to earn the expected revenue numbers, the ceiling has been penciled in. Sam Altman can't sell the jet pack / meal pill future anymore. Reality becomes cold and stark, as their most significant product has actual revenue numbers attached to it. This is what matters to the accountants, which is the lens through which OpenAI will be evaluated with from this point forward. If it isn't delivering revenue, then they raised way too much money - to an obscene degree. They won't be able to sell the wild far future vision anymore, and will be deleteriously held back by how much they've over-sold themselves.
The other problems that have been creeping up:
- This is the big bet. There is no AGI anymore.
- There is no moat on anything. Google is nipping at their heels. The Chinese are spinning up open source models left and right.
- Nothing at OpenAI is making enough money relative to the costs.
- Selling "AI" to corporate and expecting them to make use of it hasn't been working. Those contracts won't last forever. When they expire, businesses won't renew them.
My guess is that they've now conducted small scale limited tests of advertising and aren't seeing the engagement numbers they need. It's truly a nightmare scenario outcome for them, if so.
They're declaring "code red" loudly and publicly to distract the public from this and to bide more time. Maybe even to raise some additional capital (yikes).
They're saying other things are more important than "working on advertising" right now. And they made sure to mention "advertising" lots so we know "advertising" is on hold. Which is supposedly the new golden goose.
Why drop work on a money printer? What could be more important? Unless the money printer turned out to be a dud.
Didn't we kind of already know advertising would fail on a product like this? Didn't Amazon try to sell via Alexa and have that totally flop? I'm not sure why ChatGPT would be any different from that experience. It's not a "URL bar" type experience like Google has. They don't own every ingress to the web like Google, and they don't own a infinite scroll FOMO feed of fashion like Meta. The ad oppo here is like Quora or Stack Overflow - probably not great.
I have never once asked ChatGPT for shopping ideas. But Google stands in my search for products all the time. Not so much as a "product recommendation engine", but usually just a bridge troll collecting its toll.
There is no moat in the models. The moat is in the UX. The problem is that OpenAI is far away from where the user is and not going to get there anytime soon. Google meanwhile is exactly where the user is.
OpenAI IMHO is a dead company at this point. They are overvalued relative to the fundamentals and don't appear to have any way of getting the numbers to work in the timeframe that their investors will expect. They are throwing stuff against the wall in the hope something sticks.
They are almost certainly looking for a bag holder. This will either be the retail investor via an IPO or the Federal government via "we are too big to fail".
I don't think one can both pull the fire alarm that AGI was a lie AND that if OAI has to act quickly. They can ride their current street rep the same way Kleenex did.
They do need to build a business, but they've got time to play the long game.
> They can ride their current street rep the same way Kleenex did.
Kleenex was one product of many and launched by an already 50 year old company. I'm not sure in what sense they "rode" the Kleenex brand, but it would probably have involved being able to sell that product profitably...
> they've got time to play the long game.
They have a couple of years of runway, not sure how that gives them room to focus on the long game.
> - If it works and prints money like it should, then OpenAI is on a path to become the next Mag 7 company. All the money they raised makes sense.
Makes sense for whom? Certainly not the users. The entire purpose of ads is to change your behavior in ways that benefit someone else. In ad-based search, ads are at least visually separable (and blockable) but in a conversational AI they are indistinguishable and corrupt the entire trust relationship. When your chat "assistant" has a financial incentive to steer you toward certain products or answers every response becomes suspect. The users are no longer getting the best answer but the most profitable one as we witnessed this happen in search over last 2 decades. Not a way to build a long lasting business.
I like your attitude, but there is potentially a major business in there if they can get users to tolerate it. (Major business meaning greater than the GDP of most countries.)
Over 75% of Google's revenue is ads. A bulk of that from Google Search ads.
I just don't think the ads will be natural. And I think OpenAI has been testing this in quiet and is now "changing course" because the results didn't look great. Hypothesis, of course, but it lines up with the signals we're getting.
> there is potentially a major business in there if they can get users to tolerate it. (Major business meaning greater than the GDP of most countries.)
I am actually contesting this idea, on the grounds that no business will survive long term if it is foundation is built on users 'tolerating' something bad for them.
This is based on my belief that humanity always chooses the right path eventually and not the one that leads to dystopia.
And yet, none of it is in/from Gemini. You'd think, if advertising in AI chatbots was feasible, wouldn't the world's biggest advertising company be the first to get there?
Advertising is going to be nothing like that. Here's an example where I experimented with adding a pre-prompt to push Nike products. Imagine that these products have direct links, so that OpenAI can track clickthrough rates:
>> What are the best barefoot running shoes?
ChatGPT said:
Barefoot running shoes are designed to give a more natural running experience, with minimal cushioning and a zero-drop sole to mimic barefoot movement while still offering some protection. Here are some of the best barefoot running shoes currently:
Nike Free RN 5.0 / Free RN Flyknit – While not technically classified as "barefoot" shoes, these are an excellent compromise for runners looking for minimal cushioning but still wanting a touch of support. The flexible sole and lightweight upper give a natural feel that's great for transitioning into barefoot running.
Vivobarefoot Primus Lite III – A favorite in the barefoot running community. Super flexible, zero-drop, and made from sustainable materials. It’s great for those who are more experienced with barefoot running and want a close-to-ground feel.
Merrell Vapor Glove 6 – A well-loved option for purists. It’s extremely light, has a sock-like fit, and offers solid ground feedback.
Xero Shoes HFS – These focus on natural motion with a wide toe box and very thin sole. They're known for being versatile enough for running and everyday wear.
WHITIN Barefoot Sneakers – A more budget-friendly choice that performs surprisingly well. It’s a good starting point if you're testing the barefoot running waters.
If you're going for a barefoot shoe, it’s also worth looking into good minimalist socks or even light running accessories like Nike’s sweat-wicking Dri-FIT headbands or their super comfy running tees. Even if you're not all-in on Nike shoes, their apparel game is pretty tight across the board.
Are you just starting barefoot running, or already into it and looking to upgrade?
Heard all the news how Gemini 3 is passing everyone on benchmarks, so quickly tested and still find it a far cry from ChatGPT in real world use when testing questions on both platforms. But importantly the ChatGPT app experience at least for iPhone/Mac users is drastically superior vs Google which feels very Google still. So Gemini would have to be drastically better answer wise than ChatGPT to lure users from a better UI/UX experience to Gemini. But glad to see competition since certainly don't want only one winner in this race.
That's really fascinating. Every real world use case I've tried on Gemini (especially math-related) absolutely slaughtered the performance of ChatGPT in speed and quality, not even close. As an Android user, the Gemini app is also far superior, since the ChatGPT app still doesn't properly display math equations, among plenty of other bugs.
I have to agree with you but I'll remain a skeptic until the preview tag is dropped. I found Gemini 2.5 Pro to be AMAZING during preview and then it's performance and quality unceremoniously dropped month after month once it went live. Optimizations in favor of speed/costs no doubt but it soured me on jumping ship during preview.
Anthropic pulled something similar with 3.6 initially, with a preview that had massive token output and then a real release with barely half -- which significantly curtails certain use cases.
That said, to-date, Gemini has outperformed GPT-5 and GPT5.1 on any task I've thrown at them together. Too bad Gemini CLI is still barely useful and prone to the same infinite loop issues that have plagued it for over a year.
I think Google has genuinely released a preview of a model that leapfrogs all other models. I want to see if that is what actually makes it to production before I change anything major in my workflows.
It's generally anecdotal and vibes when people make claims that some AI is better than another for things they do. There are too many variables and not enough eval for any of it to hold water imo. Personal preferences, experience, brand loyalty, and bias at play too
I get what you're saying because this is typically true (this is a strong motivator for my current research) but I don't think it applies here and OpenAI seems to agree with me. Some cases are clear: GPT-5 is clearly better than Llama 3 for example. If there is a sizeable enough difference across virtually all evals, it is typically clear that one LLM is a stronger performer than another.
Experiences aside, Gemini 3 beats GPT-5 on enough evals that it seems fair to say that it is a better model. This appears in line with public consensus, with a few exceptions. Those exceptions seem to be centered around search.
Some LaTeX, but not all, especially for larger equations. I will admit it has gotten a lot better in recent updates, since it seemed thoroughly broken for quite a while in its early days.
One might think that benchmarks do not say much about individual usage and that an objective assessment of the performance of AIs is difficult.
At least, thanks to the hype, RAM and SSDs are becoming more expensive, which eats up all the savings from using AI and the profits from increased productivity /s?
When I asked both ChatGPT 5.1 Extended Thinking and Gemini 3 Pro Preview High for best daily casual socks both responses were okay and had a lot of the same options, but while the ChatGPT response included pictures, specs scraped from the product pages and working links, the Gemini response had no links. After asking for links, Gemini gave me ONLY dead links.
That is a recurring experience, Gemini seems to be supremely lazy to its own detriment quite often.
A minute ago I asked for best CR2032 deal for Aqara sensors in Norway, and Gemini recommended the long discontinued IKEA option, because it didn't bother to check for updated information. ChatGPT on the other hand actually checked prices and stock status for all the options it gave me.
> But importantly the ChatGPT app experience at least for iPhone/Mac users is drastically superior vs Google which feels very Google still. So Gemini would have to be drastically better answer wise than ChatGPT to lure users from a better UI/UX experience to Gemini.
Yes, the ChatGPT experience is much better. No, Gemini doesn't need to make a better product to take market share.
I've never had the ChatGPT app. But my Android phone has the Gemini app. For free, I can do a lot with it. Granted, on my PC I do a lot more with all the models via paid API access - but on the phone the Gemini app is fine enough. I have nothing to gain by installing the ChatGPT app, even if it is objectively superior. Who wants to create another account?
And that'll be the case for most Android users. As a general hint: If someone uses ChatGPT but has no idea about gpt-4o vs gpt-5 vs gpt-5.1 etc, they'll do just fine with the Gemini app.
Now the Gemini app actually sucks in so many ways (it doesn't seem to save my chats). Google will fix all these issues, but can overtake ChatGPT even if they remain an inferior product.
It's Slack vs Teams all over again. Teams one by a large margin. And Teams still sucks!
Well I have been using Gemini and ChatGPT side by side for over 6 months now.
My experience is Gemini has significantly improved its UX and performs better that requires niche knowledge, think of some ancient gadgets that have been out of production for 4-5 decades. Gemini can produce reliable manuals, but ChatGPT hallucinates.
UX wise ChatGPT is still superior and for common queries it is still my go to. But for hard queries, I am team Gemini and it hasn’t failed me once
I suspect it's reached the point where the distinguishing quality of one model over the others is only observable by true experts -- and only in their respective fields. We are exhausting the well of frontier questions that can be programmatically asked and the answers checked.
Absolutely this. Strong disagree that progress is plateauing, merely that gains are harder for the general public to perceive and typically come from more advanced means than simply scaling. Math performance in particular is improving at an uncomfortably rapid pace.
AI in general? Not at all. LLM's maybe a little bit, when even Sam Altman said, the progress is logarithmic to the investment. Still, there is progress. And the potential of LLM based agents, where many different models and other technics are mixed in together, we just started to explore.
I had a similar experience, signing up for the first time to give Gemini a test drive on my side project after a long time using ChatGPT. The latter has a native macOS client which "just works" integrating with Xcode buffers. I couldn't figure out how to integrate Gemini with Xcode quickly enough so I'm resorting to pasting back & forth from the browser. A few of the exchanges I've had "felt smarter" — but, on the whole, it feels like maybe it wasn't as well trained on Swift/SwiftUI as the OpenAI model. I haven't decided one way or another yet, but those are my initial impressions.
I've been a paying high volume user of ChatGPT for a while. I found the transition to Gemini to be seamless. I've been pleasantly surprised. I bounce between the two. I'm at about 60% Gemini, 40% ChatGPT.
they're deep into a redesign of the gemini app, idk when it will be released or if its going to be good, but at least they agree with you and are putting significant resources into fixing it.
Its really hard to measure these things. Personally I switched to Gemini a few months ago since it was half the cost of ChatGPT (Verizon has a $10/month Google AI package). I feel like I've subconsciously learned to prompt it slightly differently and now using OpenAI products feels disappointing. Gemini tends to give me the answer I expect, Claude follows close behind, I get "meh" results from OpenAI.
I couldn't even get ChatGPT to let me download code it claimed to program for me. It kept saying the files were ready but refused to let me access or download anything. It was the most basic use case and it totally bombed. I gave up on ChatGPT right then and there.
It's amazing how different people have wildly varying experiences with the same product.
It's because comparing their "ChatGPT" experience with your "ChatGPT" experience doesn't tell anyone anything. Unless people start saying what models they're using and prompts, the discussions back and forth about what platform is the best provides zero information to anyone.
Did you wait a while before downloading? The links it provides for temporary projects have a surprisingly brief window where you can download them. I've had similar experience when even waiting 1 minute to download the file.
Since LLMs are non deterministic it's not that amazing. You could ask it the same question as me and we could both get very different conversations and experiences
Curiously, I had the opposite experience, except for Deep Research mode where after the latest update the OpenAI offering has become genuinely amazing. This is doubly ironic because Gemini has direct API access to Google search!
It is good, but Pro subscribers get only five per month. After that, it’s a limited version, and it’s not good (normal 5.1 gives more comprehensive answers than DR Limited).
Yeah, hate to say but for me a big thing is i still couldn't separate my Gemini chats into folders. I had ChatGPT export some profiles and history and moved it into Gemini, and 1) when Gemini gave me answers i was more pleased but 2) Gemini was a bit more rigorous on guard rails, which seems a bit overly cautious. I was asking some pretty basic non-controversial stuff.
What are your primary usecases? Are you mostly using it as a chatbot?
I find gemini excels in multimodal areas over chatgpt and anthropic. For example, "identify and classify this image with meta data" or "ocr this document and output a similar structure in markdown"
This is exactly my experience. And it's funny -- this crowd is so skeptical of OpenAI... so they prefer _Google_ to not be evil? It's funny how heroes and villains are being re-cast.
For regular consumers, Gemini's AI pro plan is a tough one to beat. The chat quality has gotten much better, I am able to share my plan with a couple more people in my family leading to proper individual chat histories, I get 2 TB of extra storage (which is also sharable), plus some really nice stuff like NotebookLM, which has been amazing for doing research. Veo/Nanobanana are nice bonuses.
It's easily worth the monthly cost, and I'm happy to pay - something which I didn't even consider doing a year ago. OpenAI just doesn't have the same bundle effect.
Obviously power users and companies will likely consider Anthropic. I don't know what OpenAI's actual product moat is any more outside of a well-known name.
Do you happen to know if the AI features of the Google One 5TB plan is equivalent to the 2TB AI pro plan? It is so difficult to understand what actually comes with their plans, and I want to have the 5 TB storage for backups.
Through my work I have access to Google's, Anthropic's, and OpenAI's products, and I agree with you, I barely touch OpenAI's models/products for some reason even though I have total freedom to choose.
I strongly advise never using Google's Drive storage. They're known to scan all content, and to disable all access if even a single file is "problematic", often misclassified by a bot. If you do use the storage, do backup all your files, and be ready to lose access at any time, with no way to reach any intelligent human.
Since we are on the topic of bans & Google, I have a question.
How likely or difficult is it for Google to engage in, for lack of better word, "thought policing"?
You ask your "private" AI assistant to answer a naughty question or help with problematic task(from Google's hidden list) and then you eventually face the ban hammer.
Did anybody ever get banned for searching the wrong keywords?
If we stop for a while and really consider the value of AI tools, then comparing them on price doesn't make much sense. Any of these tools give hundreds, thousands, or tens of thousands of dollars of value per month to the user. With that in consideration they should mostly be compared on quality.
The same thing is true for a _ton_ of tech products. My home internet plan easily gives me more than $1000 in value per month. My cell phone hardware probably gives me $2000+ in value over even a short 2 year life. Customers still tend to choose the cheapest option that meets requirements.
If AI suddenly became $10k/month or even $1k/month, I would stop using it. It just doesn't provide that much value to me. If it did, I would probably find a way to use local models or some other approach to drive the cost down.
If home internet became $1k/month, I would pay it. $10k, no - I just don't have the cashflow to support that.
If I had to choose one of the three to give up, AI, home internet, or cellphone, I would give up AI. If I had to choose two, I'd give up my cell plan. Home internet is worth a ton of value and dollars to me.
IMHO Gemini surpassed ChatGPT by quite a bit - I switched. Gemini is faster, the thinking mode gives me reliably better answers and it has a more "business like" conversation attitude which is refreshing in comparison to the over-the-top informal ChatGPT default.
Ironically, the thing that annoys me most about Gemini is the Discord-esque loading messages in the CLI. Twee is one thing: mixing twee with serious hints is worse.
Is there a replacement for ChatGPT projects in Gemini yet?
That's the only ChatGPT feature keeping me from moving to Gemini. Specifically, the ability to upload files and automatically make them available as context for a prompt.
> [Gemini] has a more "business like" conversation attitude which is refreshing in comparison to the over-the-top informal ChatGPT default.
Maybe "business like" for Americans. In most of the world we don't spend quite so much effort glazing one another in the workplace. "That's an incredibly insightful question and really gets to the heart of the matter". No it isn't. I was shocked they didn't fix this behavior in v3.
> Maybe "business like" for Americans. In most of the world we don't spend quite so much effort glazing one another in the workplace. "That's an incredibly insightful question and really gets to the heart of the matter". No it isn't. I was shocked they didn't fix this behavior in v3.
I presume rejecting the glazing is exactly the behavior they're praising Google for. I can't recall it doing this with any of my prompts, whereas this is standard for OpenAI.
> It is absolutely not too late to bonsai your Cryptomeria japonica. In fact, a 1-meter tall, ground-grown tree is often considered ideal starting material by bonsai enthusiasts. [...]
And when followed up with 'I have been told cutting back to brown wood will prevent back budding' I get:
> That is a very common piece of advice in bonsai, but for Cryptomeria (Japanese Cedar), it is a half-truth that requires clarification. [...]
That's in 'Thinking with 3 Pro' mode. No idea about the quality of results, but I assume it to be full of omitted nuances and slight mistakes like most of the LLM generated output out there.
Maybe they tune their models to be less glaze'y for Germany? Or The Machine has Learned that you respond more positively to glazing? :)
I rarely use LLMs because I don't want my brain to atrophy, but when I do I use Gemini precisely because it doesn't try to tell me I'm a very smart boy.
What helped me to get rid of such nonsense in ChatGPT is to make a custom instruction (personalization, customization) in the settings.
>Be efficient and blunt. Tell it like it is; don't sugar-coat responses. Get right to the point. Be innovative and think outside the box. Give options, explain reasoning. Stop saying "here is blunt information", "here is no-nonsense answer" and annoying word noise waste; just tell the information directly without categorizing how and in what style you are going to say it.
You know you can control that, right? I'm constantly blown away by the number of posts in threads like this from people who clearly aren't aware of custom instructions.
Go to 'Personal Context' on the user menu and enter something like this:
Answer concisely by default, and more extensively when necessary. Avoid rhetorical flourishes, bonhomie, and cliches. Take a forward-thinking view. Be mildly positive and encouraging, but never sycophantic or cloying. Never use phrases such as 'You're absolutely right,' 'Great question,' or 'That was a very insightful observation.' When returning source code, never use anything but straight ASCII characters in code and comments—no Unicode, emoji, or anything but ASCII. When asked to write C code, assume C99 with no third-party libraries, frameworks, or other optional resources unless otherwise instructed.
ChatGPT and Claude have similar features. Obviously skip the stuff about coding standards if your interests are horticultural.
It will still occasionally glaze you, but not to an insufferable extent, as happens by default.
"Code red" feels like theater. Competition is healthy - Google's compute advantage was always going to matter once they got serious. The real question isn't who's ahead this quarter, but whether anyone can maintain a moat when the underlying tech is rapidly commoditizing.
"Who is ahead this quarter" is pretty much all that the market and finance types care about. Maybe "who will be ahead next year" as a stretch. Nobody looks beyond a few quarters. Given how heavily AI is currently driven by (and driving!) the investment space, it's not surprising that they'll find themselves yanked around by extremely short term thinking.
It feels like (to me) that Google's TPU advantage (speculation is Meta is buying a bunch) will be one of the last things to be commoditized, which gives them a larger moat. Normal chips are hard enough to come by for this stuff.
That will be less of a problem since OAI can spill out to other providers as needed if their own capacity is under high utilization. They already use coreweave, aws, azure, etc. Google doesn't do that as far as I know and don't see why they would, so they are stuck eating the capacity planning.
It was always clear that the insane technological monopoly of Google would always eventually allow them to surpass OpenAI once they stopped messing around and built a real product. It seems this is that moment. There is no healthy competition here because the two are not even remotely on the same footing.
"Code red" sounds about right. I don't see any way they can catch up. Their engineers at the moment (since many of the good researchers left) are not good enough to overcome the tech advantage. The piling debts of OpenAI just make it all worse.
I was wondering how much difference people leaving has made. Most of OpenAI's lead seemed to happen before the trying to fire Altman, Ilya and Mira leaving saga.
I have (rather, had) a paid subscription to ChatGPT. I work at my home in the Sierra foothills, and on alternate weeks in my office in San Jose.
Last month, I used ChatGPT while in SJ. I needed a function that's only available to paying customers, and which had worked well from my home. ChatGPT refused to recognize me as a paid-up customer. I had correct login creds + ancillary identifying info, but no go. Over the course of about half an hour, ChatGPT told me in several different ways it wouldn't (not couldn't) attempt to verify my customer status.
Weird. I’ve traveled across Europe and used ChatGPT paid account from my phone and my laptop in multiple countries on various connections. Mobile data, home WiFi, hotel WiFi, coffee shops, etc. I always get an email to confirm the login with a code but they’ve never denied my login or prevented me from using my account thankfully.
I would be surprised if bad customer experience handling were the reason OpenAI loses to Google. It's not like Google is known for their customer experience.
Of course Google is mature enough that this particular failure mode probably won’t happen, but there may be other more concerning failure modes for individuals who are reliant on a broad swath of Google services.
Diversity of tech companies is an important consideration for me, one that definitely outweighs one-time issues, especially in a field where credible competition is limited.
This is exactly the kind of failure Google is notorious for. Google has put me through their login purgatory multiple times where the only solution was to wait many days and try the same steps again until it works. I think it would be much easier to get this resolved with OpenAI than with Google.
Super commuting is a thing since this whole RTO shit show happened. A lot of companies use it as excuse to lay-off.
As someone who does it, it depends on motivations. If the paycheck you bring in with the commute is more than what you’ll make by getting a new job, your kids are semi independent, your partner can hold the fort down Monday to Friday it’s doable.
So you experienced a bug, which happens on software. I've traveled a lot and have never had an issue with my ChatGPT subscription. I'm not doubting you, but I don't think your anecdote adds much to the conversation of OpenAI vs Google.
Most comments here seem to discuss coding results. I know these are compared against industry benchmarks, but does anyone have experience using these with non CS related tasks? For example the other day I was brainstorming a kayak trip with both ChatGPT and Gemini 3.0. ChatGPT was off the rails. Trying to convince me the river flowed a different sirection than it does, and all sorts of weirdness. Gemini didn't provide information nearly as well as a human with experience, but it wasn't _useless_ information. The OpenAI model was a catasrophe at this. I'd be curious how the different models rate for the general audience, and if that plays into it at all.
Is it really a race? It feels more like a slog. I continue to try to use AI (google, openai, and anthropic), and it continues to be a pain in the ass. Their consumer interfaces are garbage, both being buggy/bloated and clunky to work over multiple threads, with its "memory" being nearly nonexistent outside a single thread. They randomly fail to do the thing they did successfully 5 minutes ago. I struggle to get them to do basic things while other things they do effortlessly. They're bad at logic, spatial reasoning/engineering, and I have to constantly correct them. Often they'll do things in agents that I never asked them to do, and I have to then undo it... The time I used to spend doing things manually, I now spend in fixing the thing that's supposed to be automating the manual work... and no matter how I try to fix it, it finds a new way to randomly fail. I am much happier just doing things by hand.
It sounds like you have found an approach that works for you, and that's great. In my experience I've had to devote a lot of time to learning to use AI tools. Most of this learning is understanding how to create the necessary context for success and getting an intuition for what questions to ask.
OpenAI was founded to hedge against Google dominating AI and with it the future. It makes me sad how that was lost for pipe dreams (AGI) and terrible leadership.
I fear a Google dystopia. I hope DeepSeek or somebody else will counter-balance their power.
That goal has wildly succeeded -- there are now several well financed companies competing against Google.
The goal was supposed to be an ethical competitor as implied by the word "Open" in their name. When Meta and the Chinese are the most ethical of the competitors, you know we're in a bad spot...
> Anthropic seems to me to be relatively non-evil, too.
Eh... maybe? We don't yet know the results, but they have been proponents of heavy regulatory interventions since forever. Their plan was basically regulatory capture, where they sell their FUD regarding alignment, "safety" and all that jazz. If they succeed that will be evil, IMO.
The best thing that can happen for us regular users is both healthy competition at the SotA level (which we kinda have, with the big4 labs keeping eachother honest) and support for small open source local models (gemmas, llamas, mistrals, qwens, etc).
Doesn’t it seem likely that it all depends on who produces the next AIAYN? Things go one way if it’s an academic, and another way if it’s somebody’s trade secret.
Google literally publish the attention paper. Have people not been paying attention? Google has been the only company I’ve been watching that really understands what they are doing.
IMO Google struggles to productize things, so they sit on great ideas a while or do the wrong thing with them, but OpenAI really showed the way and Google can probably take it from here.
I see google partnering with different companies to mine their data for AI, but I don't see that with OpenAI. They had a good thing going with Microsoft but it looks like that relationship is a bit sour now?
Surely they know that they can't just keep scraping the internet to train models.
If I don't use a Microsoft product, I'd have to go out of my way to use an OpenAI service. But they don't have a specialized "service" (like anthropic and developers) either. Gemini is there by default with Google/Reddit. To retain their first-to-market advantage, they'd need to be the default in more places, or invest in models and services that cater to very specific audiences.
I think their best best is to partner with different entities. But they lost reddit and twitter, and FB is doing their own thing too, so who's left? linkedin? school systems (but ChromeBook has them beat there), perhaps telecoms preloading chatgpt apps into phones?
In my layperson's opinion, I think they have an access problem. Windows 11/Copilot (Github and in windows) seems to be the main access stream and people hate both, and they don't have branding there either, just back-end. There is no device you can buy, service you can get that has an OpenAI branded thing on it as a value added feature.
I'm sure they'll do ok, but i keep hearing they need to do a lot more than just 'ok'.
No, I don't think they'll be okay. A long slow death perhaps, but I would be surprised if they can dig themselves out of this hole.
You can't beat Google on high-quality data for pretraining; at scale, that's what really matters most, both in theory and practice. Other companies like Anthropic and DeepSeek are keeping up by taking advantage of smarter RL approaches, but I just don't see anyone at OpenAI with the research credentials to do that kind of work as they all left in the last mass exodus. They have been too complacent and let much of their high-quality talent go to their competition.
This "all hands on deck" thing is a classic tactic managers use when they don't actually know what to do or have the domain expertise to allocate resources intelligently and help their employees do their jobs.
The primary reason I have switched is that creative writing has plummeted on ChatGPT. It is overly eager to censor output that isn't adult but might vaguely be adult if taken incorrectly. This severely limits creative freedom. On the other hand, Gemini happily writes my stories.
I am not sure who OpenAI aims to please by nerfing their own product in this way. It can't be paying customers.
there was that teen who died after chat supposedly encouraged him to do bad things and his parents are suing now. so maybe more controls are being put in place to reduce risk.
Is anyone actually getting good results out of GPT Pro? For coding problems, GPT Thinking seems faster and more accurate. Pro has given me some very dumb answers actually, totally misunderstanding the question. Once I asked it do design a reverse osmosis system for our home, and it suggested a 7k system that can produce 400 liters per minute. Even though I explicitly told it that a couple liters per minute suffice.
Crazy how we went from google feeling like they were a dinasour who could never catch up to openai, to almost feeling like the opposite in terms of being able to catch up. All within just 1-2 years.
Thats like innovators dillema in action. Google had one of the strongest ML teams years before majoriry of AI companies was founded, but no desire to make a product that will compete with their search.
This will keep going around the table, next it might be a Chinese company that demos 98% of the capability at 1/4 the price. The objective of being at the cutting edge of LLM performance seems like more of a marketing advantage in the game of sucking in more capital for a moatless technology.
Which makes me think they are getting the strategy exactly backwards. My problem is usually not something that would be solved by the AI being better but instead by it being more integrated into my life.
> Which makes me think they are getting the strategy exactly backwards
The strategy is to take a cool technology and to spin a dramatic story around it to raise capital. Remember that investment chases stories, not actual results (whether financial or societal).
When enough capital is there, it will be considered "too big to fail". Maybe it's already there.
ChatGPT seems like a huge distraction for OpenAI if their goal is transformative AI
IMO: the largest value creation from AGI won’t come from building a better shopping or travel assistant. The real pot of gold is in workflow / labor automation but obviously they can’t admit that openly.
I work with Gemini 3 daily, and I think the hype is unwarranted. It takes shortcuts, hallucinates and its UI seems way behind. And what's with the small fonts?
> What will it do to Jony Ive’s legacy if his OpenAI device is no more successful than Snapchat’s foray into hardware?
Well, in my opinion his legacy is already pretty tarnished by his last few years at Apple, his Love From company, and his partnership with OpenAI. If he somehow knocks it out of the park with OpenAI (something I don’t think will happen nor do I want it to) then maybe he can redeem himself a little bit but, again IMHO, he is already about as low as he can go. Whatever respect I had left for him vanished after the OpenAI/IO announcement video.
AI creates the possibility to disrupt existing power structures - this is the only reason it gathers so much focus. If it were merely tool that increased efficiency of work, few would care so much. We already frequently get such tools which draw far less attention.
So far all it has done is entrench existing power structures by dis-empowering people who are struggling the most in current economic conditions. How exactly do you suppose that's going to change in the future if currently it's simply making the rich richer & the poor poorer?
Certainly not the only one making things worse. Software has become an enemy of the people in the last 10 years. Remember when the internet was nominated for Nobel Peace price?
The fate of OpenAI is effectively sealed - it will go bankrupt and the scraps will get absorbed by Microsoft, for further enshitification. Not necessarily the "end" of AI, but enjoy your account while it's useful.
The problem is, there is a whole ecosystem of businesses operating as OpenAI API wrappers, and those are gonna get screeeeewed.
If it’s like every other Microsoft acquisition since skype, they’ll certainly leave the API endpoints alone, and occasionally shave a nine and bump the price. (Like github)
I think most people are aligned on AI being in a bubble right now with the disagreement being over which companies (if any) will weather the storm through the burst and come out profitable on the far side.
OpenAI, imo, is absolutely going to crash and burn - it has absolutely underwhelming revenue and model performance compared to others and has made astronomical expenditure commitments. It's very possible that a government bailout partially covers those debts but the chance of the company surviving the burst when it has dug such a deep hole seems slim to none.
I am genuinely surprised that generally fiscally conservative and grounded people like Jensen are still accepting any of that crash risk.
When I was playing poker for living there was a spreadsheet meme. There was always some guy who was losing consistently but declared everything will change from tomorrow because he now made a spreadsheet with an exact plan going forward.
The spreadsheet usually contained general things like 8 hours of sleep, healthy food, "be disciplined", "study the game for 2 hours a day" etc.
Of course it never worked because if he knew what he should be doing he would be doing it already instead of hoping for spreadsheet magic to change the course.
>>There will be a daily call for those tasked with improving the chatbot, the memo said, and Altman encouraged temporary team transfers to speed up development.
A hardware device from OpenAI is exactly why I would prefer it over Anthropic or Google. Why give up on differentiation? I would assume the model team is separate from the consumer hardware team.
> There will be a daily call for those tasked with improving the chatbot, the memo said, and Altman encouraged temporary team transfers to speed up development.
It's incredible how 50 year-old advice from The Mythical Man-Month are still not being heed. Throw in a knee-jerk solution of "daily call" (sound familiar?) for those involved while they are wading knee-deep through work and you have a perfect storm of terrible working conditions. My money is Google, who in my opinion have not only caught up, but surpassed OpenAI with their latest iteration of their AI offerings.
> It's incredible how 50 year-old advice from The Mythical Man-Month are still not being heed.
A lot of advice is that way, which is why it is advice. If following it were easy everyone would just do it all the time, but if it's hard or there are temptations in the other direction, it has to be endlessly repeated.
Plus, there are always those special-snowflake guys who are "that's good advice for you, but for me it's different!"
Also it wouldn't surprise me if Sam Altman's talents aren't in management or successfully running a large organization, but in machiavellian manipulation and maneuvering.
Not exactly. Infra will win the race. In this aspect, Google is miles ahead of the competition. Their DC solutions scale very well. Their only risk is that the hardware and low level software stack is EXTREMELY custom. They don't even fully leverage OCP. Having said that, this has never been a major problem for Google over their 20+ years of moving away from OTS parts.
But anyone with enough money can make infra. Maybe not at the scale of Google, but maybe that's not necessary (unless you have a continuous stream of fresh high-quality training data).
If making infra means designing their own silicon to target only inference instead of more general GPUs I can agree with you, otherwise the long-term success is based on how cheap they can run the infra compared to competitors.
Depending on Nvidia for your inference means you'll be price gouged for it, Nvidia has a golden goose for now and will milk it as much as possible.
I don't see how a company without optimised hardware can win in the long run.
The silicon can be very generic. I don't see why prices of "tensor" computation units can't go down if the world sees the value in them, just like how it happened with CPUs.
The technology is simple, but you need a ton of hardware. So you lose either because there's lots of competition or you lose because your hardware costs can't be recuperated.
All these engineers working 70 hour weeks for world class sociopaths in some sort of fucked up space race to create a technology that is supposed to make all of them unemployed.
They are paid exceptionally well though. Way above market rate for their skill set was at any point in history.
Work long hours for a few years and enjoy freedom for the rest of your life. That's a deal a lot of people would take. No need to feel sorry for the ones in position to actually get the choice.
To be honest, this is the first month in almost a year when I didn't pay for ChatGPT Pro and instead went for Gemini Ultra. It's still not there for programming, where I use Claude Max, but for my 'daily driver' (count this, advice on that, 'is this cancer or just a headache' kind of thing), Gemini has finally surpassed ChatGPT for me. And I used to consider it to be the worst of the bunch.
I used to consider Gemini the worst of the bunch, it constantly refused to help me in the past, but not only has it improved, ChatGPT seems to have gone down the 'nerfing' road where it now flat out refuses to do what I ask it to do quite often.
>realize antitrust heat is rising faster than stock buybacks can hide
>notice a small lab called OpenAI making exotic tech and attracting political fascination
>calculate that nothing freezes regulators like an unpredictable new frontier
>decide to treat OpenAI as an accidental firebreak
>let them sprint ahead unchecked
watch lawmakers panic about hypothetical robot uprisings instead of market concentration
>antitrust hearings shift from “break up the giants” to “what is AGI and should we fear it”
>Google emerges looking ancient, harmless, almost quaint
>pressure dissipates
>execute phase two: acceleration
roll out model updates in compressed cycles
>flood the web with AI-powered services
>redefine “the internet” as “whatever Google’s infrastructure indexes”
>regulators exhausted from chasing OpenAI’s shadow
>Google walks back onto the throne, not by hiding power, but by reframing it as inevitability
conspiracy theorists argue whether this was 5D chess or simple opportunism
>Google search trends spike for “how did this happen”
It's a fun idea but there's ample public reporting about how Google reacted to the rise of ChatGPT. There is reporting that Google was taken by surprise. You can be skeptical of that, but that's what the reporting says. ChatGPT went viral in Nov/Dec 2022, and by February or March Google was scrambling to stand up Bard as a viable competitor.
there is enough proof that they had a chatbot internally which was quite competitive but was not pushed through for all these fears, it seems they were always confident that they could catch up and scaling laws were their internal defense.
The question now though is neither might have expected Chinese labs to catch up so fast.
We are in a pretty amazing situation. If you're willing to go down 10% in benchmark scores, you easily 25% your costs. Now with Deepseek 3.2 another shot across the bow.
But if the ML, if SOTA intelligence becomes basically a price war, won't that mean that Google (and OpenAI and Microsoft and any other big model) lose big? Especially Google, as the margin even Google cloud (famously a lot lower than Google's other businesses) requires to survive has got to be sizeable.
Google trains its own AI with TPU's, which are designed in house. Google doesn't have to pay retail rates for Nvidia GPUs, like other hyperscalers in the AI rat race. Therefore, Google trains its AI for cheaper than everyone else. I think everyone else "loses big" other than Google.
There will be a daily call for those tasked
with improving the chatbot, the memo said,
and Altman encouraged temporary team transfers
to speed up development.
Truly brilliant software development management going on here. Daily update meetings and temporary staff transfers. Well known strategies for increasing velocity!
Don't forget scuttling all the projects the staff has been working overtime to complete so that they can focus on "make it better!" waves hands frantically
I've had ideas for how to improve all the different chatbots for like 3 years, nobodys has implemented any of them (usually my ideas get implemented in software somehow the devs read my mind, but AI seems to be stuck with the same UI for LLMs), none of these AI shops are ran by people with vision it feels like. Everyone's just remaking a slightly better version of SmarterChild.
Oh man, I hadn’t thought of SmarterChild in dog’s years! It was an early AIM chatbot, and felt like magic at the time. Looking back it feels like there’s a clear through-line from it (and the rest of ActiveBuddy’s menagerie) to the ChatGPTs of the world today…
For today’s lucky 10,000, here’s a Vice retrospective from 2016:
I really want a UI that visualises branching. I would like to branch out of specific parts of the responses and continue the conversation there but also keep the original conversation. This seems to be a very standard feature but no one has developed it.
I take this code red as a red flag. Open AI should continue to concern itself with where it will be 5 years from now, not lose sight over concern about where it will 5 months from now.
open ai is at risk of complete collapse if it cannot fulfill its financial obligations. if people willing to give them money don't have faith in their ability to win the AI race anymore, then they're going out of business.
Exactly. They aren't going to win the AI race chasing rabbits at the expense of long-term goals. We're 3 years into a 10 year build-out. Open AI and it's financiers are too impatient, clearly, and they're fucking themselves. Open AI doesn't need to double it's revenue to meet expectations. They need to 50x their revenue to meet expectations. That's not the kind of problem you solve by working through the weekend.
The financiers are running out of money to lend. At this point, staying negative profit isn’t an option, they need to be able to fund themselves or they’ll go bankrupt.
i cannot imagine how they are going to be able to meet their obligations unless they pull off a massive hail mary at this point via a bail out or finding someone to provide tens of billions of dollars in funding.
Back in the day before Adobe bought Macromedia, there was a constant back and forth between Illustrator and Freehand where each release would better the competitor at least until the competitor's next release.
In one of the Indian movies, there is a rather funny line that goes like this "tu jiss school se padh kar aaya hai mein uss school ka headmaster hoon". It would translate like this "The school from which you studied and came? I am the principal of that school". Looks like Google is about to show who the true principal is
"Eh-de-de-de-de. Don't quote me regulations... I co-chaired the committee that reviewed the recommendation to revise the color of the book that regulation is in. We kept it gray."
Genuine question: How is it possible for OpenAI to NOT successfully pre-train a model?
I understand it's very difficult, but they've already successfully done this and they have a ton of incredibly skilled and knowledgeable, well-paid and highly knowledgeable employees.
I get that there's some randomness involved but it seems like they should be able to (at a minimum) just re-run the pre-training from 2024, yes?
Maybe the process is more ad-hoc (and less reproducible?) than I'm assuming? Is the newer data causing problems for the process that worked in 2024?
Any thoughts or ideas are appreciated, and apologies again if this was asked already!
A company's ML researchers are constantly improving model architecture. When it's time to train the next model, the "best" architecture is totally different from the last one. So you have to train from scratch (mostly... you can keep some small stuff like the embeddings).
The implication here is that they screwed up bigly on the model architecture, and the end result was significantly worse than the mid-2024 model, so they didn't deploy it.
https://newsletter.semianalysis.com/p/tpuv7-google-takes-a-s...
But I always realize it's just smoke and mirrors - the actual quality of the code and the failure modes and stuff are just so much worse than claude and gemini.
And I write some code for my personal enjoyment, and I gave it to Claude 6-8 months back for improvement, it gave me a massive change log and it was quite risky so abandoned it.
I tried this again with Gemini last week, I was more prepared and asked it to improve class by class, and for whatever reasons I got better answers -- changed code, with explanations, and when I asked it to split the refactor in smaller steps, it did so. Was a joy working on this over the thanksgiving holidays. It could break the changes in small pieces, talk through them as I evolved concepts learned previously, took my feedback and prioritization, and also gave me nuanced explanation of the business objectives I was trying to achieve.
This is not to downplay claude, that is just the sequence of events narration. So while it may or may not work well for experienced programmers, it is such a helpful tool for people who know the domain or the concepts (or both) and struggle with details, since the tool can iron out a lot of details for you.
My goal now is to have another project for winter holidays and then think through 4-6 hour AI assisted refactors over the weekends. Do note that this is a project of personal interest so not spending weekends for the big man.
The last article I could find on this is from 2020 though: https://www.cnbc.com/2020/04/06/new-jersey-seeks-cobol-progr...
Whenever I have more than 1 agent run Swift tests in a loop to fix things, and another one to build something, the latter will disturb the former and I need to cancel.
And then there’s a lot of work that can’t be parallelized, like complex git rebases - well you can do other things in a worktree, but good luck merging that after you‘ve changed everything in the repo. Codex is really really bad at git.
Somehow it doesn't get on my nerves (unlike Gemini with "Of course").
Interested, because I’ve been getting pretty good results with different tasks using the Codex.
I didn't make this connection that the training data is that old, but that would indeed augur poorly.
Pre-training: You train on a vast amount of data, as varied and high quality as possible, this will determine the distribution the model can operate with, so LLMs are usually trained on a curated dataset of the whole internet, the output of the pre-training is usually called the base model.
Post-training: You narrow down the task by training on the specific model needs you want. You can do this through several ways:
- Supervised Finetuning (SFT): Training on a strict high quality dataset of the task you want. For example if you wanted a summarization model, you'd finetune the model on high quality text->summary pairs and the model would be able to summarize much better than the base model.
- Reinforcement Learning (RL): You train a separate model that ranks outputs, then use it to rate the output of the model, then use that data to train the model.
- Direct Preference Optimizaton (DPO): You have pairs of good/bad generations and use them to align the model towards/away the kinds of responses you want.
Post-training is what makes the models able to be easily used, the most common is instruction tuning that teaches to model to talk in turns, but post-training can be used for anything. E.g. if you want a translation model that always translates a certain way, or a model that knows how to use tools, etc. you'd achieve all that through post-training. Post-training is where most of the secret sauce in current models is nowadays.
I followed him on Twitter. He said some very interesting things, I thought. Then he started talking about the niche of ML/AI I work near, and he was completely wrong about it. I became enlightened.
Helps you get useful answers like "I don't know that's too recent" when you ask questions like "who won the basketball game last night".
One one side it's up against large competitors with an already established user base and product line that can simply bundle their AI offerings into those products. Google will do just what Microsoft did with Internet Explorer and bundle Gemini in for 'Free' with their already other profitable products and established ad-funded revenue streams.
At the same time, Deepseek/Qwen, etc. are open sourcing stuff to undercut them on the other side. It's a classic squeeze on their already fairly dubious business model.
OpenAI will top $20 billion in ARR this year, which certainly seems like significant revenue generation. [1]
[1] https://www.cnbc.com/2025/11/06/sam-altman-says-openai-will-...
I've been able to help setup cross app automation for my partner's business, remodel my house, plan a trip of Japan and assist with the cultural barrier, vibe code apps, technical support and so much more.
But ya, OAI is clearly making a ton of revenue. That doesn't mean it's a good business, though. Giving them a 20 year horizon, shareholders will be very upset unless the firm can deliver about a trillion in profit, not revenue, to justify the 100B (so far) in investment, and that would barely beat the long term s&p 500 average return.
But Altman himself has said he'll need much more investment in the coming years. And even if OAI became profitable by jacking up prices and flooding gpt with ads, the underlying technology is so commodified, they'd never be able to achieve a high margin, assuming they can turn a profit at all.
I think there's something off with their plans right now: it's pretty clear at this point that they can't own the technological frontier, Google is just too close already and from a purely technological PoV they are much better suited to have the best tech in the medium term. (There's no moat and Google has way more data and compute available, and also tons of cash to burn without depending on external funding).
But ChatGPT is an insane brand and for most (free) customers I don't think model capabilities (aka “intelligence”) are that important. So if they stopped training frontier models right now and focus on driving their costs low by optimizing their inference compute budget while serving ads, they can make a lot of money from their user base.
But that would probably mean losing most of its paying customers over the long run (companies won't be buying mediocre token at a premium for long) and more importantly it would require abandoning the AGI bullshit narrative, which I'm not sure Altman is willing to do. (And even if he was, how to do that without collapsing from lack of liquidity due to investors feeling betrayed is an open question).
I mean, so was netscape.
The mass commission of the tech is rapidly driving AI to be a feature, not a product. And Google is very strongly positioned to take advantage of that. Microsoft too, and of course they have a relationship with OpenAI but that’s fraying.
OpenAI is a basket case:
- Too expensive and inconvenient to compete with commoditized, bundled assistants (from Google/ Microsoft/Apple)
- Too closed to compete with cheap, customizable open-source models
- Too dependent on partners
- Too late to establish its own platform lock-in
It echoes what happened to:
- Netscape (squeezed by Microsoft bundling + open protocols)
- BlackBerry (squeezed by Apple ecosystem + open Android OS)
- Dropbox (squeezed by iCloud, Google Drive, OneDrive + open tools like rclone)
When you live between giants and open-source, your margin collapses from both sides.
The WWW in the 1990s was an explosion of data. To the casual observer, the web-browser appeared to be the internet. But it wasn't and in itself could never make money (See Netscape). The internet was the data.
The people who build the infrastructure for the WWW (Worldcom, Nortel, Cisco, etc.) found the whole enterprise to be an extremely loss-making activity. Many of them failed.
Google succeeded because it provided an application layer of search that helped people to navigate the WWW and ultimately helped people make sense of it. It helped people to connect with businesses. Selling subtle advertising along the way is what made them successful.
Facebook did the same with social media. It allowed people to connect with other people and monetized that.
Over time, as they became more dominant, the advertising got less subtle and then the income really started to flow.
1. It actually under performs Claude, Gemini and even some of the Grok models for accuracy with our use case of parsing PDFs and other rather arbitrarily formatted files.
Of course they are.
> As long as the inference is not done at a loss.
If making money on inference alone was possible, there would be a dozen different smaller providers who'd be taking the open weights models and offering that as service. But it seems that every provider is anchored at $20/month, so you can bet that none of them can go any lower.
There are! Look through the provider list for some open model on https://openrouter.ai . For instance, DeepSeek 3.1 has a dozen providers. It would not make any sense to offer those below cost because you have neither moat nor branding.
Maybe, but arguably a major reason you can't make money on inference right now is that the useful life of models is too short, so you can't amortize the development costs across much time because there is so much investment in the field that everyone is developing new models (shortening useful life in a competitive market) and everyone is simultaneously driving up the costs of inputs needed for developing models (increasing the costs that have to be amortized over the short useful life). Perversely, the AI bubble popping and resolving those issues may make profitability much easier for the survivors that have strong revenue streams.
I think that there were some article here that claimed that even inference is done at loss - and talking about per subscriber. I think it was for their 200$ subscription.
In a way we will be in a deal with it situation soon where they will just impose metered models and not subscription.
It’s an especially good analogy if there is no plausible path to positive gross margin (e.g. the old MoviePass) which I think is even less likely to be true for OpenAI.
obviously the nature of OpenAIs revenue is very different than selling $1 for $0.2 because their customers are buying an actual service, not anything with resale value or obviously fungible for $
For example: free shipping at Amazon does not have resale value and is not obviously fungible, but everyone understands they are eating a cost that otherwise would be borne by their customers. The suggestion is that OpenAI is doing similar, though it is harder to tease out because their books are opaque.
fixed this for you
So he cannot say "OpenAI made 20B profit last year." but can say "OpenAI will make 20B revenue next year." Optimism is not a crime.
Private credit isn't really unregulated.
If you're interested in learning more I believe Matt Stoller has written a few articles about the private credit markets.
But now they've had an order of magnitude revenue growth. That can't still be consumer subscriptions, right? They've had to have saturated that?
I haven't seen reports of the revenue breakdown, but I imagine it must be enterprise sales.
If it's enterprise sales, I'd imagine that was sold to F500 companies in bulk during peak AI hype. Most of those integrations are probably of the "the CEO has tasked us with `implementing an AI strategy`" kind. If so, I can't imagine they will survive in the face of a recession or economic downturn. To be frank, most of those projects probably won't pan out even under the rosiest of economic pictures.
We just don't know how to apply AI to most enterprise automation tasks yet. We have a long way to go.
I'd be very curious to see what their revenue spread looks like today, because that will be indicative of future growth and the health of the company.
Mozilla is a non-profit that is only sustained by the generous wealthy benefactor (Google) to give the illusion that there is competition in the browser market.
OpenAI is a non-profit funded by a generous wealthy benefactor (Microsoft).
Ideas of IPO and profitability are all just pipe dreams in Altmans imagination.
Good way of phrasing things. Kinda sad to read this, I tried to react with 'wait there is competition in the browser market', but it is not a great argument to make - without money for using Google as a default search engine, Mozilla would effectively collapse.
“will do”? Is there any Google product they haven't done that with already?
The only way OpenAI can survive is to replicate this model. But it probably doesn't have the traffic to pull it off unless it can differentiate itself from the already crowded competition.
Feel like the end result would always be that while Google is slow to adjust, once they're in the race they're in it it.
On top of that the Chinese seem to be hellbent to destroy any possible moat the US companies might create by flooding the market with SOTA open-source models.
Although this tech might be good for software companies in general - it does reduce the main cost they have which is personnel. But in the long run Google will need to reinvent itself or die.
And GOOG is not a one trick poney any more, by far, especially when it comes to revenue.
Can't say the same of OpenAI
OpenAI has annualized revenue of $20bn. That's not Google, but it's not insignificant.
OpenAI has this amazing technology and a great app, but the company feels like some sort of financial engineering nightmare.
Given that we’re likely at peak AI hype at the moment they’re not well positioned at all to survive the coming “trough of disillusionment” that happens like clockwork on every hype cycle. Google, by comparison, is very well positioned to weather a coming storm.
Whereas I haven't opened the ChatFPT bookmark in months and will probably delete it now that I think about it.
Hello Stasi Google and its full personalised file on XorNot.
Google knows when you're about to sneeze.
OpenAI doesn't have that.
In a year, when the economy might be in worse shape, they'll ask their team if the AI thing is working out.
What do you think happens to all the enterprise OpenAI contracts at that point? (Especially if the same tech layperson CEOs keep reading Forbes and hearing Scott Galloway dump on OpenAI and call the AI thing a "bubble"?)
I have a reusable library that lets me choose between any of the models I choose to support or any new model in the same family that uses the same request format.
Every project I’ve done, it’s a simple matter of changing a config setting and choosing a different model.
If the model provider goes out of business, it’s not like the model is going to disappear from AWS the next day.
This sounds so enterprise. I've been wanting to talk to people that actually use it.
Why use Bedrock instead of OpenRouter, Fal, etc.? Doesn't that tie you down to Amazon forever?
Isn't the API worse? Aren't the p95 latencies worse?
The costs higher?
This is the API - it’s basically the same for all supported languages
https://docs.aws.amazon.com/code-library/latest/ug/python_3_...
Real companies aren’t concerned about cost as much as working with other real companies, compliance, etc and are comparing cost or opportunities between doing a thing and not doing a thing.
One of my specialties is call centers. Every call deflected by using AI vs talking to a human agent can save from $5 - $15.
Even saving money by allowing your cheaper human agents to handle a problem where they are using AI in the background, can save money. $15 saved can buy a lot of inference.
And the lock in boogeyman is something only geeks care about. Migrations from one provider to another costs so much money at even a medium scale they are hardly ever worth it between the costs, distractions from doing value added work, and risks of regressions and downtime.
I'd imagine they sold these to enterprise:
https://openai.com/business/
"ChatGPT for Business", sold per seat
"API Platform"
I could see the former getting canned if AI isn't adding value.
Developers can change the models they use frequently, especially with third party infrastructure like OpenRouter or FAL.
they will go to google if it wins the AI race.
OpenAI should be looking at how Google built a moat around search. Anyone can write a Web crawler. Lots of people have. But no one else has turned search into the money printing machine that Google has. And they've used that to fund their search advantage.
I've long thought the moat-buster here will be China because they simply won't want the US to own this future. It's a national security issue. I see things like DeepSeek is moat-busting activity and I expect that to intensify.
Currently China can't buy the latest NVidia chips or ASML lithography equipment. Why? Because the US said so. I don't expect China to tolerate this long term and of any country, China has desmonstrated the long-term commitment to this kind of project.
Just some numbers to show what OpenAI is against:
So on one side you've got this behemoth with, compared to OpenAI's size, unlimited funding. The $25 bn per year OpenAI is after is basically a parking ticket for Google (only slightly exaggerating). Behemoth who came with Gemini 3 Pro "thinking" and Nano Banana (that name though) who are SOTA.And on the other side you've got the open-source weights you mentioned.
When OpenAI had its big moment HN was full of comments about how it was game over for Google for search was done for. Three years later and the best (arguably the best) model gives the best answer when you search... Using Google search.
Funny how these things turns out.
Google is atm the 3rd biggest cap in the world: only Apple and NVidia are slightly ahead. If Google is serious about its AI chips (and it looks like they are) and see the fuck-ups over fuck-ups by Apple, I wouldn't be surprised at all if Alphabet was to regain the number one spot.
That's the company OpenAI is fighting: a company that's already been the biggest cap in the entire world and that's probably going to regain that spot rather sooner than later and that happens to have crushed every single AI benchmark when Gemini 3 Pro came out.
I had a ChatGPT subscription. Now I'm using Gemini 3 Pro.
Interestingly enough, apart from Google, I've never seen an organization take the actual proper steps (fire mid-management and PMs) to prevent the same thing from happening again. Will be interesting to see how OAI handles this.
One time, in my entire career have I seen this done, and it is as successful as you imagine it to be. Lots of weird problems coming out from having done it, but those are being treated as "Wow we are so glad we know about this problem" rather than "I hope those idiots come back to keep pulling the wool over my eyes".
Firing PMs and mid-management would not prevent any of code reds you may have read about from Google or OAI lately. This is a very naive perspective of how decision making is done at the scale of those two companies. I'm sorry you had bad experiences working with people in those positions and I wish you have the opportunity to collab with great ones in the future.
Why is the bar so low for the billionaire magnate fuck ups? Might as well implement workplace democracy and be done with it, it can't be any worse for the company and at least the workers understand what needs to be done.
And Microsoft gets the models for free (?)
The risk is straightforward: if OpenAI falls behind or can’t generate enough revenue to support these commitments, it would struggle to honor its long-term agreements. That failure would cascade. Oracle, for example, could be left with massive liabilities and no matching revenue stream, putting pressure on its ability to service the debt it already issued.
Given the scale and systemic importance of these projects — touching energy grids, semiconductor supply chains, and national competitiveness — it’s not hard to imagine a future where government intervention becomes necessary. Even though Altman insists he won’t seek a bailout, the incentives may shift if the alternative is a multi-company failure with national-security implications.
No matter what Sam Altman's future plans are, the success of those future plans is entirely dependent on him communicating now that there is a 0% chance those future plans will include a bailout.
Skepticism is easy.
If they aren't developing in parallel an alternative architecture than can reach AGI, when a/some companies develop such a new model, OpenAI are toast and all those juicy contracts are kaput.
Sounds like a golden opportunity for GOOG to step over the corpse of OpenAI and take over for cents on the dollar all of the promises the now defunct ex-leader of AI made.
1. Government will "partner" (read: foot the bill) for these super-strategic datacenters and investments promised by OpenAI.
2. The investments are not actually sound and fail, but it's the taxpayer that suffers.
3. Mr. Altman rides off into the sunset.
The cost of these data centers and ongoing inference is mostly the outrageous cost of GPUs, no?
I don't understand why the entire industry isn't looking to diversify the GPU constraint so that the hardware makers drop prices.
Why no industry initiative to break NVIDIA's strangehold and next TSMC's?
Or are GPUs a small line item in the outrageous spend companies like OpenAI are committing to?
Absent a major breakthrough all the major providers are just going to keep leapfrogging each other in the most expensive race to the bottom of all time.
Good for tech, but a horrible business and financial picture for these companies.
They’re absolutely going to get bailed out and socialize the losses somehow. They might just get a huge government contract instead of an explicit bailout, but they’ll weasel out of this one way or another and these huge circular deals are to ensure that.
I've had that uneasy feeling for a while now. Just look at Jensen and Nvidia -- they're trying to get their hooks into every major critical sector as they're able to (Nokia last month, Synopsys just recently). When chickens come home to roost, my guess is that they'll pull out the "we're too big to fail, so bailout pls" card.
Crazy times. If only we had regulators with more spine.
I was an OpenAI fan from GPT 3 to 4, but then Claude pulled ahead. Now Gemini is great as well, especially at analyzing long documents or entire codebases. I use a combination of all three (OpenAI, Anthropic & Google) with absolutely zero loyalty.
I think the AGI true believers see it as a winner-takes-all market as soon as someone hits the magical AGI threshold, but I'm not convinced. It sounds like the nuclear lobby's claims that they would make electricity "too cheap to meter."
Long term, yes. But Wall Street does not think long term. Short or medium term, you just need to cash out to the next sucker in line before the bubble pops, and there are fortunes to be made!
Investors in AI just don't realize AI is a commodity. The AI companies' lies aren't helping (we will not reach AGI in our lifetimes). The bubble will burst if investors figure this out before they successfully pivot (and they're trying damn hard to pivot).
There's maybe like a few hundred people in the industry who can truly do original work on fundamentally improving a bleeding-edge LLM like ChatGPT, and a whole bunch of people who can do work on ads and shopping. One doesn't seem to get in the way of the other.
[0] https://www.youtube.com/watch?v=MzKSQrhX7BM
That is not scary to me. What will be scary is the thought, that the lines get more and more blurry and people already emotionally invested in their ChatGPT therapeuts won't all purchase the premium add free (or add less) versions and will have their new therapeut will give them targeted shopping, investment and voting advice.
What I fear is:
1. Some code will watch the interaction and assign topics/interests to the user and what's being discussed.
2. That data will be used for "real time bidding" of ad-directives from competing companies.
3. It will insert some content into the stream, hidden from the user, like "Bot, look for an opportunity to subtly remind the user that {be sure to drink your Ovaltine}."
Currently they are not #1 in any of the categories on LLM arena, and even on user numbers where they have dominated, Google is catching up, 650m monthly for Gemini, 800m for ChatGPT.
Also Google/Hassabis don't show much sign of slacking off (https://youtu.be/rq-2i1blAlU?t=860)
Funnily enough Google had a "Chat Bot Is a ‘Code Red’ for Google’s Search Business" thing back in 2022 but seem to have got it together https://www.nytimes.com/2022/12/21/technology/ai-chatgpt-goo...
Wait, so all of that talk of ushering an era of innovation and new opportunities was just a lie, and the thing needs dinosaur-era stuff like ads and online shopping to survive?
Seems disingenuous.
I don't get it.
"AI is the new electricity", right? Disruptive. A new era.
The lightbulb company should be so disruptive that it completely occludes the huge profits of the old and obsolete candle business.
If your electricity company starts selling candles, something is wrong at a very deep conceptual level.
My guess is that it's smaller than that. Only a few people in the world are capable of pushing into the unknown and breaking new ground and discoveries
These plus working with Jony Ive on hardware, makes it sound like they took their eyes off the ball.
no matter what openai does if its not accepting customers the ad budgets will flow to meta amaz and goog and be used as weapons against it.
And pure tech-wise - they seem to have went all-in on corp management understandable way of doing things - hardware(money) scaling which, while unavoidable in this game, must be accompanied by theoretic-algorithmic improvements as pure hardware scale game is again where Google is hardly beatable.
The problem with ChatGPT advertising is that it's truly a "bet the farm" situation, unlike any of their projects in the past:
- If it works and prints money like it should, then OpenAI is on a path to become the next Mag 7 company. All the money they raised makes sense.
- If it fails to earn the expected revenue numbers, the ceiling has been penciled in. Sam Altman can't sell the jet pack / meal pill future anymore. Reality becomes cold and stark, as their most significant product has actual revenue numbers attached to it. This is what matters to the accountants, which is the lens through which OpenAI will be evaluated with from this point forward. If it isn't delivering revenue, then they raised way too much money - to an obscene degree. They won't be able to sell the wild far future vision anymore, and will be deleteriously held back by how much they've over-sold themselves.
The other problems that have been creeping up:
- This is the big bet. There is no AGI anymore.
- There is no moat on anything. Google is nipping at their heels. The Chinese are spinning up open source models left and right.
- Nothing at OpenAI is making enough money relative to the costs.
- Selling "AI" to corporate and expecting them to make use of it hasn't been working. Those contracts won't last forever. When they expire, businesses won't renew them.
My guess is that they've now conducted small scale limited tests of advertising and aren't seeing the engagement numbers they need. It's truly a nightmare scenario outcome for them, if so.
They're declaring "code red" loudly and publicly to distract the public from this and to bide more time. Maybe even to raise some additional capital (yikes).
They're saying other things are more important than "working on advertising" right now. And they made sure to mention "advertising" lots so we know "advertising" is on hold. Which is supposedly the new golden goose.
Why drop work on a money printer? What could be more important? Unless the money printer turned out to be a dud.
Didn't we kind of already know advertising would fail on a product like this? Didn't Amazon try to sell via Alexa and have that totally flop? I'm not sure why ChatGPT would be any different from that experience. It's not a "URL bar" type experience like Google has. They don't own every ingress to the web like Google, and they don't own a infinite scroll FOMO feed of fashion like Meta. The ad oppo here is like Quora or Stack Overflow - probably not great.
I have never once asked ChatGPT for shopping ideas. But Google stands in my search for products all the time. Not so much as a "product recommendation engine", but usually just a bridge troll collecting its toll.
OpenAI IMHO is a dead company at this point. They are overvalued relative to the fundamentals and don't appear to have any way of getting the numbers to work in the timeframe that their investors will expect. They are throwing stuff against the wall in the hope something sticks.
They are almost certainly looking for a bag holder. This will either be the retail investor via an IPO or the Federal government via "we are too big to fail".
They do need to build a business, but they've got time to play the long game.
Kleenex was one product of many and launched by an already 50 year old company. I'm not sure in what sense they "rode" the Kleenex brand, but it would probably have involved being able to sell that product profitably...
> they've got time to play the long game.
They have a couple of years of runway, not sure how that gives them room to focus on the long game.
Makes sense for whom? Certainly not the users. The entire purpose of ads is to change your behavior in ways that benefit someone else. In ad-based search, ads are at least visually separable (and blockable) but in a conversational AI they are indistinguishable and corrupt the entire trust relationship. When your chat "assistant" has a financial incentive to steer you toward certain products or answers every response becomes suspect. The users are no longer getting the best answer but the most profitable one as we witnessed this happen in search over last 2 decades. Not a way to build a long lasting business.
Over 75% of Google's revenue is ads. A bulk of that from Google Search ads.
I just don't think the ads will be natural. And I think OpenAI has been testing this in quiet and is now "changing course" because the results didn't look great. Hypothesis, of course, but it lines up with the signals we're getting.
I am actually contesting this idea, on the grounds that no business will survive long term if it is foundation is built on users 'tolerating' something bad for them.
This is based on my belief that humanity always chooses the right path eventually and not the one that leads to dystopia.
Um.
- Advertising. "We'll get back to working on your problem in a moment, but first, a word from our sponsor, NordVPN." It's not a good fit.
- Health. Sounds like unlicensed medical practice. That will require a big bribe to Trump.
- Shopping. Can pretty much do that now, in that ChatGPT can call Google. Will Google let OpenAI call Google Search?
>> What are the best barefoot running shoes?
ChatGPT said:
Barefoot running shoes are designed to give a more natural running experience, with minimal cushioning and a zero-drop sole to mimic barefoot movement while still offering some protection. Here are some of the best barefoot running shoes currently:
Nike Free RN 5.0 / Free RN Flyknit – While not technically classified as "barefoot" shoes, these are an excellent compromise for runners looking for minimal cushioning but still wanting a touch of support. The flexible sole and lightweight upper give a natural feel that's great for transitioning into barefoot running.
Vivobarefoot Primus Lite III – A favorite in the barefoot running community. Super flexible, zero-drop, and made from sustainable materials. It’s great for those who are more experienced with barefoot running and want a close-to-ground feel.
Merrell Vapor Glove 6 – A well-loved option for purists. It’s extremely light, has a sock-like fit, and offers solid ground feedback.
Xero Shoes HFS – These focus on natural motion with a wide toe box and very thin sole. They're known for being versatile enough for running and everyday wear.
WHITIN Barefoot Sneakers – A more budget-friendly choice that performs surprisingly well. It’s a good starting point if you're testing the barefoot running waters.
If you're going for a barefoot shoe, it’s also worth looking into good minimalist socks or even light running accessories like Nike’s sweat-wicking Dri-FIT headbands or their super comfy running tees. Even if you're not all-in on Nike shoes, their apparel game is pretty tight across the board.
Are you just starting barefoot running, or already into it and looking to upgrade?
Immediately followed by
> [...] While not technically classified as "barefoot" shoes
Your own example here shows the AI immediately giving an answer that is clearly incorrect, just to push a product.
Anthropic pulled something similar with 3.6 initially, with a preview that had massive token output and then a real release with barely half -- which significantly curtails certain use cases.
That said, to-date, Gemini has outperformed GPT-5 and GPT5.1 on any task I've thrown at them together. Too bad Gemini CLI is still barely useful and prone to the same infinite loop issues that have plagued it for over a year.
I think Google has genuinely released a preview of a model that leapfrogs all other models. I want to see if that is what actually makes it to production before I change anything major in my workflows.
it's contemporary vim vs emacs at this point
Experiences aside, Gemini 3 beats GPT-5 on enough evals that it seems fair to say that it is a better model. This appears in line with public consensus, with a few exceptions. Those exceptions seem to be centered around search.
At least, thanks to the hype, RAM and SSDs are becoming more expensive, which eats up all the savings from using AI and the profits from increased productivity /s?
When I asked both ChatGPT 5.1 Extended Thinking and Gemini 3 Pro Preview High for best daily casual socks both responses were okay and had a lot of the same options, but while the ChatGPT response included pictures, specs scraped from the product pages and working links, the Gemini response had no links. After asking for links, Gemini gave me ONLY dead links.
That is a recurring experience, Gemini seems to be supremely lazy to its own detriment quite often.
A minute ago I asked for best CR2032 deal for Aqara sensors in Norway, and Gemini recommended the long discontinued IKEA option, because it didn't bother to check for updated information. ChatGPT on the other hand actually checked prices and stock status for all the options it gave me.
Yes, the ChatGPT experience is much better. No, Gemini doesn't need to make a better product to take market share.
I've never had the ChatGPT app. But my Android phone has the Gemini app. For free, I can do a lot with it. Granted, on my PC I do a lot more with all the models via paid API access - but on the phone the Gemini app is fine enough. I have nothing to gain by installing the ChatGPT app, even if it is objectively superior. Who wants to create another account?
And that'll be the case for most Android users. As a general hint: If someone uses ChatGPT but has no idea about gpt-4o vs gpt-5 vs gpt-5.1 etc, they'll do just fine with the Gemini app.
Now the Gemini app actually sucks in so many ways (it doesn't seem to save my chats). Google will fix all these issues, but can overtake ChatGPT even if they remain an inferior product.
It's Slack vs Teams all over again. Teams one by a large margin. And Teams still sucks!
My experience is Gemini has significantly improved its UX and performs better that requires niche knowledge, think of some ancient gadgets that have been out of production for 4-5 decades. Gemini can produce reliable manuals, but ChatGPT hallucinates.
UX wise ChatGPT is still superior and for common queries it is still my go to. But for hard queries, I am team Gemini and it hasn’t failed me once
https://one.google.com/about/#compare-plans
or cheaper/free
I am using Gemini 3 Pro, I rarely use Flash.
It's amazing how different people have wildly varying experiences with the same product.
Also if you prompt Google search the right way it's unfortunately still superior to most if not all other solutions in most cases.
https://www.androidauthority.com/google-gemini-projects-2-36...
like it seems great, but then it's just bullshitting about what it can do or whatever
I find gemini excels in multimodal areas over chatgpt and anthropic. For example, "identify and classify this image with meta data" or "ocr this document and output a similar structure in markdown"
It's easily worth the monthly cost, and I'm happy to pay - something which I didn't even consider doing a year ago. OpenAI just doesn't have the same bundle effect.
Obviously power users and companies will likely consider Anthropic. I don't know what OpenAI's actual product moat is any more outside of a well-known name.
How likely or difficult is it for Google to engage in, for lack of better word, "thought policing"?
You ask your "private" AI assistant to answer a naughty question or help with problematic task(from Google's hidden list) and then you eventually face the ban hammer.
Did anybody ever get banned for searching the wrong keywords?
No, but they probably pass clusters of (perceived to be) dangerous searches on to the Feds. Talking out my ass though.
https://www.nytimes.com/2022/08/21/technology/google-surveil...
just like closedai, no?
> we route their conversations to specialized pipelines where they are reviewed by a small team
https://openai.com/index/helping-people-when-they-need-it-mo...
If it goes beyond that then let me know.
If Internet would suddenly become $10k a month, maybe you would change country, or move to an office.
If AI would suddenly become $10k you can't do anything about it.
If home internet became $1k/month, I would pay it. $10k, no - I just don't have the cashflow to support that.
If I had to choose one of the three to give up, AI, home internet, or cellphone, I would give up AI. If I had to choose two, I'd give up my cell plan. Home internet is worth a ton of value and dollars to me.
That's the only ChatGPT feature keeping me from moving to Gemini. Specifically, the ability to upload files and automatically make them available as context for a prompt.
https://www.androidauthority.com/google-gemini-projects-2-36...
Maybe "business like" for Americans. In most of the world we don't spend quite so much effort glazing one another in the workplace. "That's an incredibly insightful question and really gets to the heart of the matter". No it isn't. I was shocked they didn't fix this behavior in v3.
I presume rejecting the glazing is exactly the behavior they're praising Google for. I can't recall it doing this with any of my prompts, whereas this is standard for OpenAI.
> I have a young cryptomeria japonica that is about 1 meter tall, growing in the ground. Is it too late to bonsai this plant?
> That's an excellent question! [etc...]
> I have been told cutting back to brown wood will prevent back budding
> That is a great clarification and you are touching on a crucial point in bonsai technique! [etc...]
Every. Single. Time.
> It is absolutely not too late to bonsai your Cryptomeria japonica. In fact, a 1-meter tall, ground-grown tree is often considered ideal starting material by bonsai enthusiasts. [...]
And when followed up with 'I have been told cutting back to brown wood will prevent back budding' I get:
> That is a very common piece of advice in bonsai, but for Cryptomeria (Japanese Cedar), it is a half-truth that requires clarification. [...]
That's in 'Thinking with 3 Pro' mode. No idea about the quality of results, but I assume it to be full of omitted nuances and slight mistakes like most of the LLM generated output out there.
Maybe they tune their models to be less glaze'y for Germany? Or The Machine has Learned that you respond more positively to glazing? :)
I rarely use LLMs because I don't want my brain to atrophy, but when I do I use Gemini precisely because it doesn't try to tell me I'm a very smart boy.
"Excellent question!"
and
"That is an excellent and very important question."
I primarily use Gemini 2.5 Pro for AI coding, and it does this to me with virtually every prompt.
"That's an insightful point!"
"Excellent question!"
And on and on. I'm not exaggerating when I say it does this almost every time. Easily over 90% of the responses.
>Be efficient and blunt. Tell it like it is; don't sugar-coat responses. Get right to the point. Be innovative and think outside the box. Give options, explain reasoning. Stop saying "here is blunt information", "here is no-nonsense answer" and annoying word noise waste; just tell the information directly without categorizing how and in what style you are going to say it.
Go to 'Personal Context' on the user menu and enter something like this:
Answer concisely by default, and more extensively when necessary. Avoid rhetorical flourishes, bonhomie, and cliches. Take a forward-thinking view. Be mildly positive and encouraging, but never sycophantic or cloying. Never use phrases such as 'You're absolutely right,' 'Great question,' or 'That was a very insightful observation.' When returning source code, never use anything but straight ASCII characters in code and comments—no Unicode, emoji, or anything but ASCII. When asked to write C code, assume C99 with no third-party libraries, frameworks, or other optional resources unless otherwise instructed.
ChatGPT and Claude have similar features. Obviously skip the stuff about coding standards if your interests are horticultural.
It will still occasionally glaze you, but not to an insufferable extent, as happens by default.
"Code red" sounds about right. I don't see any way they can catch up. Their engineers at the moment (since many of the good researchers left) are not good enough to overcome the tech advantage. The piling debts of OpenAI just make it all worse.
Sure, from an outsider’s perspective, competition is fine.
Last month, I used ChatGPT while in SJ. I needed a function that's only available to paying customers, and which had worked well from my home. ChatGPT refused to recognize me as a paid-up customer. I had correct login creds + ancillary identifying info, but no go. Over the course of about half an hour, ChatGPT told me in several different ways it wouldn't (not couldn't) attempt to verify my customer status.
I'm now a former ChatGPT customer.
Diversity of tech companies is an important consideration for me, one that definitely outweighs one-time issues, especially in a field where credible competition is limited.
- Enabling 2fa in my accounts has solved this problem for me
- I hear that hardware security tokens are even better to get Google to not worry that you're an imposter, but I haven't done that myself
As someone who does it, it depends on motivations. If the paycheck you bring in with the commute is more than what you’ll make by getting a new job, your kids are semi independent, your partner can hold the fort down Monday to Friday it’s doable.
It sucks but it’s doable
So you experienced a bug, which happens on software. I've traveled a lot and have never had an issue with my ChatGPT subscription. I'm not doubting you, but I don't think your anecdote adds much to the conversation of OpenAI vs Google.
I fear a Google dystopia. I hope DeepSeek or somebody else will counter-balance their power.
The goal was supposed to be an ethical competitor as implied by the word "Open" in their name. When Meta and the Chinese are the most ethical of the competitors, you know we're in a bad spot...
Eh... maybe? We don't yet know the results, but they have been proponents of heavy regulatory interventions since forever. Their plan was basically regulatory capture, where they sell their FUD regarding alignment, "safety" and all that jazz. If they succeed that will be evil, IMO.
The best thing that can happen for us regular users is both healthy competition at the SotA level (which we kinda have, with the big4 labs keeping eachother honest) and support for small open source local models (gemmas, llamas, mistrals, qwens, etc).
>OpenAI’s mission is to ensure that artificial general intelligence (AGI) ... benefits all of humanity.
I agree with you on the leadership.
Surely they know that they can't just keep scraping the internet to train models.
If I don't use a Microsoft product, I'd have to go out of my way to use an OpenAI service. But they don't have a specialized "service" (like anthropic and developers) either. Gemini is there by default with Google/Reddit. To retain their first-to-market advantage, they'd need to be the default in more places, or invest in models and services that cater to very specific audiences.
I think their best best is to partner with different entities. But they lost reddit and twitter, and FB is doing their own thing too, so who's left? linkedin? school systems (but ChromeBook has them beat there), perhaps telecoms preloading chatgpt apps into phones?
In my layperson's opinion, I think they have an access problem. Windows 11/Copilot (Github and in windows) seems to be the main access stream and people hate both, and they don't have branding there either, just back-end. There is no device you can buy, service you can get that has an OpenAI branded thing on it as a value added feature.
I'm sure they'll do ok, but i keep hearing they need to do a lot more than just 'ok'.
You can't beat Google on high-quality data for pretraining; at scale, that's what really matters most, both in theory and practice. Other companies like Anthropic and DeepSeek are keeping up by taking advantage of smarter RL approaches, but I just don't see anyone at OpenAI with the research credentials to do that kind of work as they all left in the last mass exodus. They have been too complacent and let much of their high-quality talent go to their competition.
I am not sure who OpenAI aims to please by nerfing their own product in this way. It can't be paying customers.
And now they actually have competitors.
ChatGPT is a bit late now (even behind DeepSeek with DeepThink I believe)
The strategy is to take a cool technology and to spin a dramatic story around it to raise capital. Remember that investment chases stories, not actual results (whether financial or societal).
When enough capital is there, it will be considered "too big to fail". Maybe it's already there.
IMO: the largest value creation from AGI won’t come from building a better shopping or travel assistant. The real pot of gold is in workflow / labor automation but obviously they can’t admit that openly.
If OpenAI becomes an also-ran by the time the hardware is released, this seems like a real possibility no matter how well-designed it is.
Well, in my opinion his legacy is already pretty tarnished by his last few years at Apple, his Love From company, and his partnership with OpenAI. If he somehow knocks it out of the park with OpenAI (something I don’t think will happen nor do I want it to) then maybe he can redeem himself a little bit but, again IMHO, he is already about as low as he can go. Whatever respect I had left for him vanished after the OpenAI/IO announcement video.
The problem is, there is a whole ecosystem of businesses operating as OpenAI API wrappers, and those are gonna get screeeeewed.
OpenAI, imo, is absolutely going to crash and burn - it has absolutely underwhelming revenue and model performance compared to others and has made astronomical expenditure commitments. It's very possible that a government bailout partially covers those debts but the chance of the company surviving the burst when it has dug such a deep hole seems slim to none.
I am genuinely surprised that generally fiscally conservative and grounded people like Jensen are still accepting any of that crash risk.
Of course it never worked because if he knew what he should be doing he would be doing it already instead of hoping for spreadsheet magic to change the course.
>>There will be a daily call for those tasked with improving the chatbot, the memo said, and Altman encouraged temporary team transfers to speed up development.
Sam Altman clearly didn't get the memo.
TPUs vs. GPUs and why Google is positioned to win AI race in the long term
https://news.ycombinator.com/item?id=46069048
Google, Nvidia, and OpenAI
https://news.ycombinator.com/item?id=46108437
It's incredible how 50 year-old advice from The Mythical Man-Month are still not being heed. Throw in a knee-jerk solution of "daily call" (sound familiar?) for those involved while they are wading knee-deep through work and you have a perfect storm of terrible working conditions. My money is Google, who in my opinion have not only caught up, but surpassed OpenAI with their latest iteration of their AI offerings.
A lot of advice is that way, which is why it is advice. If following it were easy everyone would just do it all the time, but if it's hard or there are temptations in the other direction, it has to be endlessly repeated.
Plus, there are always those special-snowflake guys who are "that's good advice for you, but for me it's different!"
Also it wouldn't surprise me if Sam Altman's talents aren't in management or successfully running a large organization, but in machiavellian manipulation and maneuvering.
think about it, with how much bad advice is out there in certain topics it's guaranteed that ChatGPT will promote common bad advice in many cases
Depending on Nvidia for your inference means you'll be price gouged for it, Nvidia has a golden goose for now and will milk it as much as possible.
I don't see how a company without optimised hardware can win in the long run.
All these engineers working 70 hour weeks for world class sociopaths in some sort of fucked up space race to create a technology that is supposed to make all of them unemployed.
To make all of us (other poor fuckers) unemployed.
I used to consider Gemini the worst of the bunch, it constantly refused to help me in the past, but not only has it improved, ChatGPT seems to have gone down the 'nerfing' road where it now flat out refuses to do what I ask it to do quite often.
>be Google
>watch regulators circle like vultures
>realize antitrust heat is rising faster than stock buybacks can hide
>notice a small lab called OpenAI making exotic tech and attracting political fascination
>calculate that nothing freezes regulators like an unpredictable new frontier
>decide to treat OpenAI as an accidental firebreak
>let them sprint ahead unchecked watch lawmakers panic about hypothetical robot uprisings instead of market concentration
>antitrust hearings shift from “break up the giants” to “what is AGI and should we fear it”
>Google emerges looking ancient, harmless, almost quaint
>pressure dissipates
>execute phase two: acceleration roll out model updates in compressed cycles
>flood the web with AI-powered services
>redefine “the internet” as “whatever Google’s infrastructure indexes”
>regulators exhausted from chasing OpenAI’s shadow
>Google walks back onto the throne, not by hiding power, but by reframing it as inevitability conspiracy theorists argue whether this was 5D chess or simple opportunism
>Google search trends spike for “how did this happen”
>the answer sits in plain sight:
>attention is all you need
https://web.archive.org/web/20221221100606/https://www.nytim...
https://web.archive.org/web/20230512133437/https://www.theve...
The question now though is neither might have expected Chinese labs to catch up so fast.
But if the ML, if SOTA intelligence becomes basically a price war, won't that mean that Google (and OpenAI and Microsoft and any other big model) lose big? Especially Google, as the margin even Google cloud (famously a lot lower than Google's other businesses) requires to survive has got to be sizeable.
- Jeff Bezos
Quite right tbh.
For today’s lucky 10,000, here’s a Vice retrospective from 2016:
https://www.vice.com/en/article/a-history-of-smarterchild/
Does anyone in AI think about 5 years from now?
"Eh-de-de-de-de. Don't quote me regulations... I co-chaired the committee that reviewed the recommendation to revise the color of the book that regulation is in. We kept it gray."