MikeTheGreat 12 hours ago

(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!

  • nodja 10 hours ago

    > Genuine question: How is it possible for OpenAI to NOT successfully pre-train a model?

    The same way everyone else fails at it.

    Change some hyper parameters to match the new hardware (more params), maybe implement the latest improvements in papers after it was validated in a smaller model run. Start training the big boy, loss looks good, 2 months and millions of dollars later loss plateaus, do the whole SFT/RL shebang, run benchmarks.

    It's not much better than the previous model, very tiny improvements, oops.

    • yalok 4 hours ago

      add to it multiple iterations of having to restart pretraining from some earlier checkpoint when loss plateaus too early or starts increasing due to some bugs…

    • thefourthchime 9 hours ago

      Isn't that what GPT 4.5 was?

      • wrsh07 8 hours ago

        That was a large model that iiuc was too expensive to serve profitably

        Many people thought it was an improvement though

  • encomiast 11 hours ago

    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.

    • MikeTheGreat 10 hours ago

      Ah. Thanks for posting - this makes a lot of sense.

      I can totally see how they're able to pre-train models no problem, but are having trouble with the "noticeably better" part.

      Thanks!

    • mudkipdev 11 hours ago

      OpenAI allegedly has not completed a successful pretraining run since 4o

  • cherioo 12 hours ago

    GPT4.5 was allegedly such a pre-train. It just didn’t perform good enough to announce and product it as such.

    • htrp 11 hours ago

      it wasn't economical to deploy but i expect it wasn't wasted, expect the openai team to pick that back up at some point

      • mips_avatar 10 hours ago

        The scoop Dylan Patel got was that part way through the gpt4.5 pretraining run the results were very very good, but it leveled off and they ended up with a huge base model that really wasn't any better on their evals.

  • octoberfranklin 12 hours ago

    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.

    • MikeTheGreat 10 hours ago

      Huh - I did not know that, and that makes a lot of sense.

      I guess "Start software Vnext off the current version (or something pretty close)" is such a baseline assumption of mine that it didn't occur to me that they'd be basically starting over each time.

      Thanks for posting this!

cmiles8 15 hours ago

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.

  • an0malous 15 hours ago

    > 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.

    • abixb 12 hours ago

      >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.

    • willis936 14 hours ago

      This would trigger something that people in power would rather not trigger.

      • johncolanduoni 5 hours ago

        The shenanigans that set off the GFC were much more nakedly corrupt and didn’t have even a fig leaf of potential usefulness to anybody to justify them. The revolution failed to materialize then. If the AI bust isn’t worse for the median person than 2008, I don’t think people in power have anything to fear.

        • immibis an hour ago

          Why do we think it won't be worse? If you don't count AI companies we're already in a pretty big recession.

      • bibimsz 13 hours ago

        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.

      • watwut 13 hours ago

        Nah, people in power are openly and blatantly corrupt and it does a little. People in power dont care and dont have to care.

    • mywittyname 15 hours ago

      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.

    • immibis an hour ago

      It will be the biggest bailout in history and financed entirely by money printing at a time when the stability of the dollar is already being questioned, right? Not good.

  • qnleigh 14 hours ago

    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.

    • originalvichy 12 hours ago

      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.

    • cmiles8 12 hours ago

      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.”

      • qnleigh 8 hours ago

        Interesting. And these people weren't mostly techies? My impression has been that the further someone is from tech, the more likely they are to think that ChatGPT is synonymous with LLMs.

        • egillie 3 hours ago

          I'm seeing it outside of techies. My dad told me "AI Google said that..."

    • Tycho 12 hours ago

      They integrated it into Google search immediately so I think a lot of people will bother less with ChatGPT when a google search is just as effective.

    • nateglims 12 hours ago

      I think the theory is if you get to that point, it's already over.

  • turnsout 14 hours ago

    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."

    • 0xbadcafebee 14 hours ago

      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).

    • BryanLegend 11 hours ago

      Helping to prevent a possible skynet scenario probably makes those checks easier to write.

      There's a lot more than money at stake.

    • turtletontine 12 hours ago

      > 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!

  • daxfohl 15 hours ago

    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.

  • jiggawatts 6 hours ago

    Did Google actually train a new model? The cutoff dates for Gemini 3 and 2.5 are the same.

    • aix1 5 hours ago

      I think this simply suggests the same (or very similar) training corpora.

      • jiggawatts 2 hours ago

        Surely, they would throw current events, news articles, the latest snapshot of WikiPedia, etc...

        I can't imagine it making sense to purposefully neglect to keep a model as up-to-date as possible!

  • dist-epoch 15 hours ago

    So why did Google stock increase massively since about when Gemini 2.5 Pro was released, their first competitive model?

    • raw_anon_1111 14 hours ago

      That’s not evidence of anything in and of itself. RIMs stock price was at its highest in 2009 two years after the iPhone came out.

      • davidnc 10 hours ago

        I was curious about this - if my Google results are accurate, it looks like the stock actually peaked in June 2007, the same month that the iphone was released.

        It seems that Blackberry's market share of new phone sales peaked at 20% in 2009. So I'm not sure if it's coincidence, but it looks like the market actually did a pretty good job of pricing in the iphone/android risk well before it was strongly reflected in sales.

        • raw_anon_1111 10 hours ago

          You are correct. I remember the anecdote as something peaking. I thought it was the stock price. It was actually market share

    • hiddencost 12 hours ago

      Because Google already has many healthy revenue streams that will benefit from LLMs and all it has to do in the AI space is remain competitive.

  • numbers_guy 15 hours ago

    Yep, I thought they might have some secret sauce in terms of training techniques, but that doesn't seem to be the case.

danielodievich 11 hours ago

Last week there we had a customer request that landed in our support on a feature that I partially wrote and wrote a pile of public documentation on. Support engineer ran customer query through Claude (trained on our public and internal docs) and it very, very confidently made a bunch of stuff up in the response. It was quite plausible sounding and it would have been great if it worked that way, but it didn't. While explaining why it was wrong in a Slack thread with support engineer and another engineer who also worked on that feature, he ran Augment (that has full source code of the feature) which promptly and also very confidently made up more stuff (but different!). Some choice bleeding eye emojis were exchanged. I'm going to continue to use my own intelligence, thank you.

  • kristianp 9 hours ago

    How is that comment relevant to this story about OpenAI's response to perceptions that Google has gained in market share?

    • varenc 9 hours ago

      Popular HN threads about anything AI related always attract stories highlighting AI failures. It's such a common pattern I want to analyze it and get numbers. (which might require AI...)

      • Yeask 8 hours ago

        Popular HN threads about anything AI related always attract stories highlighting AI success. It's such a common pattern I want to analyze it and get numbers. (which might require to use my brain...)

    • raincole 9 hours ago

      Welcome to Hacker News. You're allowed to post anti-AI, anti-Google or anti-Musk content in any thread. /s

  • oersted an hour ago

    Relying on the model’s own “memory” to answer factual queries is almost always a mistake. Fine-tuning is almost always a more complex, more expensive and less effective method to give a model access to a knowledge base.

    However using the model as a multi-hop search robot, leveraging it’s general background knowledge to guide the research flow and interpret findings, works exceedingly well.

    Training with RL to optimize research tool use and reasoning is the way forward, at least until we have proper Stateful LLMs that can effectively manage an internal memory (as in Neural Turing Machines, and such).

  • ramraj07 2 hours ago

    "trained on our public and internal docs" trained how? Did you mean fine-tuned haiku? Did you actually fine tune correctly? Its not even a recommended architecture.

    Or did you just misuse basic terminology about LLMs and are now saying it misbehaved, likely because your org did something very bad with?

  • pshirshov 9 hours ago

    All depends on the tasks and the prompting engineers.

    Even with your intelligence you would need years to deliver something like this: https://github.com/7mind/jopa

    The outcome will be better for sure, but you won't do anything like that in a couple of weeks. Even if you have a team of 10. Or 50.

    And I'm not an LLM proponent. Just being an empirical realist.

  • tomp 10 hours ago

    I don't know man.

    My code runs in 0.11s

    Gemini's code runs in 0.5s.

    Boss wants an explanation. ¯\_(ツ)_/¯

    • loloquwowndueo 9 hours ago

      As long as the explanation is going to come out being wrong, I’m sure you can whip something up in 0 seconds.

    • brazukadev 9 hours ago

      0.11s is faster than 0.5s

      • tomp 4 hours ago

        Yeah that’s the point. Now instead of just writing good code, I’m also supposed to debug shitty AI code.

      • gmzamz 9 hours ago

        Boss is using ai. 11 is clearly bigger than 5

  • scotty79 11 hours ago

    Yeah, LLMs are not really good about things that can't be done.

    At some point you'll be better off with implementing features they hallucinated. Some people with public APIs already took this approach.

    • AdieuToLogic 10 hours ago

      >> Support engineer ran customer query through Claude (trained on our public and internal docs) and it very, very confidently made a bunch of stuff up in the response.

      > Yeah, LLMs are not really good about things that can't be done.

      From the GP's description, this situation was not a case of "things that can't be done", but instead was the result of a statistically generated document having what should be the expected result:

        It was quite plausible sounding and it would have been 
        great if it worked that way, but it didn't.
      • verdverm 2 hours ago

        The core issue is likely not with the LLM itself. Given sufficient context, instructions, and purposeful agents, a DAG of these will not produce such consistently wrong results with good grounding context

        There are a lot of devils in the details and there are few in the story

    • 131hn 10 hours ago

      They are trained with 100% true facts and sucessfull paths.

      We humans grec our analysis/reasoning skills towards the 99.9999% failed attempts of everything we did, uncessfull trials and errors, wastefull times and frustrations.

      So we know that behind a truth, there’s a bigger world of fantasy.

      For LLM, everything is just a fantasy. Everything is as much true as it’s opposite. It will need a lot more than the truth to build intelligence, it will require controled malice and deceptions

      • antinomicus 10 hours ago

        I was with you until the very last line, can you expand on that?

rappatic 19 hours ago

> 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.

  • whiplash451 19 hours ago

    The bottleneck isn’t the people doing the work but the leadership’s bandwidth for strategic thinking

    • kokanee 18 hours ago

      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.

      • stanford_labrat 16 hours ago

        chatgpt making targeted "recommendations" (read ads) is a nightmare. especially if it's subtle and not disclosed.

      • cortesoft 15 hours ago

        Exactly. This is more about “the product isn’t good enough yet to survive the enshittification effect of adding ads.”

    • tiahura 18 hours ago

      How is strategic thinking going to produce novel ideas about neural networks?

      • ceejayoz 18 hours ago

        The strategic thinking revolves around "how do we put ads in without everyone getting massively pissed?" sort of questions.

    • sien 15 hours ago

      If only they had a tool that they claim could help with things like that....

  • techblueberry 18 hours ago

    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?

    • tim333 17 hours ago

      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.

      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...

    • jinushaun 18 hours ago

      If that was the case, MS would be on top given how entrenched Windows, Office and Outlook are.

      • techblueberry 18 hours ago

        I'm not suggesting that OpenAI write shit integrations with existing ecosystems.

  • logsr 18 hours ago

    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.

  • ma2rten 19 hours ago

    Delaying doesn't necessarily mean they stop working on it. Also it might be a question of compute resource allocation as well.

  • jasonthorsness 19 hours ago

    ha what an incredible consumer-friendly outcome! Hopefully competition keeps the focus on improving models and prevents irritating kinds of monetization

    • another_twist 19 hours ago

      If there's no monetization, the industry will just collapse. Not a good thing to aspire to. I hope they make money whilst doing these improvements.

      • Ericson2314 18 hours ago

        If people pay for inference, that's revenue. Ads and stuff is plan B for inference being too cheap, or the value being too low.

      • thrance 18 hours ago

        If there's no monetization, the industry will just collapse, except for Google, which is probably what they want.

      • gaigalas 16 hours ago

        > the industry will just collapse

        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.

    • apparent 16 hours ago

      Just like uber rides funded by VC cash was great...until the VC money ran out and prices jumped to fill the gap.

      • raducu 3 hours ago

        the prices jumped and uber is now profitable, I think that's the future for AI as well -- some will fail, but eventually some will be profitable.

    • crazygringo 11 hours ago

      If they don't start on ads and shopping, they're going to go out of business.

      I'd rather a product that exists with ads, over one that's disappeared.

      The fact is, personal subscriptions don't cover the bills if you're going to keep a free tier. Ads do. I don't like it any more than you do, but I'm a realist about it.

  • rob74 18 hours ago

    I for one would say, the later they add the "ads" feature, the better...

    • saintfire 15 hours ago

      Eh, get the enshittification done sooner than later so people aren't fooled into thinking it's actually worth anyone's time.

  • ronnier 16 hours ago

    >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

lateforwork 14 hours ago

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.

  • techblueberry 12 hours ago

    "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.

  • greedo 14 hours ago

    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.

    • __turbobrew__ 12 hours ago

      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.

    • Tycho 12 hours ago

      Commitments here means money that people have agreed to lend them in future.

      • staticman2 8 hours ago

        Does it mean have agreed to lend them in a binding agreement that OpenAI can sue to enforce?

  • BeFlatXIII 13 hours ago

    I'm hoping for Congressional gridlock to save us from bailing out a cascading failure. The harder it hits, the better.

  • sholain 4 hours ago

    "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,"

    No, there's a not of noise about this but these are just 'statements of intent'.

    Oracle very intimately understands OpenAI's ability to pay.

    They're not banking $50B in chips and then waking up naively one morning to find out OpenAI has no funding.

    What will 'cascade' is maybe some sentiment, or analysts expectations etc.

    Some of it, yes, will be a problem - but at this point, the data centre buildout is not an OpenAI driven bet - it's a horizontal be across tech.

    There's not that much risk in OpenAI not raising enough to expand as much as it wants.

    Frankly - a CAPEX slowdown will hit US GDP growth and freak people out more than anything.

  • maxilevi 14 hours ago

    most of them are non binding letters of intent, i don't think it's as trite as you put it

    • caminante 14 hours ago

      The government bailout part doesn't even kick in until they sink enough to need trillions of annual revenue.

      Skepticism is easy.

  • PantaloonFlames 7 hours ago

    At first I read “enormous longterm commitments” as customers committing to OpenAI. But you are saying it’s the reverse.

  • scrollop 13 hours ago

    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.

  • pphysch 14 hours ago

    Last week's announced Genesis Mission from the Department of Energy could be the vehicle for this bailout.

    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.

    • strtok 14 hours ago

      Privatize gains, socialize losses.

  • ur-whale 14 hours ago

    > 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.

  • ijidak 13 hours ago

    Isn't the NVIDIA-TSMC duopoly the problem here?

    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?

    • layer8 11 hours ago

      Because it would take many years, and Google is using its own TPUs anyway.

TechRemarker 16 hours ago

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.

  • hodgehog11 15 hours ago

    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.

    • dudeinhawaii 15 hours ago

      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.

    • verdverm 15 hours ago

      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

      it's contemporary vim vs emacs at this point

      • hodgehog11 13 hours ago

        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.

    • bdhtu 15 hours ago

      What do you mean? It renders LaTex fine on Android.

      • hodgehog11 15 hours ago

        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.

      • null_deref 15 hours ago

        I had a problem where ChatGPT rendered math to me from right to left. Sure thing YMMV

    • kristofferR 15 hours ago

      Try doing some more casual requests.

      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.

    • croes 15 hours ago

      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?

  • karmasimida 14 hours ago

    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

  • BeetleB 14 hours ago

    > 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!

  • binarymax 15 hours ago

    Benchmaxxing galore by lots of teams in this space.

    • emp17344 15 hours ago

      I think it’s entirely possible that AI actually has plateaued, or has reached a point where a jump in intelligence comes at the cost of reliability.

      • hugh-avherald 15 hours ago

        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.

        • hodgehog11 15 hours ago

          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.

      • lukan 15 hours ago

        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.

  • pohl 15 hours ago

    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.

  • doug_durham 14 hours ago

    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.

  • kranke155 15 hours ago

    Gemini comes with the 1.99 Google One plan. So I use that

    • BeetleB 14 hours ago

      Actually, it comes with the free plan. The $1.99 plan doesn't give you any more AI capabilities. Only at the $19.99/mo plan do you get more.

      https://one.google.com/about/#compare-plans

      • kranke155 2 hours ago

        Well then the usage is already so useful in Free mode that I didn’t even notice it. “Thinking ” has a meaningful cap. But I have not felt the need to pay for more. I pay for Claude.

  • xnx 15 hours ago

    > So Gemini would have to be drastically better answer wise than ChatGPT to lure users from a better UI/UX experience to Gemini.

    or cheaper/free

  • lanthissa 15 hours ago

    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.

    • tmaly 13 hours ago

      I did notice a bug on the iPhone, even with app background refresh, if the phone shuts off the screen, a prompt that was processing stalls out.

  • tapoxi 16 hours ago

    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 am using Gemini 3 Pro, I rarely use Flash.

  • golfer 16 hours ago

    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.

    • embedding-shape 15 hours ago

      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.

      • jiggawatts 6 hours ago

        It’s the equivalent of the user that points at their workstation tower and exclaims that the “hard drive is broken!”

        Use the right words, get the right response.

        Ah… ahhh… I get now why they get such bad results from AI models.

    • dudeinhawaii 15 hours ago

      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.

    • bdbdbdb 15 hours ago

      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

    • _whiteCaps_ 14 hours ago

      The same thing happens to me in Claude occasionally. I have to tell it "Generate a tar.gz archive for me to download".

  • par 15 hours ago

    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.

  • r_lee 15 hours ago

    I'm confused as well, it hallucinated like crazy

    like it seems great, but then it's just bullshitting about what it can do or whatever

  • potsandpans 15 hours ago

    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"

  • j45 15 hours ago

    Training and gaming for the benchmarks is different than actual use.

  • jiggawatts 16 hours ago

    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!

    • threecheese 15 hours ago

      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).

    • observationist 16 hours ago

      Google search is awful. I don't think they can put lipstick on that particular pig and expect anyone to think it's beautiful.

      • coppsilgold 14 hours ago

        I'm sure they give their AI models a superior search than they give to us.

        Also if you prompt Google search the right way it's unfortunately still superior to most if not all other solutions in most cases.

  • mrcwinn 15 hours ago

    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.

achow 15 hours ago

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.

  • lanthissa 15 hours ago

    if you want to compete with google it seems like ad space is the single most important thing to push out quickly.

    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.

    • AlexCoventry 8 hours ago

      OpenAI is trying to revolutionize human industry. The money it can make from ads will be a rounding error, if they can pull that off.

      • dmead 5 hours ago

        People who believe this should be studied

        • johncolanduoni 5 hours ago

          Well, they didn’t say OpenAI was right. I think that a lot of the people working there believe that. It was kind of built into the original corporate/non-profit structure (that they since blew up).

    • jazzyjackson 13 hours ago

      If their endgame is competing with other ad brokers, what was all that talk of AGI for?

  • simonsarris 10 hours ago

    Didn't they announce all kinds of other things? A social network like X, and a browser, at least.

  • clickety_clack 15 hours ago

    100%. Especially if it’s just ads and a new Siri/Alexa that they’ve got cooking.

    • rpastuszak 15 hours ago

      Advertising, especially with LLMs/chat bots, is a dangerous mixture.

  • trhway 15 hours ago

    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.

    • tjwebbnorfolk 15 hours ago

      Google definitely made errors, but it looks like it got them out of its system early in the game. They've been killing it since the summer.

      • vessenes 13 hours ago

        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.

  • echelon 15 hours ago

    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.

    • spiralpolitik 13 hours ago

      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".

      • energy123 11 hours ago

        > There is no moat in the models.

        I guess that's mostly true, but why does Jane Street get to have a moat in models but LLM companies can't? It feels like a structurally similar situation. The critical mass of research talent is somewhat of a moat in itself.

        • chroma205 4 hours ago

          > I guess that's mostly true, but why does Jane Street get to have a moat in models but LLM companies can't?

          Common misconception by people outside quant trading.

          Modern “alpha” in trading does not come from better models but rather business connections with exchanges and regulators for preferential fees and/or revenue agreements.

          If you are a “lead market maker” like Jane Street for ETFs, you can effectively skip the FIFO queue that retail traders and large passive index funds (VTI, VOO) must wait in.

          Citadel has exclusive contracts to execute PFOF trades with e.g. Schwab. Even a simple exponential moving average model can be profitable with such a business arrangement.

          OpenAI and Sam Altman tried to cut a deal (threaten?) with the US government, but looks like US government called Sam’s bluff.

    • gausswho 15 hours ago

      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.

      • shkkmo 14 hours ago

        > 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.

      • echelon 14 hours ago

        If they swing and miss with advertising, they have less time.

    • freediver 14 hours ago

      > - 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.

      • echelon 14 hours ago

        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.

  • Animats 15 hours ago

    > advertising, AI agents for health and shopping,

    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?

    • ori_b 14 hours ago

      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?

      • Peritract 12 hours ago

        > What are the best barefoot running shoes?

        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.

        • ori_b 6 hours ago

          Yep. Exactly. It won't be obvious, clearly marked ads, but subtle biases, skew, and placement of slightly misplaced products in answers.

          You seem to think I want this future. I'm merely making a prediction on the most profitable, and thus most likely, way to advertise with an LLM.

sometimes_all 18 hours ago

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.

  • adrr 9 hours ago

    Gemini also will answer most queries where ChatGpt won't do a lot of things. Example: "Create an image of Snow white". This will give the stand "Violates our content policy" even though the story was written hundreds of years ago. You can even point out the story is in the public domain and it still won't do it.

    I remember when it wouldn't even give me the lyrics to the star spangled banner. https://news.ycombinator.com/item?id=44832990#44833365

  • venusenvy47 15 hours ago

    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.

    • beAbU 2 hours ago

      From what I can see the 2TB AI pro and 5TB (non AI) are the same, except the google drive storage.

      The difference between the AI and non-AI 2TB plan is 1000 AI "credits" (tokens?) vs 200. €120 p/a difference between the two for me which is huge.

    • sometimes_all 8 hours ago

      Yeah it was an absolute nightmare trying to figure out the difference, and I still do not know the correct answer to this, and by the looks of it, neither does Google support, because they were as clueless as I was when I asked them about it.

      One thing I read on a reddit thread [1] was that the AI pro 2 TB plan explicitly allows sharing the AI and storage benefits when you enable family sharing on them, while the 5 TB plan doesn't.

      However, when I went to sign up, the 5 TB plan wasn't available at all! It's only their lite and basic plans (the one with 30 and 100 GB of storage); the 5TB one only showed up after I signed up for the pro plan, and judging by how the UX looked, you pay an extra amount on top of your AI pro plan.

      Now I definitely need family sharing, but I don't need the full 2 TB, let alone 5 TB, so I didn't bother checking further about the 5TB plan.

      Also, I am in India, maybe things are different in your region?

      [1] https://www.reddit.com/r/GoogleOne/comments/1nib21a/solved_g...

  • piva00 18 hours ago

    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.

  • OutOfHere 16 hours ago

    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.

    • beAbU 2 hours ago

      This has never happened to me in more than 5 years of paying for Google Drive. And my drive is chock full of bootleg books and movies and stuff.

      Having said that, an offline backup of a couple of terabytes will rarely break the bank and is not a bad idea at all.

      I probably need to get on that.

      • OutOfHere an hour ago

        It happens more with adult content or files misclassified as such. It has happened to people.

        Secondly, a Google account can be disabled for a broader variety of reasons, not limited to the above causes.

    • sometimes_all 7 hours ago

      I agree with you 100%. We do syncs to another non-google storage account anyway, plus the google accounts are primarily for Android phone usage because photos and videos take up quite a big chunk of space now; they do not have any legitimately important files stored outside of photos sync and phone backups, so there is no deep loss if the account gets banned outside of some inconveniences.

    • devsda 16 hours ago

      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?

      • staticman2 6 hours ago

        If Google is smart they'd ban Gemini access while leaving services like Gmail enabled because otherwise customers wouldn't trust them and would avoid Gemini.

        I don't think there's any reports of banning from all Google services based on Gemini use.

      • Andrex 15 hours ago

        > 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.

    • acuozzo 5 hours ago

      Solution: Use Google Drive to backup a VeraCrypt volume?

    • throwacct 16 hours ago

      Which product do you recommend? OneDrive? Dropbox?

      • pcchristie 9 hours ago

        Filen is quite good, is E2E encrypted and currently offering (final round of) lifetime plans for Black Friday.

        They are not super mature yet (though have been around for several years) so the product still has some improvements to be made, but I like it.

      • mattmaroon 15 hours ago

        I have to imagine they are all on the lookout for CSAM. They’d simply have to be.

        If it goes beyond that then let me know.

        • OutOfHere an hour ago

          There is no evidence that any storage service that offers E2E encryption does any scanning of adult content.

          Note that possessing significant adult content in non-E2E storage risks eventual misclassification by a bot.

      • [removed] 14 hours ago
        [deleted]
  • carlosjobim 15 hours ago

    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.

    • sometimes_all 8 hours ago

      > With that in consideration they should mostly be compared on quality

      Take a look at the comments in the thread and tell me whether there is a consensus on which AI has the best "quality". Gemini, Claude, ChatGPT are all stochastic machines; they'll give me a different output at different times for the very same query, with differences in quality each time within themselves, let alone other products.

      I did my own checks; newer Gemini's output is consistently "good enough" for me and my family now, we individually do not use the full extent of the Pro plan (collectively, we do), and NotebookLM is something which more than one of us uses everyday; Image generation is something we use once a week or so. Given all this, the feature breadth within Gemini covers all bases for us, with a significant catch-up in quality compared to earlier to a point that we don't really need to look elsewhere for now.

      Plus, for us USD 20 is not a small amount; it's equivalent to one of our larger utility bills we need to pay for every month. So price is definitely an important point of consideration.

    • aftbit 15 hours ago

      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.

      • mattmaroon 15 hours ago

        I don’t know, I ditched my ISP of many years as soon as a better option came up, even though it cost more, because it is much higher quality.

      • dist-epoch 14 hours ago

        Home internet and cell phones are fungible. AI is not.

        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.

        • aftbit 11 hours ago

          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.

redbell an hour ago

The current situation of OpenAI is difficult. At present time, even the giants (Meta, MS, Apple, AMZN) with deep pockets would find it extremely challenging to compete against Google in the AI race, let alone a VC-funded startup.

•Google has data, a lot of private data actually (YT, Gmail, Workspace, Search Queries.. you name it) •Google has a lot of money •Google has top-talented AI engineers (Eying on DeepMind & Demis Hassabis staff) •Google has a huge userbase

With $20B in ARR and hundreds of billions in funding, would OpenAI be able to make its own remontada as Google did? I'm not sure, but it would be a long challenging journey.

  • mvcosta91 42 minutes ago

    They also control their own hardware stack with TPUs.

curioussquirrel 4 hours ago

This is probably not a core concern for most HN readers, but at work we do multilingual testing for synthetic text data generation and natural language processing. Emphasis on multilingual. Gemini has made some serious leaps from 1.5 to 2.5 and now 3.0, and is actually proficient in languages that other models can only dream of. On the other hand, GPT-5 has a really mixed performance in a lot of categories.

  • jimmydoe 2 hours ago

    Very good to know. I use Gemini for many translation related work, the 1m windows is very helpful too.

zhyder 8 hours ago

It's all about the chip economics. I don't know how the _manufacturing cost_ of Google's TPUs compares to Nvidia's GPUs, for inference of equivalent token throughput.

But at the moment Nvidia's 75-80% gross margin is slowly killing its customers like OpenAI. Eventually Nvidia will drop its margins, because non-0 profit from OpenAI is better than the 0 it'll be if OpenAI doesn't survive. Will be interesting to see if, say, 1/3 the chip cost would make OpenAI gross margin profitable... numbers bandied in this thread of $20B revenue with $115B cost imply they need 1/6 the chip cost, but I doubt those numbers are right (hard to get accurate $ numbers for a private company for the benefit of us arm-chair commenters).

  • mrtksn 6 hours ago

    Yes, from the first principles perspective this AI thingy is just about running electricity through some wires printed on silicon by a Taiwanese company using a Dutch machine. Which means, up until the Taiwanese you have plenty of room to cut margins up until that point the costs are mostly greed based. That is Nvidia is asking for the highest price the customer can pay and they have quite a way to the cost that define their min price. Which means AI companies can actually keep getting better deals until the devices delivered to them are priced close to TSMCs bulk wafer printing prices.

Phelinofist 19 hours ago

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.

  • energy123 11 hours ago

    I've found Gemini 3.0 Pro to be bad at multi turn conversation and instruction following. It ignores your follow up question unless you draw attention to it with caps or something.

    Not a major complaint for technical work where you don't even want to do much multi turn conversation. Just an observation.

  • cj 18 hours ago

    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.

  • mvdtnz 17 hours ago

    > [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.

    • Phelinofist 3 hours ago

      Not quite - I'm German :P

      But as a sibling has said, the "super nice question homie" texts are not coming (as much) in Gemini as in ChatGPT (for me). I know that you can tune ChatGPTs persona, but that changed also the answer quality for me for the worse.

    • MangoToupe 16 hours ago

      > 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.

      • mvdtnz 15 hours ago

        I'm a daily user of Gemini. I get this glazing every single time. This is my very last interaction with Gemini (edited for brevity),

        > 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.

  • devnullbrain 12 hours ago

    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.

gherkinnn 2 hours ago

I remember, maybe 2-3 years ago, chuckling at Google with their Bard naming and being late to the game and so on. It seems like I was very wrong and that they caught up quickly enough. I was also wrong in thinking MS doing well, when their recent Copilot moves across Office, Windows, and GitHub have been a joke.

paxys 10 hours ago

I think we are finally seeing the effects of the steady stream of departures of top researchers and leaders from OpenAI since last year. Sure you can declare a "code red", but who is going to lead the effort? Set the direction? Do the heavy lifting? Chart the path forward? Sam Altman is a salesman, not a researcher. Ilya is no longer around. Most of the other top brass has been poached by Google/Meta/Anthropic or left to start their own thing. The people left behind are probably good at iterating, but can they really make the next leap forward on their own?

poemxo 13 hours ago

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.

  • greenchair 13 hours ago

    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.

badmonster 16 hours ago

"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.

  • hodgehog11 15 hours ago

    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.

    • tim333 15 hours ago

      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.

  • aftbit 15 hours ago

    "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.

    • devnullbrain 12 hours ago

      People who only care about this quarter don't donate to a non-profit in the hopes it turns into an investment in a private company.

  • m-schuetz 16 hours ago

    Yeah, but now it's questionable whether the insane investments will ever pay off.

  • Andrex 15 hours ago

    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.

    • eden-u4 15 hours ago

      Also, they have all the infra to actually use all that tpus advantage (as well as actual researchers, contrariwise to OpenAI)

      • laluser 15 hours ago

        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.

    • laluser 15 hours ago

      OAI is already working on shipping their own chips.

      • Andrex 15 hours ago

        True, but Google's been making them for 10 years, which subjectively feels like a long time in tech.

  • skybrian 15 hours ago

    Declaring a “code red” seems to be a direct result of strong competition?

    Sure, from an outsider’s perspective, competition is fine.

notepad0x90 15 hours ago

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'.

  • hodgehog11 15 hours ago

    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.

qoez 15 hours ago

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.

  • SXX 15 hours ago

    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.

    And now they actually have competitors.

  • rvnx 15 hours ago

    Google (generalist/media) > Anthropic (code) > x.AI (excellent price/quality balance).

    ChatGPT is a bit late now (even behind DeepSeek with DeepThink I believe)

bilekas 3 hours ago

> Altman said the company will be delaying initiatives like ads, shopping and health agents, and a personal assistant, Pulse, to focus on improving ChatGPT

It's so telling that they're delaying these "festures" because the know full well people don't want them.

  • apples_oranges 3 hours ago

    I don't understand this view. I think most people would be happy to use the best models for free in exchange for seeing ads. That's basically what google and many others successfully do for decades.

    • bilekas 2 hours ago

      Because it will degrade experience entirely, and companies always go too far with it. Advertisement online these days is so intrusive it's a slog to browse without some form of adblocker.

      When the AI starts suggesting products or services without being straight up about it, it's not giving you 'knowledge' it's just feeding you whatever it's been paid to say. If that's what you want, power to you.

      • apples_oranges 35 minutes ago

        Yes I agree (and personally avoid ads where I can with blocking or using paid subscriptions) but many or most people will still accept that deal.

    • [removed] 2 hours ago
      [deleted]
alecco 18 hours ago

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.

  • bryanlarsen 18 hours ago

    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...

    • alecco 18 hours ago

      I said DeepSeek because they are very open (not just weights). A young company and very much unlike Chinese Big Tech and American Big Tech.

    • epiccoleman 16 hours ago

      Without having followed the issue of "AI Ethics" that closely, Anthropic seems to me to be relatively non-evil, too.

      • NitpickLawyer 15 hours ago

        > 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).

  • tim333 14 hours ago

    AGI was the thing from the start. From the OpenAI Charter:

    >OpenAI’s mission is to ensure that artificial general intelligence (AGI) ... benefits all of humanity.

    I agree with you on the leadership.

  • tiahura 18 hours ago

    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.

0xbadcafebee 14 hours ago

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.

  • doug_durham 14 hours ago

    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.

dr_kretyn 6 hours ago

Personally I find the current Google products mediocre almost on all aspects. The killer feature of chat bots is voice chat and ChatGPT works great, and Gemini is extremely quiet without a way to increase volume. It's also difficult to figure out how to sign up for Gemini, or even the keyboard that I'm typing is making so many incorrect predictions. I just don't trust Google. To me they're pure marketing and their engineering excellence ended a few years ago.

andai 7 hours ago

They don't have much to worry about as long as Google keeps focusing on the models and neglecting the experience of actually using them.

  • jatins 4 hours ago

    Gemini app is pretty solid and aistudio is a good dev focused offering. GCP and Vertex AI is still a bit of a mess but I wouldn't say the overall UX is too bad at this point

scoofy 14 hours ago

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.

  • energy123 11 hours ago

    I never understood this line of reasoning. I found it much more impressive that OpenAI's ML researchers realized this is the thing and bet big on it first, than to come up with it in the first place. It's underappreciated how much talent and insight it takes to see the obvious.

    • scoofy 11 hours ago

      The TPU architecture is the most impressive thing I care about. They developed them and have been using them internally for years. This shows they grok what they're actually doing.

      There are serious philosophical problems with betting big on an interesting outcome like ChatGPT, even though it seems obvious (Google also did this of course), but creating the best architecture to do that job seems like a first-principles intelligent move, because there was no reason to keep using graphics cards except that they "did the job."

  • paxys 10 hours ago

    The company didn't publish the paper, employees did. And all of them have since moved on to other companies, including OpenAI.

  • causal 14 hours ago

    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.

    • [removed] 11 hours ago
      [deleted]
  • raw_anon_1111 14 hours ago

    Google has great technology, their ability to make and focus on great product development without getting distracted is the issue

  • tokioyoyo 14 hours ago

    If Google wasn’t threatened by OpenAI et al., it wouldn’t be making Gemini today though.

ridgeguy 15 hours ago

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.

I'm now a former ChatGPT customer.

  • QuantumNomad_ 14 hours ago

    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.

  • poemxo 13 hours ago

    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.

  • dasil003 14 hours ago

    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.

    • caseyf7 14 hours ago

      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.

      • kirubakaran 14 hours ago

        I'm not trying to defend Google (shudder!), just trying to be helpful:

        - 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

  • drivebyhooting 14 hours ago

    How do you handle family obligations and a super commute like that?

    • ridgeguy an hour ago

      My commute is every other week, so it's not terrible. I drive to SJ Sunday night, stay in a hotel that's 5 minutes from my office, then drive home Friday afternoon.

      It averages 3.25hrs one way, or about 13 hrs/month, given my every other week schedule. It's a little tiring, but doable.

    • orochimaaru 14 hours ago

      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.

      It sucks but it’s doable

  • hn_throwaway_99 14 hours ago

    I mean, cool story bro.

    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.

  • [removed] 14 hours ago
    [deleted]
socketcluster 6 hours ago

I declared 'code red' at my house as Google, OpenAI and Anthropic catch up in my software development career race.

hunter-gatherer 12 hours ago

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.

dwa3592 18 hours ago

why couldn't GPT5.1 improve itself? Last I heard, it can produce original math and has phd level intelligence.

  • teaearlgraycold 7 hours ago

    I believe it was Sam Altman that said software engineers wouldn't have jobs by the end of the year. They still have a few weeks to make good on that.

    • ares623 3 hours ago

      I bet my retirement funds on that promise!

davebren 12 hours ago

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.

danans 15 hours ago

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.

  • mattmaroon 15 hours ago

    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.

    • danans 11 hours ago

      > Which makes me think they are getting the strategy exactly backwards

      The strategy is to take an admittedly cool technology and spin a dramatic story around it to raise capital, while providing a rationale for workforce reductions. 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.