SemiAnalysis said it last week and AFAIK it wasn't denied.

https://newsletter.semianalysis.com/p/tpuv7-google-takes-a-s...

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 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.

> with no means of significant revenue generation.

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-...

It would be funny if OpenAI turns for-profit, faceplants, and then finds new life (as Mozilla did) as a non-profit sharing its tools for free.

> 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?

Maybe? But you could have written this same thing in 1999 with OpenAI and Google replaced by Google and Yahoo, respectively.

> An innovative product with no means of significant revenue generation.

OpenAI has annualized revenue of $20bn. That's not Google, but it's not insignificant.

"Code Red" if implemented correctly should provide a single priority for the company. Engineers will be moved to the most important project(s).

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.

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 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.

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

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

> 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.

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.

> 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.

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.

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."

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

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

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.

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.

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

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.

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.

> 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?

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

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?

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

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

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

>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

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.

> 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!

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.

Benchmaxxing galore by lots of teams in this space.

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.

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

> 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

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

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.

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.

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.

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!

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

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"

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

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.

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.

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.

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.

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.

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.

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

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.

"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.

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

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.

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.

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

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

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.

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.

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.

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

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

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.

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.

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

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

That looks pretty... amateurish. I can't imagine selling customer a service that doesn't even hit the third nine

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...

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.

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.

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.

C'mon man. You know why...

ChatGPT is very complementary so they were probably high on their own supply.

If Gemini 3 had been a flop it wouldn't have been so bad for them.

> 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.

Not sure what you mean. His legacy to date is ruining the iphone because he couldn’t think of anything to do beyond “thinner”.

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?

Jensen cashed out on a billion dollars. Why would he even care anymore at this point?

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?

They will just have to change of LLM provider.

They gave up on that a long time ago.

OpenAI is for-profit: https://www.theguardian.com/technology/2025/oct/28/openai-fo...

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.

https://web.archive.org/web/20221221100606/https://www.nytim...

https://web.archive.org/web/20230512133437/https://www.theve...

That would be believable if you forget the sheer incompetence and bureaucracy Google was/is filled with

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.

This is one conspiracy theory I've actually considered. Google waited until the Chrome outcome to come out swinging.

Besides, can't they just allocate more ChatGPT instances to accelerating their development?

> 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.

the thought that this might be done one recommendation of ChatGPT has me rolling

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

Imho it just shows how relatively simple this technology really is, and nobody will have a moat. The bubble will pop.

Also, google has plenty of (unmatched?) proprietary data and their own money tree to fuel the money furnace.

There is always a daily call if a U.S. startup fails. Soon there will be quadrants and Ikigai Venn diagrams on the internal Slack.

Wait, shouldn't their internal agents be able to do all this work by now?

Don't forget the bleak subtext of all this.

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.

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.

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

…someone even wrote a book about this. Something about “mythical men”… :D

"The results of this quarter were already baked in a couple of quarters ago"

- Jeff Bezos

Quite right tbh.

What if they make 2 daily calls, that would surely improve the velocity by 2 times!

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.

Its easy to dismiss it but what would you do instead?

The beatings will continue until morale^H^H^H^H^H^H chatGPT improves...

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.

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.

Does anyone in AI think about 5 years from now?

or maybe even code brown

I think the most relevant quote is from Futurama:

"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."

Probably all of the ML foundation like transformers which OpenAI used to create its chatbot was originally developed at Google.