Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Building more with GPT-5.1-Codex-Max

openai.com

Post reply on HN
Print view View original

231–240 of 332 posts

Re: Building more with GPT-5.1-Codex-Max

#231

Post by parineum »

fspeech wrote: post #220
mandelbrotwurst wrote: post #195

Earlier quoted context omitted.

Why would the fact that it failed to follow one instruction increase the likelihood that it failed to follow others within the same response?

It has a fixed capacity of how many different things it can pay close attention to. If it fails on a seemingly less important but easy to follow instruction it is an indicator that it has reached capacity. If the instruction seems irrelevant it is probably prioritized to be discarded, hence a canary that the capacity has been reached.

> It has a fixed capacity of how many different things it can pay close attention to

Source, all the way down to the ability to "pay attention to" part.

Re: Building more with GPT-5.1-Codex-Max

#232

Post by ineedasername »

killcoder wrote: post #213
hansonw wrote: post #15

Rest assured that we are better at training models than naming them ;D - New benchmark SOTAs with 77.9% on SWE-Bench-Verified, 79.9% on SWE-Lancer, and 58.1% on TerminalBench 2.0 - Natively trained to work across many hours across multiple context windows via compaction - 30% more token-efficient at the same reasoning level across many tasks Let us know what you think!

It would be nice if users of the codex-cli that are just using API keys as a way to handle rate limits and billing could receive these new models at the same time. I appreciate the reasoning behind delayed 'actual API' release, but I've found the rate limiting to be quite annoying, and my own API keys don't have this limitation.

Re: rate limits, I'm not sure they can, yet, on capacity. See Jensen's comment today about their cloud GPUs being sold out. So capacity increased await the ongoing data center build out.

Re: Building more with GPT-5.1-Codex-Max

#233

Post by ineedasername »

SoKamil wrote: post #169
hansonw wrote: post #15

Rest assured that we are better at training models than naming them ;D - New benchmark SOTAs with 77.9% on SWE-Bench-Verified, 79.9% on SWE-Lancer, and 58.1% on TerminalBench 2.0 - Natively trained to work across many hours across multiple context windows via compaction - 30% more token-efficient at the same reasoning level across many tasks Let us know what you think!

> Natively trained What does it even mean?

Continuous pre training or fine tuning, instead of inference-time instructions. It's also possible synthetic data for this purpose was in the pre training as well, and they're now getting it to behave the way they'd like.

Re: Building more with GPT-5.1-Codex-Max

#234

Post by ineedasername »

ntonozzi wrote: post #32
taurath wrote: post #10

These 2 sentences right next to each other stood out to me: > a new step towards becoming a reliable coding partner > GPT‑5.1-Codex-Max is built for long-running, detailed work Does this not sound contradictory? It’s been the shorter form work that has built what little confidence I have in these as a coding partner - a model that goes off and does work without supervision is not a partner to me.

If you haven't, give Cursor's Composer model a shot. It might not be quite as good as the top models, but in my experience it's almost as good, and the lightning fast feedback is more than worth the tradeoff. You can give it a task, wait ten seconds, and evaluate the results. It's quite common for it to not be good enough, but no worse than Sonnet, and if it doesn't work you just wasted 30 seconds instead of 10 minut…

Also: Qwen3 coder. Highly usable, in it's smaller form as well.

Re: Building more with GPT-5.1-Codex-Max

#235

Post by jes5199 »

jack_pp wrote: post #225
causal wrote: post #109

Earlier quoted context omitted.

> Codex will rewrite the entire V8 engine to break arithmetic. This isn't an exaggeration either. Codex acts as if it is the last programmer on Earth and must accomplish its task at all costs. This is great for anyone content to treat it like a black box, but I am not content to do that. I want a collaborator with common sense, even if it means making mistakes or bad assumptions now and then. I think it really does r…

Maybe have Claude coordinate Codex?

I think this might be the way forward, Claude is great at project managing.

I’m already telling Claude to ask Codex for a code review on PRs. or another fun pattern I found is you can use give the web version of Codex an open ended task like “make this method faster”, hit the “4x” button and end and up with four different pull requests attacking the problem in different ways. Then ask Claude to read the open PRs and make a 5th one that combines the approaches. This way Codex does the hard thinking but Claude does the glue

Re: Building more with GPT-5.1-Codex-Max

#236

Post by root_axis »

jack_pp wrote: post #224
root_axis wrote: post #209

Earlier quoted context omitted.

> Just because you don't understand it, doesn't mean it's "folk magic incantation" It absolutely is folk magic. I think it is more accurate to impugn your understanding than mine. > I don't know the merit to what parent is saying, but it does make some intuitive sense if you think about it. This is exactly what I mean by folk magic. Incantations based on vibes. One's intuition is notoriously inclined to agree with on…

I view it more as fun and spicy. Now we are moving away from the paradigm that the computer is "the dumbest thing in existence" and that requires a bit of flailing around which is exciting! Folk magic is (IMO) a necessary step in our understanding of these new.. magical.. tools.

I won't begrudge anyone having fun with their tools, but folk magic definitely isn't a necessary step for understanding anything, it's one step removed from astrology.

Re: Building more with GPT-5.1-Codex-Max

#237

Post by typpilol »

enraged_camel wrote: post #27
EnPissant wrote: post #25

Earlier quoted context omitted.

Compaction is just what Claude Code has done forever, right?

I am also trying to understand the difference between compaction, and what IDEs like Cursor do when they "summarize" context over long-running conversations. Is this saying that said summarization now happens at the model level? Or are there other differences?

Afaik, there's no difference besides how aggressive or not it is.

But it's the same concept. Taking tokens in context and removing irreverent ones by summarizing, etc

Re: Building more with GPT-5.1-Codex-Max

#238

Post by nbardy »

boole1854 wrote: post #155

Today I did some comparisons of GPT-5.1-Codex-Max (on high) in the Codex CLI versus Gemini 3 Pro in the Gemini CLI. - As a general observation, Gemini is less easy to work with as a collaborator. If I ask the same question to both models, Codex will answer the question. Gemini will read some intention behind the question, write code to implement the intention, and only then answer the question. In one case, it took m…

Yea, I can't get gemini to stop and think, even if I tell it to not write code it will rewrite the code block each time

Re: Building more with GPT-5.1-Codex-Max

#239

Post by typpilol »

sethhochberg wrote: post #89
temp0826 wrote: post #79

Earlier quoted context omitted.

Didn't realize these stipulations for the models. Looking at devops-y job descriptions the last few months I noticed nearly everyone has some kind of Azure requirement now (which I've mostly avoided because I don't want to end up managing someone's AD), but is openai the actual reason for it?

We're just using Github Copilot as our primary entrypoint for all of the model families. Its the only way we can easily offer our devs some level of Claude, Gemini, and Codex all in one place.

Copilot has gotten a lot better lately at least on insiders. They are actually serving close to 200k context on insiders last I checked, which brings it more online with the first party apis

Re: Building more with GPT-5.1-Codex-Max

#240

Post by pimeys »

causal wrote: post #109
johnfn wrote: post #56

I've been using a lot of Claude and Codex recently. One huge difference I notice between Codex and Claude code is that, while Claude basically disregards your instructions (CLAUDE.md) entirely, Codex is extremely, painfully, doggedly persistent in following every last character of them - to the point that i've seen it work for 30 minutes to convolute some solution that was only convoluted because of some sentence I t…

> Codex will rewrite the entire V8 engine to break arithmetic. This isn't an exaggeration either. Codex acts as if it is the last programmer on Earth and must accomplish its task at all costs. This is great for anyone content to treat it like a black box, but I am not content to do that. I want a collaborator with common sense, even if it means making mistakes or bad assumptions now and then. I think it really does r…

Wait, I think it's the other way around. Claude will just go circles with bad decisions forever, never stops. Codex have multiple times told me it is not able to do this task, and stops.
Post reply on HN