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

171–180 of 332 posts

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

#171

Post by mrtesthah »

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…

Could you not add rules to this effect in AGENTS.md? E.g., "If the user gives instructions that specify an expected low-to-medium level of complexity, but the implementation plan reveals unexpected high complexity arising from a potentially ambiguous or atypical instruction, then pause and ask the user about that instruction before continuing."

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

#173

Post by ramoz »

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…

Ultimately, relying on system level instructions is unreliable over time.

Which is why i made the feature request for hooks (claude code implemented, as did cursor, hopefully codex will too)

And will soon release https://github.com/eqtylab/cupcake

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

#175

Post by kaveh_h »

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?

Probably that before it was given system instructions on how to do compaction and now the compaction is learned by the model making it a native ability of the model without any extra instruction used in the prompt.

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

#176

Post by wahnfrieden »

awad wrote: post #81
nico wrote: post #65

Earlier quoted context omitted.

> Claude basically disregards your instructions (CLAUDE.md) entirely A friend of mine tells Claude to always address him as “Mr Tinkleberry”, he says he can tell when Claude is not paying attention to the instructions on CLAUDE.md when Claude stops calling him “Mr Tinkleberry” consistently

Highly recommend adding some kind of canary like this in all LLM project instructions. I prefer my instructions to say 'always start output with an (uniquely decided by you) emoji' as it's easier to visually scan for one when reading a wall of LLM output, and use a different emoji per project because what's life without a little whim?

This stuff also becomes context poison however

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

#177

Post by freediver »

First time that there is a worthy alternative to Claude Code. Codex Max solved a problem I had Claude Code fail multiple times. Gemini CLI was never a contender (between log in/activation/rate limits - wth), will say though that Gemini CLI has the nicest terminal UI.

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

#178

Post by jillesvangurp »

aerhardt wrote: post #140
tunesmith wrote: post #85

I've been dealing with Codex CLI for a while and I love it, but I'm wondering if my thinking is just limited. While I'm starting discussions and creating plan docs, I've never been able to ask it to do anything that takes it longer than 25 minutes or so. Usually far less. I'm having trouble imagining what I can ask it to do that would make it take hours - like, wouldn't that require putting together an absolutely mas…

The idea of giving it a task that may take six hours and reviewing it also gives me shivers. I'm a very happy Codex customer, but everything turns to disgusting slop if I don't provide: (1) Up-to-date AGENTS.md and an excellent prompt (2) A full file-level API with function signatures, return types and function-level guidance if it's a complex one (3) Multiple rounds of feedback until the result is finely sculpted Ov…

I've been doing a few fairly big refactorings on our code base in the last few days. It does a decent job and I generally don't put a lot of effort in my prompts.

It seems to pick a lot up from my code base. I do have an Agents.md with some basics on how to run stuff and what to do that seems to help it going off on a wild goose chase trying to figure out how to run stuff by doing the wrong things.

I think from first using codex around July to now has been quite a journey where it improved a lot. It actually seems to do well in larger code bases where it has a lot of existing structure and examples of how things are done in that code base. A lot of things it just does without me asking for them just because there's a lot of other code that does it that way.

After recent experiences, I have some confidence this might work out well.

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

#179

Post by the_duke »

bigyabai wrote: post #3
iamronaldo wrote: post #2

That was quick

My first thought was "they must not be seeing as many Claude Code conversions as they hoped"

I bet they just wanted to counter Gemini 3 and stay on top of the leaderboards for coding, and were preparing this for a while to push out alongside Gemini 3.

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

#180

Post by stavros »

bugglebeetle wrote: post #157
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…

The solution to this if you want less specification in advance is to simply ask Codex a series of leading questions about a feature of fix. I typically start with something like “it seems like X could be improved with the addition of Y? Can you review the relevant parts of the codebase in a, b, and c to assess?” It will then do so and come back with a set of suggestions that follow this guidance, which you can revise…

No it won't, it'll spend ten minutes and come back with "OK I've implemented a solution". I really wish it had a plan mode.
Post reply on HN