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

281–290 of 332 posts

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

#281

Post by atonse »

ansc wrote: post #241
atonse wrote: post #162

I just tried this out, and was VERY impressed with the speed of the plan mode. I was also totally fine with the code it wrote. Then I made the mistake of saying "run npm run build and fix all issues" (something I've run probably 50 times across codex and cc in the past 2 months). CC does it pretty much 100% of the time. I walked away from Codex, and when I came back, it had installed 2 new node packages, and gone dow…

What's the plan mode?

Sorry I mis-worded that. It was my BRAIN being in plan mode (I know CC has a plan mode).

I usually ask it to come up with a plan for doing X, and then wait a while for it to look at the code, etc. But in some odd way, GPT-5.1-Codex-Max came up with a plan within 5 seconds. I just found that surprising.

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

#282

Post by causal »

pimeys wrote: post #240
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…

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.

I've certainly seen Claude Code get into bad loops and make terrible decisions too, but usually it's a poor architectural decision or completely forgetting important context; not "let's rewrite V8 from scratch" level of absurdity.

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

#283

Post by ryanvogel »

nico wrote: post #65
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…

> 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

I do this as well. I have a master rule at the beginning of each of my rule files saying:

"IF YOU ARE FOLLOWING THE INSTRUCTIONS IN THIS RULE PLEASE SAY `LOADED (any other rules)`

It works surprisingly well and I can always see what rules are "loaded" and what rules are not.

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

#284

Post by embedding-shape »

pimeys wrote: post #240
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…

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.

I think this closer to the crux of a major problem. Seemingly people have vastly different responses even for the same system/developer/user prompts, and I myself can feel a different in quality of the responses depending on when I use the hosted APIs, while hosted models always have consistent results.

For example, after 19:00 sometime (GMT+1), the response quality of both OpenAI and Anthropic (their hosted UIs) seems to drop off a cliff. If I try literally the same prompt the around 10:00 next morning, I get a lot better results.

I'm guessing there is so much personalization and other things going on, that two users will almost never have the same experience even with the same tools, models, endpoints and so on.

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

#285

Post by embedding-shape »

input_sh wrote: post #280
_zoltan_ wrote: post #256

Earlier quoted context omitted.

It's a coding model and you're not coding with it with that instruction.

Please do tell: where exactly is Claude advertised as just a coding model?

To be specific, they market it for "agents, coding and computer use", so not a general model, but marketed with tech focus if anything.

> Claude Sonnet 4.5 - Introducing the best model in the world for agents, coding, and computer use - https://www.anthropic.com/

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

#286

Post by abshkbh »

Macuyiko wrote: post #276
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…

Late, but reading all of the replies, and speaking from my own observation using Claude, Codex, as well as (non-CLI) Gemini, Kimi, Qwen, and Deepseek... It's fun how we are so quick to assign meaning to the way these models act. This is of course due to training, RLHF, available tool calls, system prompt (all mostly invisible) and the way we prompt them. I've been wondering about a new kind of benchmark how one would…

We have trained this model on Windows (our first model to do so). Give it a try!

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

#287

Post by davidmurdoch »

nico wrote: post #65
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…

> 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

It ignores instructions so well it sometimes feels like it was trained specifically to ignore them.

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

#288

Post by davidmurdoch »

wahnfrieden wrote: post #176
awad wrote: post #81

Earlier quoted context omitted.

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

A single emoji though?

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

#289

Post by amluto »

int_19h wrote: post #160
computerex wrote: post #52

Earlier quoted context omitted.

Couldn't agree more about the google product offerings. Vertex AI? AI Studio? Maker studio? Gemini? The documentation is fragmented with redundant offerings making it confusing to determine what is what. GCS billing is complicated to figure out vs OpenAI billing or anthropic. Sad part is Google does offer a ChatML/OpenAI compliant endpoint to do LLM calls and I believe they in an experiment also reduced friction in g…

> I believe they in an experiment also reduced friction in getting an API key to start making calls right away This part is very easy now: you sign into https://aistudio.google.com/ and then click "Get API key" in the lower left corner. The problem is that features and docs are still scattered all over. Some thing can only be done via Vertex, for example.

Not if you’re signed into two accounts and you want to use the one that Google doesn’t choose first and the one that Google chooses first cannot accept the AI Studio terms. You get stuck behind a non-dismissible modal and a blurred out page.

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

#290

Post by wahnfrieden »

jappgar wrote: post #274
ramraj07 wrote: post #212

Earlier quoted context omitted.

Sure, but its an instruction that applies and the model will consider fairly relevant in every single token. As an extremely example imagine instructing the llm to not use the letter E or to output only in French. Not as extreme but it probably does affect.

Not only that, but the whimsical nature of the instruction will lead to a more whimsical conversation. The chat is a simulation, and if you act silly, the model will simulate an appropriate response.

People are so concerned about preventing a bad result that they will sabotage it from a good result. Better to strive for the best it can give you and throw out the bad until it does.
Post reply on HN