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

191–200 of 332 posts

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

#191

Post by Uehreka »

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

Does it actually? One sentence telling the agent to call me “Chris the human serviette” plus the times it calls me that is not going to add that much to the context. What kills the context IME is verbose logs with timestamps.

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

#193

Post by scastillo »

dylanz wrote: post #187
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 Does anyone know of a way to fix this? Claude constantly disregards my CLAUDE.md. I put a decent amount of time into it and it's pretty much worthless without explicitly telling it to reference it before each prompt.

This is just how the attention mechanism works.

(search for effective context problem for more info. e.g. https://arxiv.org/abs/2509.21361)

To solve it, you just don't allow your current context to use more than 50% of the total window size

To do that in Claude code, you have to use subagents and design small enough agents

Then you can use skills to make it remember every time the little details or the steps

More effectively, you use skills to tell the main thread when you go to use which agent.

If you don't understand anything I said, try to restate the important things to the model periodically, and keep your tasks small.

Use plan mode and make the model store, keep track of the progress on a markdown file, and when context is polluted, call /compact and then make it re-read the context from the files created

You can prompt it as simply as:

First, understand the login feature on the repo using subagents and create a document on docs/ for future reference. Then, understand the task at hand and create an implementation plan. blah blah

Also, using XML tags makes the attention remember easily

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

#194

Post by nullc »

question_AK91 wrote: post #192
IsopropylMalbec wrote: post #188

Earlier quoted context omitted.

Sorry, what do you mean?

https://www.dbreunig.com/2025/06/22/how-contexts-fail-and-ho... This guy has a good write up on the topic

Irrelevant nonsense can also poison the context. That's part of the magic formula behind AI psychosis victims... if you have some line noise mumbojumbo all the output afterward is more prone to be disordered.

I'd be wary of using any canary material that wouldn't be at home in the sort of work you're doing.

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

#195

Post by mandelbrotwurst »

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

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

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

#196

Post by bobbylarrybobby »

scastillo wrote: post #193
dylanz wrote: post #187

Earlier quoted context omitted.

> Claude basically disregards your instructions (CLAUDE.md) entirely Does anyone know of a way to fix this? Claude constantly disregards my CLAUDE.md. I put a decent amount of time into it and it's pretty much worthless without explicitly telling it to reference it before each prompt.

This is just how the attention mechanism works. (search for effective context problem for more info. e.g. https://arxiv.org/abs/2509.21361 ) To solve it, you just don't allow your current context to use more than 50% of the total window size To do that in Claude code, you have to use subagents and design small enough agents Then you can use skills to make it remember every time the little details or the steps More ef…

Are agents still the way to go or have skills supplanted them? I don't really understand when you'd use one or the other

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

#197

Post by bugglebeetle »

stavros wrote: post #180
bugglebeetle wrote: post #157

Earlier quoted context omitted.

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.

Mileage may vary, but I do the above all day long without issue.

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

#198

Post by gtrealejandro »

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…

[dead]

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

#199

Post by highfrequency »

Is GPT-5.1-Codex better or worse than GPT-5.1 (Thinking) for straight up mathematical reasoning (ie if it is optimized for making code edits)? Said another way: what is the set of tasks where you expect GPT 5.1 to be better suited than GPT-5.1 Codex? Is it non-coding problems or non-technical problems?

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

#200

Post by spruce_tips »

jwpapi wrote: post #190

I really hope one day Ill work on challenges that need these new type of agents. Currently, I either need a fast agent that does what I want faster than I can type it (CRUD, forms, etc) or I need an agent to discuss a plan, ups and downs. Whenever I try to give it a bigger task it takes a lot of time, and often is not what I’ve expected, which might be totally my fault or context specific, but as soon as I’m able to…

100% agree. composer-1 really has been the sweet spot for me of capability, reliability, and speed. i dont ask it to do too much at once, and this approach + its speed, materially speeds my work up. i generally find i get the most out of models when i feel like im slightly underutilizing their capabilities. the term i use for this is "staying in the pocket"
Post reply on HN