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…
Building more with GPT-5.1-Codex-Max
201–210 of 332 posts
Re: Building more with GPT-5.1-Codex-Max
#202I'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
Re: Building more with GPT-5.1-Codex-Max
#203I would love to see all the big players put 1% of the effort they put into model training into making the basic process of paying and signing in suck less. Claude: they barely have a signin system at all. Multiple account support doesn’t exist. The minimum seat count for business is nonsense. The data retention policies are weak. OpenAI: Make ZDR a thing you can use or buy without talking to sales, already. And for t…
Agree 1,000%. I just won’t even waste my time with the google stuff cuz I can’t figure out how to pay with it. And that’s a problem everywhere at google. Our google play account is suspended cuz I can’t verify the company. It won’t let me cuz it says I’m not the owner. I’ve always been the owner of my company. For 18 years. There is no one else. Once some error said make sure the owner email matches your profile in g…
YES I had this and eventually fixed it. I really don't know what I did but lots of clicking on random links and signing into things in different orders and then one day it somehow worked.
So frustrating.
Re: Building more with GPT-5.1-Codex-Max
#204Earlier 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
Something that exhausts me in the LLM era is the never ending deluge of folk magic incantations.
I don't know the merit to what parent is saying, but it does make some intuitive sense if you think about it. As the context fills up, the LLM places less attention on further and further back in the context, that's why the LLM seems dumber and dumber as a conversation goes on. If you put 5 instructions in the system prompt or initial message, where one acts as a canary, then you can easier start to see when exactly it stops following the instructions.
Personally, I always go for one-shot answer, and if it gets it wrong or misunderstands, restart from the beginning. If it doesn't get it right, I need to adjust the prompt and retry. Seems to me all current models do get a lot worse quickly, once there is some back and forth.
Re: Building more with GPT-5.1-Codex-Max
#205I'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…
I've been really impressed with codex so far. I have been working on a flight simulator hobby project for the last 6 months and finally came to the conclusion that I need to switch from floating origin, which my physics engine assumes with the coordinate system it uses, to a true ECEF coordinate system (what underpins GPS). This involved a major rewrite of the coordinate system, the physics engine, even the graphics…
Re: Building more with GPT-5.1-Codex-Max
#206I would love to see all the big players put 1% of the effort they put into model training into making the basic process of paying and signing in suck less. Claude: they barely have a signin system at all. Multiple account support doesn’t exist. The minimum seat count for business is nonsense. The data retention policies are weak. OpenAI: Make ZDR a thing you can use or buy without talking to sales, already. And for t…
Google keeps changing their privacy and “don’t train on my data/code” options. When gemini-cli launched, there was a clear toggle for “don’t train on my code.” That’s now gone; it just links to a generic privacy page for me. Maybe something with my account changed, I can't figure it out. Deep in the Cloud Gemini console, there’s another setting that might control training, but it’s not clear what products it actually…
Re: Building more with GPT-5.1-Codex-Max
#207I 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…
Treat it as a developer that just joined the project and isn't aware of the conventions.
Provide hints for the desired API design, mention relevant code locations that should be read to gain context on the problem, or that do similar things.
An AGENTS.md that explains the project and provides some general guidelines also helps a lot.
Codex can be incredibly strong when prompted the right way.
Re: Building more with GPT-5.1-Codex-Max
#208I'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…
This feels very strange to me. I use Claude a lot and it follows the instructions very well. What's in your CLAUDE.md file? it's supposed to be fairly concise/brief and not use up too much context.
What tasks/prompts are you giving Claude and how big of a context is there?
EDIT: Also which model are you using?
Re: Building more with GPT-5.1-Codex-Max
#209Earlier quoted context omitted.
Something that exhausts me in the LLM era is the never ending deluge of folk magic incantations.
Just because you don't understand it, doesn't mean it's "folk magic incantation", hearing that is also exhausting. I don't know the merit to what parent is saying, but it does make some intuitive sense if you think about it. As the context fills up, the LLM places less attention on further and further back in the context, that's why the LLM seems dumber and dumber as a conversation goes on. If you put 5 instructions…
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 one's own conclusions.
> If you put 5 instructions in the system prompt or initial message, where one acts as a canary, then you can easier start to see when exactly it stops following the instructions.
This doesn't really make much sense.
First of all, system prompts and things like agent.md never leave the context regardless of the length of the session, so the canary has absolutely zero meaning in this situation, making any judgements based on its disappearance totally misguided and simply a case of seeing what you want to see.
Further, even if it did leave the context, that doesn't then demonstrate that the model is "not paying attention". Presumably whatever is in the context is relevant to the task, so if your definition of "paying attention" is "it exists in the context" it's actually paying better attention once it has replaced the canary with relevant information.
Finally, this reasoning relies on the misguided idea that because the model produces an output that doesn't correspond to an instruction, it means that the instruction has escaped the context, rather than just being a sequence where the model does the wrong thing, which is a regular occurrence even in short sessions that are obviously within the context.
Re: Building more with GPT-5.1-Codex-Max
#210This is a tangent: Has anyone noticed that GPT-5.0 at some point started producing much faster, crappier answers, then 5.1 made it slower + better again? (Both in Thinking mode)
It seems like they might still be heavily nerfing / quantizing the models in production a couple weeks before a new release, like they have always (unofficially) done.