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

181–190 of 332 posts

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

#181

Post by baby »

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!

Did you guys fix not being able to enable websearches or configure no timeouts for specific commands in the SDk (error 124 is way too common for long running tasks)

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

#183

Post by baby »

andai wrote: post #103
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!

So context window is still 400k but the model got good at removing irrelevant context?

Or is more succinct in its thoughts

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

#184

Post by baby »

EnPissant wrote: post #25
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!

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

Yes. It was missing in codex until now

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

#185

Post by baby »

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?

Codex couldnt do what claude did before when reaching full context window

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

#187

Post by dylanz »

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.

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

#188

Post by IsopropylMalbec »

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

Sorry, what do you mean?

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

#189

Post by jadbox »

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…

Try checking your temp for any tool using Gemini.

"For Gemini 3, we strongly recommend keeping the temperature parameter at its default value of 1.0.While previous models often benefited from tuning temperature to control creativity versus determinism, Gemini 3's reasoning capabilities are optimized for the default setting. Changing the temperature (setting it below 1.0) may lead to unexpected behavior, such as looping or degraded performance, particularly in complex mathematical or reasoning tasks."

https://ai.google.dev/gemini-api/docs/gemini-3?thinking=high

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

#190

Post by jwpapi »

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 define the task properly I would prefer a faster model as it will be good enough, but faster. I really don’t have problems anymore that I can’t reasonable solve fast enough with this approach.

I’ve run multiple gpt-5 codex concurrent sessions in the cloud, but I didn’t accept one thing they did.

Eventually thinking through it, reading hack boom is faster than outsourcing the work for 30 minutes + 30 minutes to digest +30 minutes to change..

Post reply on HN