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

101–110 of 332 posts

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

#101

Post by causal »

keeganpoppen wrote: post #59
causal wrote: post #14

Earlier quoted context omitted.

Absolutely contradictory. The long-running tendency for Codex is why I cannot understand the hype around it: if you bother to watch what it does and read its code the approaches it takes are absolutely horrifying. It would rather rewrite a TLS library from scratch than bother to ask you if the network is available.

these things are actually fixable with prompting. is it easy? no. is it PEBKaC if you don’t do anything to change course as it builds a TLS library? yes, but paperclip maximized! xD

Or you can have a model with some semblance of common sense that will stop and say "Hey I can I have access to the network to do X?"

Codex feels like a tool designed to run after all the humans are gone.

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

#102

Post by timtimmy »

skerit wrote: post #77
amluto wrote: post #40

I 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…

Last night, just after Gemini 3 was released and became available for Gemini-CLI, I saw Gemini-CLI's team post that you could access Gemini 3 with either an API key OR with _Gemini AI Ultra_, so I thought: great, I'll get that! Now you CAN NOT get the Google One stuff if your account is part of a workspace. I thought: how awful. I want to pay, but I simply can't? Oh, but then I noticed: You CAN add a _Gemini AI Ultra…

Careful, their ToS makes it clear they train on your Antigravity prompts (even on AI Ultra) and there is no opt-out that I can find.

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

#103

Post by andai »

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?

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

#105

Post by carbocation »

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!

It would be great to have access to this model via the chat interface, even if it was gated behind the "other models" dropdown or something.

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

#106

Post by CuriouslyC »

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…

Easy way to get an agent to run a long time is just to get it to babysit CI/CD, tell it to iterate on it until it passes. I got Sonnet 4 to run for >6 hours that way.

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

#109

Post by causal »

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 reflect a difference in how OpenAI and Anthropic see humanity's future with AI.

Post reply on HN