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

111–120 of 332 posts

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

#111

Post by sinatra »

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…

In my AGENTS.md (which CLAUDE.md et al soft link to), I instruct them to "On phase completion, explicitly write that you followed these guidelines." This text always shows up on Codex and very rarely on Claude Code (TBF, Claude Code is showing it more often lately).

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

#112

Post by Atotalnoob »

999900000999 wrote: post #94

I really would prefer them to start creating customized models. I've vibe coded Godot games extensively. Just about every model I've tried likes to invent imaginary functions. I was really prefer for there to be a way for me to pick model trained in whatever framework I need. Reviewing AI generated code feels like editing a long book, and every now and then you notice some words are just completely made up. You then…

I’ve found writing a MCP server with access to the docs cloned locally does wonders.

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

#113

Post by GaggiX »

999900000999 wrote: post #94

I really would prefer them to start creating customized models. I've vibe coded Godot games extensively. Just about every model I've tried likes to invent imaginary functions. I was really prefer for there to be a way for me to pick model trained in whatever framework I need. Reviewing AI generated code feels like editing a long book, and every now and then you notice some words are just completely made up. You then…

Add the documentation to the context window in that case, a bit of context engineering.

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

#114

Post by sinatra »

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!

I currently use GPT‑5.1-Codex High and have a workflow that works well with the 5-hour/weekly limits, credits, et al. If I use GPT‑5.1-Codex-Max Medium or GPT‑5.1-Codex-Max High, how will that compare cost / credits / limits wise to GPT‑5.1-Codex High? I don't think that's clear. "Reduced tokens" makes me think it'll be priced similarly / lower. But, "Max" makes me think it'll be priced higher.

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

#115

Post by ed »

qsort wrote: post #34
simianwords wrote: post #28

Earlier quoted context omitted.

context window is not some physical barrier but rather the attention just getting saturated. what did i get wrong here?

> what did i get wrong here? You don't know how an LLM works and you are operating on flawed anthropomorphic metaphors. Ask a frontier LLM what a context window is, it will tell you.

Parent is likely thinking of sparse attention which allows a significantly longer context to fit in memory

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

#116

Post by ineedasername »

simonw wrote: post #99

Thinking level medium: https://tools.simonwillison.net/svg-render#%3Csvg%20xmlns%3D... Thinking level xhigh: https://tools.simonwillison.net/svg-render#%20%20%3Csvg%20xm...

Medium has things dialed in. When both high and low are coherent but medium goes to cubism? That’s intent. Or it had a miscue on proportions vs shape placement. Either way, it’s great, sandwiched the way it is, between the other two. Did it put a comment in all of them or just the one w/ the hat?

Also, thanks for the posts— it’s hugely helpful to have a continuity of insightful perspective throughout.

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

#117

Post by brobdingnagians »

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…

Such great case studies of how LLM coding will make all of your employees 1000x more productive at coding, design, and UX. They really are leading the way showing us into the brighter future of AI software /s

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

#118

Post by XenophileJKO »

spectraldrift wrote: post #96

Weird how they only share three hand-picked evals, ignoring the evals where they were left in the dust like ARC-AGI2. This post is so misleading, I don't even know whether to trust the numbers they did share. One is just fraction of a percentage point away from Gemini 3 pro, which is awfully convenient for marketing and easy to hide. Very open, OpenAI.

Not really that weird. This isn't intended to be a "general" model. This is a coding model so they showed the coding evals. The assumption would be relative to GPT5.1, non-coding evals would be likely regress or be similar.

Like when advertising the new airliner, most people don't care about how fast it taxis.

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

#119

Post by lucasban »

leetrout wrote: post #100
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…

And stop asking for phone numbers for "fraud prevention" when I've already given you my name, address and credit card.

The fun one for me is that I moved countries and last I checked there’s still no way to change your phone number on ChatGPT short making a new account, so now my account is associated with a phone number that I no longer have access to and will eventually be reassigned to someone else.

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

#120

Post by swivelmaster »

atonse wrote: post #49
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…

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…

> designed by a fiefdom full of territorial managers

What's harder than herding cats? Herding cats with MBAs and OKRs.

Post reply on HN