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

41–50 of 332 posts

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

#41

Post by poly2it »

agentifysh wrote: post #26
spmartin823 wrote: post #7

I still want something no one has, which is the ability to launch agents in different git worktrees simultaneously and check the results out on my main branch for testing when they are finished.

lots of tools that do this and I ended up going down this rabbit hole something that could just plug in to codex instead of requiring a fork http://github.com/agentify-sh/10x does minimal overhead with agent orchestration (its just a bash/typescript) as its main focus was adding enhancements to codex like double redundant checkpoint via git and jj (lessons learned from codex being git reset --hard happy), something l…

Your link is a 404.

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

#43

Post by cube2222 »

agentifysh wrote: post #39
cube2222 wrote: post #23

Somewhat related, after seeing the praise for codex in the Sonnet 4.5 release thread I gave it a go, and I must say, that CLI is much worse than Claude Code (even if the model is great, I’m not sure where the issue really lies between the two). It was extremely slow (like, multiple times slower than Sonnet with Claude Code, though that’s partially on me for using thinking-high I guess) to finish the task, with the ba…

sure claude code has better ux but honestly its hard to get any good amount of usage out of the subscriptions vs what codex offers at the same price with claude im constantly hitting rate limits with codex getting substantially more and "slow" isn't really a problem for me as long as it keep working the only complaint i have is that codex itself has usage limited now (Either due to outstanding git issues around tools…

Well as I said, codex didn’t adhere to codebase standards for me and the code quality was worse (very defensive), so even after waiting longer, results weren’t there for me.

But the subscription thing is a non-issue for me as I use the API, and mostly use Claude Code synchronously, with the occasional rare background agent.

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

#44

Post by embirico »

taurath wrote: post #10

These 2 sentences right next to each other stood out to me: > a new step towards becoming a reliable coding partner > GPT‑5.1-Codex-Max is built for long-running, detailed work Does this not sound contradictory? It’s been the shorter form work that has built what little confidence I have in these as a coding partner - a model that goes off and does work without supervision is not a partner to me.

(Disclaimer: Am on the Codex team.) We're basically trying to build a teammate that can do both short, iterative work with you, then as you build trust (and configuration), you can delegate longer tasks to it.

The "# of model-generated tokens per response" chart in [the blog introducing gpt-5-codex](https://openai.com/index/introducing-upgrades-to-codex/) shows an example of how we're improving the model good at both.

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

#47

Post by qsort »

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!

Codex is an outstanding product and incremental upgrades are always welcome. I'll make sure to give it a try in the coming days. Great work! :)

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

#48

Post by nartho »

syntaxing wrote: post #46

I rarely used Codex compared to Claude because it was extremely slow in GitHub copilot . Like maybe 2-5X slower than Claude Sonnet. I really wish they just made their models faster than “better”

Have you tried Mistral ? Definitely one of the fastest models

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

#49

Post by atonse »

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 google payments and I was like, what is google payments and where do I even begin with that? I’ve never paid for google play so what does payments have to do with anything?

It’s totally random stuff. Get your shit together, google. Make your products and payment systems coherent, rather than it obviously looking like it was designed by a fiefdom full of territorial managers.

Post reply on HN