Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

GPT-5-Codex

openai.com

Post reply on HN
Print view View original

21–30 of 144 posts

Re: GPT-5-Codex

#21

Post by dwaltrip »

tedsanders wrote: post #8
jumploops wrote: post #5

Interesting, the new model's prompt is ~half the size (10KB vs. 23KB) of the previous prompt[0][1]. SWE-bench performance is similar to normal gpt-5, so it seems the main delta with `gpt-5-codex` is on code refactors (via internal refactor benchmark 33.9% -> 51.3%). As someone who recently used Codex CLI (`gpt-5-high`) to do a relatively large refactor (multiple internal libs to dedicated packages), I kept running in…

> SWE-bench performance is similar to normal gpt-5, so it seems the main delta with `gpt-5-codex` is on code refactors SWE-bench is a great eval, but it's very narrow. Two models can have the same SWE-bench scores but very different user experiences. Here's a nice thread on X about the things that SWE-bench doesn't measure: https://x.com/brhydon/status/1953648884309536958

so annoying you cant read replies without an account nowadays

Re: GPT-5-Codex

#22

Post by siva7 »

jumploops wrote: post #5

Interesting, the new model's prompt is ~half the size (10KB vs. 23KB) of the previous prompt[0][1]. SWE-bench performance is similar to normal gpt-5, so it seems the main delta with `gpt-5-codex` is on code refactors (via internal refactor benchmark 33.9% -> 51.3%). As someone who recently used Codex CLI (`gpt-5-high`) to do a relatively large refactor (multiple internal libs to dedicated packages), I kept running in…

So you're all saying suddenly codex cli w gpt 5 codex is better than claude code? Hard to believe

Re: GPT-5-Codex

#24

Post by Tiberium »

poszlem wrote: post #17
robotswantdata wrote: post #13

Codex CLI IDE just works, very impressed with the quality. If you tried it a while back and didn’t like it, try it again via the vscode extension generous usage included with plus. Ditched my Claude code max sub for the ChatGPT pro $200 plan. So much faster, and not hit any limits yet.

Wait, what? They now allow claude code like subscription instead of the API too?

Yes, just do "codex login" and it'll use your ChatGPT subscription.

Re: GPT-5-Codex

#26

Post by Tiberium »

dwaltrip wrote: post #21
tedsanders wrote: post #8

Earlier quoted context omitted.

> SWE-bench performance is similar to normal gpt-5, so it seems the main delta with `gpt-5-codex` is on code refactors SWE-bench is a great eval, but it's very narrow. Two models can have the same SWE-bench scores but very different user experiences. Here's a nice thread on X about the things that SWE-bench doesn't measure: https://x.com/brhydon/status/1953648884309536958

so annoying you cant read replies without an account nowadays

Use Nitter, the main instance works but there are a lot of other instances as well.

https://nitter.net/brhydon/status/1953648884309536958

Re: GPT-5-Codex

#28

Post by jumploops »

siva7 wrote: post #22
jumploops wrote: post #5

Interesting, the new model's prompt is ~half the size (10KB vs. 23KB) of the previous prompt[0][1]. SWE-bench performance is similar to normal gpt-5, so it seems the main delta with `gpt-5-codex` is on code refactors (via internal refactor benchmark 33.9% -> 51.3%). As someone who recently used Codex CLI (`gpt-5-high`) to do a relatively large refactor (multiple internal libs to dedicated packages), I kept running in…

So you're all saying suddenly codex cli w gpt 5 codex is better than claude code? Hard to believe

Not suddenly, it's been better since GPT-5 launched.

Prompting is different, but in a good way.

With Claude Code, you can use less prompting, and Claude will get token happy and expand on your request. Great for greenfield/vibing, bad for iterating on existing projects.

With Codex CLI, GPT-5 seems to handle instructions much more precisely. It won't just go off on it's own and do a bunch of work, it will do what you ask.

I've found that being more specific up-front gets better results with GPT-5, whereas with Claude, being more specific doesn't necessarily stop the eagerness of it's output.

As with all LLMs, you can't compare apples to oranges, so to clarify, my experiences are primarily with Typescript and Rust codebases.

Re: GPT-5-Codex

#30

Post by jumploops »

pants2 wrote: post #6
jumploops wrote: post #5

Interesting, the new model's prompt is ~half the size (10KB vs. 23KB) of the previous prompt[0][1]. SWE-bench performance is similar to normal gpt-5, so it seems the main delta with `gpt-5-codex` is on code refactors (via internal refactor benchmark 33.9% -> 51.3%). As someone who recently used Codex CLI (`gpt-5-high`) to do a relatively large refactor (multiple internal libs to dedicated packages), I kept running in…

Interestingly, "more steerable" can sometimes be a bad thing, as it will tend to follow your prompt to the letter even if that's against your interests. It requires better prompting and generally knowing what you're doing - might be worse for vibe-coders and better for experienced SWEs.

Yes, given a similarly sparse prompt, Claude Code seems to perform "better" because it eagerly does things you don't necessarily know to ask

GPT-5 may underwhelm with the same sparse prompt, as it seems to do exactly what's asked, not more

You can still "fully vibe" with GPT-5, but the pattern works better in two steps:

1. Plan (iterate on high-level spec/PRD, split into actions)

2. Build (work through plans)

Splitting the context here is important, as any LLM will perform worse as the context gets more polluted.

Post reply on HN