News for hackers. Stuff that matters.
Re:GPT-5-Codex by tedsanders on Monday September 15, 2025 @02:23PM (#45253200)
> 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

Re:GPT-5-Codex by dwaltrip on Monday September 15, 2025 @04:19PM (#45254437)
so annoying you cant read replies without an account nowadays
Re:GPT-5-Codex by dcre on Monday September 15, 2025 @08:02PM (#45256438)
Change the url from x.com to xcancel.com to see it all.
Re:GPT-5-Codex by Tiberium on Monday September 15, 2025 @04:41PM (#45254646)
Use Nitter, the main instance works but there are a lot of other instances as well.

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