Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

> Some models (looking at you, GPT-5-Codex) seemed to mistake “more complex” for “better.”

That's what working with GPT-5-Codex on actual code also feels like.



YES, and the sad truth is that the only person who can write good, simple code is likely the one who doesn't need an AI helper. ;(


Funny because I've felt that way and have switched back to Claude Sonnet 4.5 for agentic coding.

If Sonnet doesn't solve my problem, sometimes Codex actually does.

So it isn't like Codex is always worse. I just prefer to try Sonnet 4.5 first.


So it's an accurate simulation of a programmer then




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: