logoalt Hacker News

unsupp0rtedlast Thursday at 12:38 PM1 replyview on HN

GPT 5.2 High is the gold standard in code quality right now.

The “Codex” models suck.

Claude, even Opus, creates major side-effects and misses obvious root causes of bugs.


Replies

kachapopopowlast Thursday at 12:50 PM

haven't done bug hunting with openai so cannot comment, but given the right tools opus can most definitely solve bugs as well.

I think opus is special because it was trained explicitely on very strong reliance on such tools while gpt seems to "know" how things work a lot better reducing the need for tools.

opus being able to dedicate a lot more parameters for these things make it a better model if you give it what it needs, but that's just my observation. it's also much faster as a bonus.