Hacker News new | ask | show | jobs
by stavros 119 days ago
I asked both to help me with a hardware bug. Codex kept trying things, being sure of what the problem is every time, and every time making it worse.

Opus went off and browsed my dependencies for ten minutes, and came back and solved the problem firs try.
2 comments
saberience 119 days ago
Heh, I find Codex to be a far, far smarter model than Claude Code.

And there's a good reason the most "famous" vibe coders, including the OpenClaw creator all moved to Codex, it's just better.

Claude writes a lot more code to do anything, tons of redundent code, repeated code etc. Codex is only model I've seen which occasionally removes more code than it writes.

link
Huppie 119 days ago
Funnily enough I've been using Codex 5.3 on maximum thinking for bug hunting and code reviews and it's been really good at it (it's just seem to have a completely different focus than Opus.)

I generally don't like the way codex approaches coding itself so I just feed its review comments back in to Claude Code and off we go.

link
stavros 119 days ago
I just created an OpenCode skill where both these models will talk to each other and discuss bug-finding approaches.

In my experience, two different models together works much better than one, that's why this subscription banning is distressing. I won't be able to use a tool that can use both models.

link