News for hackers. Stuff that matters.
Re:Show HN: State of the Art of Coding Models, According to ... by brihati on Monday May 04, 2026 @05:45AM (#48006476)
I use both Codex & Claude Code. With Codex, their long running agents are still not as good as Claude Code. But I don't complain because they burn very less tokens as compared to Claude Code for the same task. But having said that, if I am provided limitless tokens for each of them, my go to harness will be Claude Code

There are no comments on this comment yet.