News for hackers. Stuff that matters.

A comment on The Codex App. Parent comment

Re:The Codex App by 650REDHAIR on Monday February 02, 2026 @03:33PM (#46861085)
I hit the Claude limit within an hour.

Most of my tokens are used arguing with the hallucinations.

I’ve given up on it.

[ Parent | on HN ]
Re:The Codex App by hnsr on Monday February 02, 2026 @04:02PM (#46861503)
Do you use Claude Code, or do you use the models from some other tool?

I find it quite hard to hit the limits with Claude Code, but I have several colleagues complaining a lot about hitting limits and they use Cursor. Recently they also seem to be dealing with poor results (context rot?) a lot, which I haven't really encountered yet.

I wonder if Claude Code is doing something smart/special

[ Parent | on HN ]
Re:The Codex App by TuxSH on Monday February 02, 2026 @03:52PM (#46861355)
In my case I've had it (Opus Thinking in CC) hit 80% of the 5-hour limit and 100% of the context window with one single tricky prompt, only to end up with worthless output.

Codex at least 'knows' to give up in half the time and 1/10th of the limits when that happens.

[ Parent | on HN ]
Re:The Codex App by theshrike79 on Monday February 02, 2026 @04:50PM (#46862158)
I don't want to be That Guy, but if you're "arguing with hallucinations" with an AI Agent in 2026 you're either holding it wrong or you're working on something highly nonstandard.
[ Parent | on HN ]