(steerlabs.substack.com)

323 points steerlabs | 1 comments | 04 Dec 25 20:48 UTC | HN request time: 0.218s | source

Show context

- Claude, please optimise the project for performance.

o Claude goes away for 15 minutes, doesn't profile anything, many code changes.

o Announces project now performs much better, saving 70% CPU.

- Claude, test the performance.

o Performance is 1% _slower_ than previous.

- Claude, can I have a refund for the $15 you just wasted?

o [Claude waffles], "no".

1. lukev ◴[08 Dec 25 15:37 UTC] No.46193483[source]▶

If you provide it a benchmark script (or ask it to write one) so it has concrete numbers to go off of, it will do a better job.

I'm not saying these things don't hallucinate constantly, they do. But you can steer them toward better output by giving them better input.

The "confident idiot" problem: Why AI needs hard rules, not vibe checks