←back to thread

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

(steerlabs.substack.com)
323 points steerlabs | 2 comments | 04 Dec 25 20:48 UTC | HN request time: 0s | source
Show context
nickdothutton ◴[08 Dec 25 13:30 UTC] No.46192002[source]▶
- 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".

replies(7): >>46192071 #>>46192493 #>>46192534 #>>46192607 #>>46193483 #>>46194123 #>>46194739 #
jama211 ◴[08 Dec 25 14:29 UTC] No.46192607[source]▶
While you’re making unstructured requests and expecting results, why don’t you ask your barista to make you a “better coffee” with no instructions. Then, when they make a coffee with their own brand of creativity, complain that it tastes worse and you want your money back.
replies(5): >>46192820 #>>46192865 #>>46193079 #>>46195156 #>>46197842 #
1. nickdothutton ◴[08 Dec 25 15:09 UTC] No.46193079[source]▶
I was experimenting with Claude Code and requested something more CPU efficient in a very small project, there were a few avenues to explore, I was interested to see what path it would take. It turned out that it seized upon something which wasn't consuming much CPU anyway and was difficult to optimise further. I learned that I'd have to be more explicit in future and direct an analysis phase and probably kick-in a few strategies for performance optimisation which it could then explore. The refund request was an amusement. It was $15 well spent on my own learning.
replies(1): >>46213731 #
2. jama211 ◴[10 Dec 25 03:35 UTC] No.46213731[source]▶
Ah ok, so you just totally misrepresented your experiences for comedic effect. Good for you I guess