←back to thread

We put a coding agent in a while loop

(github.com)
425 points sfarshid | 1 comments | 24 Aug 25 16:18 UTC | HN request time: 0.214s | source
Show context
joshmlewis ◴[25 Aug 25 16:11 UTC] No.45015413[source]▶
One of the biggest nuggets people need to take away from this:

> At one point we tried “improving” the prompt with Claude’s help. It ballooned to 1,500 words. The agent immediately got slower and dumber. We went back to 103 words and it was back on track.

Keep your prompts / agent instructions short. Focus on the wide view, not specifics.

replies(1): >>45018618 #
1. narmiouh ◴[25 Aug 25 20:29 UTC] No.45018618[source]▶
The problem with simple prompts it it gives AI the most leeway to do what it thinks is important, which may work in case of just convert from one language to another (even in those cases it took its own liberties - good or bad). This won't work when devising a new application from scratch or where you are expecting consistent agentic output to be usable in a predictable situation.