←back to thread

We put a coding agent in a while loop

(github.com)
425 points sfarshid | 2 comments | 24 Aug 25 16:18 UTC | HN request time: 0.546s | source
Show context
beefnugs ◴[24 Aug 25 17:01 UTC] No.45005811[source]▶
"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."

Isn't this the exact opposite of every other piece of advice we have gotten in a year?

Another general feedback just recently, someone said we need to generate 10 times, because one out of those will be "worth reviewing"

How can anyone be doing real engineering in such a: pick the exact needle out of the constantly churning chaos-simulation-engine that (crashes least, closest to desire, human readable, random guess)

replies(5): >>45005876 #>>45006945 #>>45007356 #>>45009461 #>>45011229 #
1. dhorthy ◴[24 Aug 25 17:12 UTC] No.45005876[source]▶
Hmm what sorts of advice in the last year are you referring to? Like the “run it ten times and pick the best one” thing? Or something else?

I kind of agree that picking from 10 poorly-promoted projects is dumb.

The engineering is in setting up the engine and verification so one agent can get it right (or 90% right) on a single run (of the infinite ish loop)

replies(1): >>45006274 #
2. jjani ◴[24 Aug 25 18:00 UTC] No.45006274[source]▶
> Hmm what sorts of advice in the last year are you referring to?

They're almost certainly referring to first creating a fleshed out spec and then having it implement that, rather than just 100 words.