HN Explorer

Ask HN: How do you get AI loops to converge?

1 points by outlore ↗ HN
For any arbitrary coding task, how can a Ralph loop break out of a local minima and converge, such that, even if the loop runs again, there are no tasks left to complete?

I want to learn more resources for loop engineering, deterministic tooling etc.

What I am noticing is the agents/subagents oscillate between repeatedly patching the same bits of code over and over, or introducing new bugs.

Thank you!

9 comments

[ 338 ms ] story [ 371 ms ] thread
igrlk
for GUI work the stop condition that worked for me is interaction + visual tests.

make sure all component interactions are automatically tested. screenshot the screens the task touches, and let your agent see what changes it made