Live data from Hacker News

Provide agents with automated feedback

banay.me

1–10 of 87 posts

Re: Provide agents with automated feedback

#4
Beyond Linting and Shell Exec (gh, Playwright etc), what other additional tools did you find useful for your tasks, HN?!

Most of my feedback that can be automated is done either by this or by fuzzing. Would love to hear about other optimisations y'all have found.

Re: Provide agents with automated feedback

#8
post #2

This jumps to proof assistants and barely mentions fuzzing. I've found that with a bit of guidance, Claude is pretty good at suggesting interesting properties to test and writing property tests to verify that invariants hold.

If you give Claude examples of good and bad property tests, and explain why, it gets much better than it was out of the box.

Re: Provide agents with automated feedback

#9
post #4

Beyond Linting and Shell Exec (gh, Playwright etc), what other additional tools did you find useful for your tasks, HN?! Most of my feedback that can be automated is done either by this or by fuzzing. Would love to hear about other optimisations y'all have found.

Teaching them skills for running API and e2e tests and how to filter those tests so it can check if what it did works quickly.

Re: Provide agents with automated feedback

#10
post #20

[stub for offtopicness]

"Back pressure" is already a term widely used in computing for something entirely different: https://schmidscience.com/what-does-back-pressure-in-compute...

I have the same argument with “crypto”
Post reply on HN