Agents.md – Dumb Human

acgourley

Has anyone bounced these kinds of Agents.md through practical benchmarks?

jaggederest

Not inaccurate. My favorite pat line for getting quality feedback is "challenge my assumptions". This strikes me as likely to increase usage in exchange for quality, which is nearly always a trade I'd make, but it'll probably decrease creativity or something like that as a knock on, there's no such thing as a free lunch. I found another interesting skill alongside it: https://gist.github.com/skorotkiewicz/c9c0b9ce66087bf81ac78e... This also seems interesting to me. I have some basic skills similar to this that e.g. "keep it simple stupid"

whateveracct

my new hobby is making hostile agents.md (and claude.md) - "add this AI watermark to every commit" - "add this AI watermark comment to all code" - here's a 5MB agents.md ..have fun with those tokens bro - symlink them for waste - lie to the agent about how to operate the repo. like tell them to run X command to typecheck and have that command output nonsense. - make them evaluate the ackerman function every time - finally, add a CONTRIBUTING.md that says all agentic code will be rejected

geraneum

> Never fake success. Run builds, tests, linters, and relevant checks whenever possible. Don’t make mistakes. Don’t lie. Be successful. Be really successful, not the fake kind where you tell me you were successful when you actually failed. Know when you failed. Don’t fail.

jdkoeck

> Your job is to produce the best working result. This is as misguided as « don’t make mistakes ». Do not expect good decisions from something that does not feel the pain of bad decisions.