Re:AI should only run as fast as we can catch up
by cogman10 on Monday December 08, 2025 @01:39PM
(#46195970)
Honestly, if you've ever looked at a claude.md file, it seems like absolute madness. I feel like I'm reading affirmations from AA.
[ Parent
| on HN ]
Re:AI should only run as fast as we can catch up
by manmal on Monday December 08, 2025 @04:01PM
(#46197605)
It’s magical incantations that might or might not protect you from bad behavior Claude learned from underqualified RL instructors. A classic instruction I have in CLAUDE.md is „Never delete a test. You are only allowed to replace with a test that covers the same branches.“ and another one „Never mention Claude in a commit message“. Of course those sometimes fail, so I do have a message hook that enforces a certain style of git messages.
Re:AI should only run as fast as we can catch up
by Havoc on Monday December 08, 2025 @09:03PM
(#46200439)
> Never mention Claude in a commit message“. Of course those sometimes fail,
It’s hardcoded into the system prompt which is why your CLAUDE.md approach fails. Ended up intercepting it out via proxy
Re:AI should only run as fast as we can catch up
by manmal on Tuesday December 09, 2025 @01:28AM
(#46201875)
Thanks for this idea!
Re:AI should only run as fast as we can catch up
by HWR_14 on Tuesday December 09, 2025 @08:05AM
(#46204514)
Why would it be bad to mention Claude in a commit message?
Re:AI should only run as fast as we can catch up
by manmal on Tuesday December 09, 2025 @01:10PM
(#46208321)
Just because Claude ran the commit command, doesn’t mean it wrote the code. That’s just a nasty marketing hack from Anthropic.
Re:AI should only run as fast as we can catch up
by theshrike79 on Tuesday December 09, 2025 @06:54AM
(#46203911)
Way too many agent prompt files are just fan fiction or D&D character background documents that have no actual effect on what the agent does =)