alt Hacker NewsI love the accept reject flow because I still constantly have to stop AI models from writing awful architecture or reimplementing code we already wrote elsewhere
Replies
I just check the git diff after claude code writes stuff. Stage things before letting it run wild so I can undo whatevs.
Yeah, I have found the same. A lot of times it does get things right, but if it deviates man it can just drift hard.
For example, sometimes Claude just obsessively reads files and goes on massive tangents. Then when I stop it and ask, "why are you doing that?", it kindly apologizes and admits it shouldn't have gone on a tangent.
The token burn if I don't stop it would be quite high.
Granted, this might be because I'm not giving it optimal prompt/negative-prompt instructions though.
How is it different from Keep / Discard in other tools? I've been slowly converting my git repositories to jj locally because that gives me more granular fallback and mix and match options.