Few things give me more dread than reviewing the mediocre code written by an overconfident LLM, but arguing in a PR with an overconfident LLM that its review comments are wrong is up there.
by nolanl
0 subcomment
I've found Bugbot to be shockingly effective at finding bugs in my PRs. Even when it's wrong, it's usually worth adding a comment, since it's the kind of mistake a human reviewer would make.
by agent013
1 subcomments
The biggest problem with LLM reviews for me is not false positives, but authority. Younger devs are used to accepting bot comments as the ultimate truth, even when they are clearly questionable
Hacker News