Re:Two things LLM coding agents are still bad at
by ngruhn on Thursday October 09, 2025 @02:50PM
(#45531575)
I was about to write my own tool for this but then I discovered:
git diff --color-moved=dimmed-zebra
That shows a lot of code that was properly moved/copied in gray (even if it's an insertion). So gray stuff exactly matches something that was there before. Can also be enabled by default in the git config.
Re:Two things LLM coding agents are still bad at
by VMG on Thursday October 09, 2025 @02:59PM
(#45531672)
Perfect. This is why I visit this website
Re:Two things LLM coding agents are still bad at
by erichocean on Thursday October 09, 2025 @03:34PM
(#45532088)
I used autochrome[0] for Clojure code to do this. (I also made some improvements to show added/removed comments, top-level form moves, and within-string/within-comment edits the way GitHub does.)
At first I didn't like the color scheme and replaced it with something prettier, but then I discovered it's actually nice to have it kinda ugly, makes it easier to detect the diffs.
Re:Two things LLM coding agents are still bad at
by karczex on Thursday October 09, 2025 @03:21PM
(#45531943)
Thanks:)
Re:Two things LLM coding agents are still bad at
by paulhebert on Thursday October 09, 2025 @05:36PM
(#45533364)
I would love if GitHub implemented this in their UI! There’s and issue: https://github.com/orgs/community/discussions/9632
Re:Two things LLM coding agents are still bad at
by godelski on Thursday October 09, 2025 @08:50PM
(#45534509)
That's a great solution and I'm adding it to my fallback. But also, people might be interested in diff-so-fancy[0]. I also like using batcat as a pager.
Re:Two things LLM coding agents are still bad at
by steveklabnik on Thursday October 09, 2025 @01:09PM
(#45530389)
I personally agree with you. I think that stacked diffs will be more important as a way of dealing with those larger diffs.
Re:Two things LLM coding agents are still bad at
by alfalfasprout on Thursday October 09, 2025 @04:28PM
(#45532688)
Yep, this pattern of LLMs reviewing LLMs is terrifying to me. It's literally the inmates running the asylum.
Needs to clearly handle the large diffs they produce - anyone have any ideas