alt Hacker NewsI know LLM generated code comes with it's own challenges, but the absolutists are definitely clinging to a time that has passed. I saw a recent discussion on Immich where a maintainer flatout denied a PR saying "That diff looks LLM-generated to me; is that indeed the case? If so, we'd prefer not to receive a PR for it" The PR was from a professional software engineer, who worked weeks of his free time on a big feature. Well structured + tested. Dismissed just because AI was used. https://github.com/immich-app/immich/discussions/23745#discu...
"Well structured + tested". Who would know? The diff is almost 200k changed lines. Good on them for saying no to this nonsense.
There's a good chance the actual needed implementation is less than 20k lines (I've found that LLM bloat grows exponentially), but even that's a stretch to review and accept wholesale.