Elektrine lite

← Feed

@theneverfox@pawb.social

Post #42164

2025-12-08 16:24 UTC

AI isn’t good at changing code, or really even understanding it… It’s good at writing it, ideally 50-250 lines at a time

Replies (3)

  • @Evotech@lemmy.world 2025-12-08 16:35

    I’m just not following the mindset of “get ai to code your whole program” and then have real people maintain it? Sounds counter productive I think you need to make your code for an Ai to maintain. Use Static code analysers like SonarQube to ensure that the code is maintainable and that functions are small and well defined as you write it.

    Open ##42193

  • @lepinkainen@lemmy.world 2025-12-08 16:37

    I’ve made full-ass changes on existing codebases with Claude It’s a skill you can learn, pretty close to how you’d work with actual humans

    Open ##42204

  • @MangoCats@feddit.it 2025-12-09 14:12

    It’s good at writing it, ideally 50-250 lines at a time I find Claude Sonnet 4.5 to be good up to 800 lines at a chunk. If you structure your project into 800ish line chunks with well defined interfaces you can get 8 to 10 chunks working cooperatively pretty easily. Beyond about 2000 lines in a chunk, if it’s not well defined, yeah - the hallucinations start to become seriously problematic. The new Opus 4.5 may have a higher complexity limit, I haven’t really worked with it enough to characterize… I do find Opus 4.5 to get much slower than Sonnet 4.5 was for similar problems.

    Open ##45397