• ExLisper@lemmy.curiana.net
    link
    fedilink
    arrow-up
    5
    arrow-down
    1
    ·
    4 天前

    AI writes overly complex ccode

    100%. It doesn’t have a concept of maintainability. If you tell it to do X it will happily rewrite half o the codebase to achieve it where a person would stop and look for alternative solution. I see this as the biggest issue with current models. They can implement anything but someone still needs to check if the solution makes sense. AI can’t tell.

    • FizzyOrange@programming.dev
      link
      fedilink
      arrow-up
      2
      arrow-down
      1
      ·
      2 天前

      Funny I’ve seen the opposite. I want it to rewrite half the codebase to do things properly. A human shouldn’t do that because of the effort, but it’s no issue for AI.

      However it very often says “that’s too big of a change so I’ll do this workaround instead” which is not what I want at all.

      But I agree they sometimes implement things that don’t actually make sense to do. Mostly you can solve that by just asking how to program / code works at a high level without needing to read every line.

      • ExLisper@lemmy.curiana.net
        link
        fedilink
        arrow-up
        2
        arrow-down
        1
        ·
        2 天前

        Yes, sometimes it’s the opposite. I guess the issue is simply that AI can’t tell between those two. It’s great a big rewrites because it has such a huge context but it will often try to sneak in some things you didn’t ask for or skip some parts because… no one knows why. Then on other occasions it will add tons of code to fix a bug in some extremely unlikely path. It’s very smart and very stupid at the same time.