• sunbeam60@feddit.uk
    link
    fedilink
    English
    arrow-up
    0
    ·
    1 day ago

    In my experience, AI writes better code (and tests) than most developers and much worse architecture than a senior engineer.

    I suspect the architecture is fine, really, but AI is so comfortable juggling 19 balls that it’s architecture never needs simplification and clarity. But as a human reading it, it’s just a mess and humans need much more coherence and encapsulation.

    • moseschrute@lemmy.world
      link
      fedilink
      English
      arrow-up
      0
      ·
      19 hours ago

      I feel like AI writes good code but then every once in a while it does the absolute dumbest thing in the world. And you have to be really vigilant so you can’t it doing dumb shit.

      • sunbeam60@feddit.uk
        link
        fedilink
        English
        arrow-up
        0
        ·
        14 hours ago

        For sure. I’d never just accept AI code without serious investigation but it’s a useful tool for good programmers.

    • log@lemmy.blahaj.zone
      link
      fedilink
      English
      arrow-up
      0
      ·
      22 hours ago

      Then most developers you know are subpar. Frontier models routinely write far worse code than I. And I am only a moderately decent dev.

      I have even seen llm code generated with a frontier model that blew straight through array boundaries without a worry in the world.

      They can be useful at work, especially for tech I know little about, and as an additional set of eyes to avoid easy mistakes like off by ones, or doing wrong pointer arithmetic, but they are pretty abysmal at code generation.

      • Taleya@aussie.zone
        link
        fedilink
        English
        arrow-up
        0
        ·
        18 hours ago

        Nononono “tech you know little about” means you don’t know enough to see the holes it’s making

        • log@lemmy.blahaj.zone
          link
          fedilink
          English
          arrow-up
          0
          ·
          6 hours ago

          True, but what I mean is that it can find ways to do what I need to do even for things that I don’t know a lot about. If the “solution” it finds ends up being a bunch of hacks I change my approach. If it finds supported and documented APIs, I read their documentation and make sure that my mental model of the the things I’ve just learned about matches the code and explanation from the llm, and if they do I rewrite the code in a way that makes sense and iterate from there.

          I also don’t copy paste the code and rewrite it inline. I rewrite it in a different window from scratch. The llm is confined to its browser window.

          Essentially, I use these things the way I used to use google a few years ago: searching for documentation and examples. That is no longer possible with today’s search engines.

      • red_tomato@lemmy.world
        link
        fedilink
        English
        arrow-up
        0
        ·
        19 hours ago

        I thought the same earlier this year. Opus 4.8 mostly produced garbage code in my eyes. Then Opus 5.5 came and now it can routinely produce about the same quality as me but much faster.