• Metype @pawb.social
    link
    fedilink
    English
    arrow-up
    11
    arrow-down
    1
    ·
    14 hours ago

    Code analysis and suggestion tools in many professional IDEs are not powered by LLMs, in the IDEs I use, there’s an available LLM that I’ve disabled the plugin for (and never paid for so it did nothing anyways). LLMs are simply too slow for the kind of code completion and recommendation algorithms used by IDEs and so using them is not “using genAI”

    • theneverfox@pawb.social
      link
      fedilink
      English
      arrow-up
      3
      arrow-down
      2
      ·
      11 hours ago

      Uh… Sorry but no, LLMs are definitely fast enough. It works just like auto complete, except sometimes it’s a genius that pulls the next few lines you were about to write out of the ether, and sometimes it makes up a library to do something you never asked for

      Mostly it works about as well as code completion software, but it’ll name variables much better

      • Boakes@lemmy.world
        link
        fedilink
        English
        arrow-up
        3
        ·
        9 hours ago

        I believe you that genAI is being used for code suggestions, but I wouldn’t call it a genius.

        This is anecdotal but over the last couple of years I’ve noticed Visual Studio’s autocomplete went from suggesting exactly what I wanted more often than not to just giving me hot garbage today. Like even when I’m 3-4 lines in to a very obvious repeating pattern it’ll suggest some nonsense variation on it that’s completely useless. Or just straight making up variable and function names that don’t exist, or suggesting inputs to function calls that don’t match the signature. Really basic stuff that any kind of rules-based system should have no problem with.

        • theneverfox@pawb.social
          link
          fedilink
          English
          arrow-up
          1
          ·
          6 hours ago

          I wouldn’t call it a genius either, it’s just all over the place. Sometimes it’s scary good and predicts your next move, most of the time it’s just okay, sometimes it’s annoyingly bad