• tatterdemalion@programming.dev
    link
    fedilink
    arrow-up
    24
    arrow-down
    3
    ·
    edit-2
    2 days ago

    Pretty much everyone I’ve talked to about this says the same thing. LLMs are useful for one-off scripts or quickly generating boilerplate. It just turns out that those tasks don’t make up the majority of programming work unless you are in a bullshit job anyway.

    We aren’t yet great at knowing when LLM will save time and when it will inflate time.

    • flambonkscious@sh.itjust.works
      link
      fedilink
      English
      arrow-up
      6
      ·
      2 days ago

      If only we libraries online of boilerplate crap with a few options to transfom them slightly… We’d need a lot less datacentres

      • Corngood@lemmy.ml
        link
        fedilink
        arrow-up
        5
        ·
        2 days ago

        We should have tools and libraries that help us avoid boilerplate, not ones that help us write more of it.

        • flambonkscious@sh.itjust.works
          link
          fedilink
          English
          arrow-up
          1
          ·
          2 days ago

          Yes!

          I’m not even a programmer, but lot of this is really dictated by the language, isn’t it? (C or .Net, for example - and all the default crap needed for UI elements I’ve had to endure in Powershell, which was probably calling a .Net library)

          • Corngood@lemmy.ml
            link
            fedilink
            arrow-up
            3
            ·
            2 days ago

            C at least has a preprocessor. C# has almost nothing except generators, which are a huge pain in the ass. Java seems to be similar.

            Lisp is the greatest. Everything else is in between.

    • FizzyOrange@programming.dev
      link
      fedilink
      arrow-up
      7
      arrow-down
      2
      ·
      2 days ago

      They’re probably pretty good for CRUD apps, which do tend to be like 50% boilerplate, but also I also wouldn’t characterise them as “bullshit”. Boring maybe.