• HakFoo@lemmy.sdf.org
    link
    fedilink
    English
    arrow-up
    10
    ·
    2 months ago

    As a (non-game) developer, AI isn’t even that great at reducing my burden.

    The organization is enthusiastic about AI, so we set up the Gitlab Copilot plugin for our development tools.

    Even as “spicy autocomplete” only about one time in 4 or so it makes a useful suggestion.

    There’s so much hallucination, trying to guess the next thing I want and usually deciding on something that came out of its shiny metal ass. It actually undermines the tool’s non-AI features, which pre-index the code to reliably complete fields and function names that actually exist.

    • Dark Arc@social.packetloss.gg
      link
      fedilink
      English
      arrow-up
      4
      ·
      edit-2
      2 months ago

      I was going to defend “well ray tracing is definitely a time saver for game developers because they don’t have to manually fake lighting anymore.” Then I remembered ray tracing really isn’t AI at all… So yeah, maybe for artists that don’t need to use as detailed of textures because the AI models can “figure out” what it presumably should look like with more detail.

      I’ve been using FSR as a user on Hunt Showdown and I’ve been very impressed with that as a 2k -> 4k upscale… It really helps me get the most out of my monitors and it’s approximately as convincing as the native 4k render (lower resolutions it’s not nearly as convincing for … but that’s kind of how these things go). I see the AI upscalers as a good way to fill in “fine detail” in a convincing enough way and do a bit better than traditional anti aliasing.

      I really don’t see this as being a developer time saver though, unless you just permit yourself to write less performant code … and then you’re just going to get complaints in the gaming space. Writing the “electron” of gaming just doesn’t fly like it does with desktop apps.

    • hoshikarakitaridia@lemmy.world
      link
      fedilink
      English
      arrow-up
      2
      ·
      2 months ago

      I know this is a bit late, but copilot is only ok if used for code completion. I switched to the free tier of supermaven a month ago and it’s been way more helpful, as it can handle context better. Probably cuts coding in half and takes away a third of debugging.

      Asking chatgpt for code has also become better, but imo still not reliable enough to regularly use. Just had some docker code written and it got it wrong 3 times so I gave up on that.

      I get your point, AI can only save time if you know exactly what you’re doing and it will only be helpful sometimes. But when it is, it’s such a time saver.

      • taladar@sh.itjust.works
        link
        fedilink
        English
        arrow-up
        2
        ·
        edit-2
        2 months ago

        Mostly it really is just a fancier auto-complete. It is most useful for situations where you want to essentially do the equivalent of copy&paste and then make changes in a few predictable places in each copy.

        It is total crap at writing code itself to the point where you need to read the code and understand it to know it hasn’t screwed up, something that takes much, much longer than just writing it yourself.

        • hoshikarakitaridia@lemmy.world
          link
          fedilink
          English
          arrow-up
          2
          ·
          2 months ago

          Yeah AI as a dev is shit, but AI as a more thoughtful auto-complete is actually pretty great.

          To me it looks like AIs currently are right at the boundary between being a tool and being a companion. But to be a full companion, they can’t be up against the boundary, they need to be well established and tried and tested as a companion to be used repeatedly, so we’re still a few decades out from that from what I can tell.