• Mothra@mander.xyz
    link
    fedilink
    arrow-up
    7
    ·
    1 year ago

    Currently the obvious use is to help people express their thoughts in words. It’s helped me a lot writing out resumes and cover letters. This can be extended to languages other than our main/first one.

    It’s also great to narrow down research on a personal scale in areas where if you have no expertise it would be very hard for you to figure out what you are looking for. I’ve used it to ID plants, insects and diseases successfully. I didn’t get a precise result from ChatGPT, but that’s not what I asked. I just requested pointers in the right direction. It delivered.

    The next obvious implementation is with software interface. I’ve already used it (unsuccessfully) to work with Unreal Engine and other 3d software. I got half baked results because the models were not trained specifically for the software in question. But if they were, it would be very easy to just ask the software how to do something instead of searching everywhere for potential answers. That doesn’t sound too far fetched and I heard it’s a feature that will become standard.

        • crazystuff@discuss.online
          link
          fedilink
          arrow-up
          1
          ·
          1 year ago

          I’d say it works pretty well most of the time, probably depends on the coding language. I use it regularly for PHP/Laravel and JS, and still get surprised when it delivers full working functions from a comment.

          There’s a free trial, give it a try

    • howrar@lemmy.ca
      link
      fedilink
      arrow-up
      2
      ·
      1 year ago

      I’ve never had much success having Copilot write actual code. Where is been very helpful is in writing documentation, boilerplate, and just being a very smart autocomplete. That alone has saved me so much time and energy already.

    • SirGolan@lemmy.sdf.org
      link
      fedilink
      arrow-up
      1
      ·
      1 year ago

      I’m curious about this. What model were you using? A few people at my game dev company have said similar things about it not producing good code for unity and unreal. I haven’t seen that at all. I typically use GPT4 and Copilot. Sometimes the code has a logic flaw or something, but most of the time it works on the first try. I do at this point have a ton of experience working with LLMs so maybe it’s just a matter of prompting? When Copilot doesn’t read my mind (which tends to happen quite a bit), I just write a comment with what I want it to do and sometimes I have to start writing the first line of code but it usually catches on and does what I ask. I rarely run into a problem that is too hairy for GPT4, but it does happen.

      • Mothra@mander.xyz
        link
        fedilink
        arrow-up
        2
        ·
        1 year ago

        I am not sure if my answer is correct- I’ve tried ChatGPT to help me with Unreal in February/March this year. I can’t recall what model.

        As for my query- I’m an artist, not a coder. I found ChatGPT would usually point me in the right direction if I had a simple interface question, but not when dealing with materials… Or the sequencer. I haven’t used Copilot though.

        • SirGolan@lemmy.sdf.org
          link
          fedilink
          arrow-up
          2
          ·
          1 year ago

          Ahh ok that makes sense. I think even with GPT4, it’s still going to be difficult for a non-programmer to use for anything that isn’t fairly trivial. I still have to use my knowledge of stuff to know the right things to ask. In Feb or Mar, you were using GPT3 (4 requires you to pay monthly). 3 is much worse at everything than 4.