• DokPsy@infosec.pub
    link
    fedilink
    arrow-up
    29
    arrow-down
    1
    ·
    1 year ago

    I don’t mind the tool itself if you use it as such. I do mind when people use its output as the final product. See: the lawyer who used chatgpt for a legal brief

    • XEAL@lemm.ee
      link
      fedilink
      arrow-up
      6
      arrow-down
      1
      ·
      1 year ago

      The lawyer fuck up is what happens when someone doesn’t know or understand the limitations of a LLM.

      If you want a GPT model tailored and specialized for a specific task, you have to train it with custom data, fine tune it and tweak the model’s parameters. You cannot do that from the ChatGPT web/app, you need a custom implementation coded in Python or some other language.

        • XEAL@lemm.ee
          link
          fedilink
          arrow-up
          2
          ·
          1 year ago

          Thanks. I have a quite powerful rig, but at the moment I work with OpenAI’s API using GPT 3.5 Turbo using a custom (but shitty) Python script with a simple Gradio web interface. However, I mostly stopped improving or updating it months ago. As long as I don’t use LlamaIndex, the cost is quite low.

          I already use Stable Diffusion WebUI, tho.

          Also the “fine tuning” I was talking about is this https://platform.openai.com/docs/guides/fine-tuning

          • TechieDamien@lemmy.ml
            link
            fedilink
            arrow-up
            2
            ·
            1 year ago

            I am aware what fine tuning is. It is available from the train tab while the base checkpoint is loaded in both cases.

      • uralsolo [he/him]@hexbear.net
        link
        fedilink
        English
        arrow-up
        2
        ·
        edit-2
        1 year ago

        I also don’t think that the ChatGPT model is able to do something that requires referencing case law or medical texts or whatever else at all in its current form. The way it works by generating probabilities for certain words is all wrong for doing something where the value of the output isn’t subjective - you need the model to be able to distinguish between facts and opinion, you need it to be able to cite sources for what it says, you need it to be able to produce coherent cause and effect chains and formulate an argument, all things which no currently existing LLM is capable of no matter how much you fine tune it because of how it works.

      • DokPsy@infosec.pub
        link
        fedilink
        arrow-up
        1
        ·
        1 year ago

        I’m glad you understand my point. Chatgpt is not Google. It’s a language model that will give you something that looks like the thing you asked for it to provide. It can and will pull facts out of its recycle bin if it fits the cadence of what it expects the answer to look like.

        • XEAL@lemm.ee
          link
          fedilink
          arrow-up
          1
          ·
          edit-2
          1 year ago

          ChatGPT is not Google, but sometimes it can work as a glorified search engine or even compete with asking in forums.

          I’ve lost count of how many times ChatGPT has produced Bash or Python code for what I needed. Yes, sometimes the code is wrong and/or requires tweaking and sometimes I resorted to look into the documentation, but no one will answer faster and anytime of the day like ChatGPT does, at least not for free.

          • DokPsy@infosec.pub
            link
            fedilink
            arrow-up
            1
            ·
            1 year ago

            It’s a tool to aid in creating a product, not a tool that magics out a finished product. That’s my point. Too many people use it as the latter instead of the former.

            • XEAL@lemm.ee
              link
              fedilink
              arrow-up
              1
              ·
              1 year ago

              100% agree.

              Maybe, with lots of training, weaking and testing the latter could be achieved, but that’s it.

      • DokPsy@infosec.pub
        link
        fedilink
        arrow-up
        2
        ·
        1 year ago

        Letting a language model do the work of thinking is like building a house and using a circular saw to put nails in. It will do it but you should not trust the results.

        It is not Google. It can, will, and has made up facts as long as it fits the format expected

        Not at the very least proof reading and fact checking the output is beyond lazy and a terrible use of a tool. Using it to create the end product instead of as a tool to use in creation of an end product are two very different things.

          • Carighan Maconar@lemmy.world
            link
            fedilink
            arrow-up
            2
            ·
            1 year ago

            The person you first replied to asked you to see the legal brief as an example of why they mind using the output as the finished product. You then asked for an explanation. To which I asked you, hey, have you actually looked at that example? You have not.

            What exactly do you want here, other than be argumentative for combative reasons?