• Throwaway@lemm.ee
    link
    fedilink
    English
    arrow-up
    44
    arrow-down
    3
    ·
    11 months ago

    Not without making a new model. AI arent like normal programs, you cant debug them.

        • Echo Dot@feddit.uk
          link
          fedilink
          English
          arrow-up
          1
          arrow-down
          12
          ·
          11 months ago

          Well that’s an easy problem to solve by not being a useless programmer.

          • Throwaway@lemm.ee
            link
            fedilink
            English
            arrow-up
            10
            arrow-down
            2
            ·
            11 months ago

            You’d think so, but it’s just not. Pretend “Gamer” is a slur. I can type it “G A M E R”, I can type it “GAm3r”, I can type it “GMR”, I can mix and match. It’s a never ending battle.

            • Echo Dot@feddit.uk
              link
              fedilink
              English
              arrow-up
              1
              arrow-down
              3
              ·
              11 months ago

              That’s because regular expressions are a terrible way to try and solve the problem. You don’t do exact tracking matching you do probabilistic pattern matching and then if the probability of something exceeds a certain preset value then you block it then you alter the probability threshold on the frequency of the comment coming up in your data set. Then it’s just a matter of massaging your probability values.

      • anteaters@feddit.de
        link
        fedilink
        English
        arrow-up
        6
        arrow-down
        1
        ·
        11 months ago

        They’ll need another AI to screen what you tell the original AI. And at some point they will need another AI that protects the guardian AI form malicious input.

    • raynethackery@lemmy.world
      link
      fedilink
      English
      arrow-up
      1
      arrow-down
      4
      ·
      11 months ago

      I just find that disturbing. Obviously, the code must be stored somewhere. So, is it too complex for us to understand?

      • Overzeetop@sopuli.xyz
        link
        fedilink
        English
        arrow-up
        12
        ·
        11 months ago

        It’s not code. It’s a matrix of associative conditions. And, specifically, it’s not a fixed set of associations but a sort of n-dimensional surface of probabilities. Your prompt is a starting vector that intersects that n-dimensional surface with a complex path which can then be altered by the data it intersects. It’s like trying to predict or undo the rainbow of colors created by an oil film on water, but in thousands or millions of directions more in complexity.

        The complexity isn’t in understanding it, it’s in the inherent randomness of association. Because the “code” can interact and change based on this quasi-randomness (essentially random for a large enough learned library) there is no 1:1 output to input. It’s been trained somewhat how humans learn. You can take two humans with the same base level of knowledge and get two slightly different answers to identical questions. In fact, for most humans, you’ll never get exactly the same answer to anything from a single human more than simplest of questions. Now realize that this fake human has been trained not just on Rembrandt and Banksy, Jane Austin and Isaac Asimov, but PoopyButtLice on 4chan and the Daily Record and you can see how it’s not possible to wrangle some sort of input:output logic as if it were “code”.

      • 31337@sh.itjust.works
        link
        fedilink
        English
        arrow-up
        3
        ·
        11 months ago

        Yes, the trained model is too complex to understand. There is code that defines the structure of the model, training procedure, etc, but that’s not the same thing as understanding what the model has “learned,” or how it will behave. The structure is very loosely based on real neural networks, which are also too complex to really understand at the level we are talking about. These ANNs are just smaller, with only billions of connections. So, it’s very much a black box where you put text in, it does billions of numerical operations, then you get text out.

      • Throwaway@lemm.ee
        link
        fedilink
        English
        arrow-up
        1
        arrow-down
        8
        ·
        11 months ago

        Pretty much, and it’s not written by a human, making it even worse. If you’ve every tried to debug minimized code, it’s a bit like that, but so much worse.