Surprised pikachu face

  • socialmedia@lemmy.world
    link
    fedilink
    English
    arrow-up
    23
    arrow-down
    1
    ·
    3 months ago

    Just want to point out that it absolutely is possible to train an AI that will keep track of its sources for inspiration and can attribute those when it makes a response.

    Meaning creators could be compensated for their parts of AI generated stuff, if anyone wanted to.

      • UnderpantsWeevil@lemmy.world
        link
        fedilink
        English
        arrow-up
        5
        arrow-down
        2
        ·
        3 months ago

        The entire training set isn’t used in each permutation. Your keywords are building the samples based on metadata tags tied back to the original images.

        If you ask for “Iron Man in a cowboy hat”, the toolset will reach for some catalog of Iron Man images and some catalog of cowboy hat images and some catalog of person-in-cowboy-hat images, when looking for a basis of comparison as it renders the image.

        These would be the images attributed to the output.

        • Trantarius@lemmy.dbzer0.com
          link
          fedilink
          English
          arrow-up
          2
          ·
          3 months ago

          Do you have a source for this? This sounds like fine-tuning a model, which doesn’t prevent data from the original training set from influencing the output. The method you described would only work if the AI is trained from scratch on only images of iron man and cowboy hats. And I don’t think that’s how any of these models work.

    • mm_maybe@sh.itjust.works
      link
      fedilink
      English
      arrow-up
      1
      ·
      3 months ago

      I think that there are some people working on this, and a few groups that have claimed to do it, but I’m not aware of any that actually meet the description you gave. Can you cite a paper or give a link of some sort?