Update: engineers updated the @Grok system prompt, removing a line that encouraged it to be politically incorrect when the evidence in its training data supported it.

  • sqgl@sh.itjust.works
    link
    fedilink
    English
    arrow-up
    6
    ·
    edit-2
    12 hours ago

    Why is PC even factored in? Shouldn’t the LLM just favour evidence from the outset?

    • kewjo@lemmy.world
      link
      fedilink
      English
      arrow-up
      9
      arrow-down
      1
      ·
      11 hours ago

      no one understands how these models work, they just throw shit at it and hope it sticks

      • ToastedRavioli@midwest.social
        link
        fedilink
        English
        arrow-up
        5
        arrow-down
        1
        ·
        11 hours ago

        Well thats just not true, I mean LLMs really are not extremely complicated. At the end of the day it’s just algorithmic sorting of information

        So in practice any given flavor of LLM is basically like a librarian. Your librarian can be a well adjusted human or an antisemitic nutjob, but so long as they sort information and can point it out to you technically they are doing their job equally as well. The real problem doesnt begin until youve trained the librarian to recommend Mein Kampf when people ask for information about the water cycle or whatever

        • Thorry84@feddit.nl
          link
          fedilink
          English
          arrow-up
          5
          ·
          9 hours ago

          I think they meant people don’t know how these models work in practice. On a theoretical level they are well understood. But in practice they behave in a chaotic way (chaotic in the math sense of the word). A small change in the input can lead to wild swings in the output. So when people want to change the way the models acts by changing the system prompt, it’s basically impossible to say what change should be made to achieve the desired outcome. And often such a change doesn’t even exist, only something that’s close enough is possible. So they have to resort to trial and error, trying to tweak things like the system prompt and seeing what happens.

    • acosmichippo@lemmy.world
      link
      fedilink
      English
      arrow-up
      5
      ·
      11 hours ago

      The problem is LLMs are programmed by biased people and trained on biased data. So “good” AI developers will attempt to mitigate that in some way.