I have not read the article yet but i think this is a good topic to discuss here.

  • robot_dog_with_gun [they/them]@hexbear.net
    link
    fedilink
    English
    arrow-up
    3
    arrow-down
    5
    ·
    4 days ago

    LLMs work by hallucinating, the wild shit that gets shared isn’t an accident, it’s how they generate all their output.

    people have trained models on internal document sets and it gets things wrong, they are simply not useful for facts. they don’t think, they don’t have knowledge, they just pull scrabble tiles in a clever statistical way that fools you into trusting it.

    • percyraskova@lemmygrad.ml
      link
      fedilink
      arrow-up
      7
      ·
      4 days ago

      thats a tooling/prompting/context window management problem. it can be solved with proper programming procedures and smart memory management