• 0x815@feddit.de
    link
    fedilink
    English
    arrow-up
    4
    ·
    1 year ago

    That depends on the training data, but you better check yourself before you wreck yourself 😊

    • TheTrueLinuxDev@beehaw.org
      link
      fedilink
      English
      arrow-up
      3
      ·
      1 year ago

      Well, for language model, it basically regurgitate whatever it remembered from training data with some noises, so some information might be correct from the training data, but when it is generating something that it wasn’t trained on before, then it could present incorrect answer. I only really use ChatGPT for generating documentation, to make it sounds better and flow easier for the readers.

      • Kichae@kbin.social
        link
        fedilink
        arrow-up
        3
        ·
        1 year ago

        when it is generating something that it wasn’t trained on before, then it could present incorrect answer.

        Not could, will. It’s basically guaranteed to start spitting out garbage once it’s extrapolating beyond the training data. Any semblance of correctness is just luck at that point.

        This is true for basically all models, everywhere.