• delirious_owl@discuss.online
    link
    fedilink
    arrow-up
    2
    ·
    6 months ago

    Are you sure that you can reproduce the model, given the same inputs? Reproducibility is a difficult property to achieve. I wouldn’t think LLMs are reproduce.

    • sweng
      link
      fedilink
      arrow-up
      2
      ·
      edit-2
      6 months ago

      In theory, if you have the inputs, you have reproducible outputs, modulo perhaps some small deviations due to non-deterministic parallelism. But if those effects are large enough to make your model perform differently you already have big issues, no different than if a piece of software performs differently each time it is compiled.

      • delirious_owl@discuss.online
        link
        fedilink
        arrow-up
        1
        ·
        edit-2
        6 months ago

        That’s the theory for some paradigms that were specifically designed to have the property of determinism.

        Most things in the world, even computers, are non-deterministic

        Nondeterminism isn’t necessarily a bad thing for systems like AI.