• FiniteBanjo@feddit.online
    link
    fedilink
    English
    arrow-up
    0
    ·
    17 hours ago

    They Don’t pass 4/5.

    They pass 0/5 because they are 80% (that number is way too optimistic btw) accurate to human output on every one of the five attempts.

    They also can’t be forced to learn and retake the trial because they don’t have any contextual awareness, they just guess the next word in a sequence.

    Even if a machine made 4 self edits sucessfully, it would be permanently disfigured by the one failure and no longer be capable of making good edits.

    • Zos_Kia@jlai.lu
      link
      fedilink
      English
      arrow-up
      0
      ·
      2 hours ago

      That’s cool but you’re describing the models from 2 years ago and also not considering harnesses, which account for most of the progress of the last year or so.