• jsomae@lemmy.ml
    link
    fedilink
    arrow-up
    1
    ·
    5 hours ago

    This is not correct. Even if trained on purely peer-reviewed and published math papers, it will still make math errors.

        • surph_ninja@lemmy.world
          link
          fedilink
          arrow-up
          1
          ·
          3 hours ago

          I’m confused. Are you saying all AI models are bad at math, or one in particular? You’re speaking broadly, so I assume the former.

          • jsomae@lemmy.ml
            link
            fedilink
            arrow-up
            1
            ·
            edit-2
            3 hours ago

            Broadly. All AI models are bad at math. By math I mean mathematical reasoning, not arithmetic. (It’s already well-known they’re bad at arithmetic unsupplemented.)

            Actually – they’re pretty good at math as far as a typical undergrad goes. But they still make a lot of mistakes; 40% of the time is not an unreasonable estimate, depending on use case.