• Knock_Knock_Lemmy_In@lemmy.world
    link
    fedilink
    English
    arrow-up
    2
    ·
    8 days ago

    Run something with a 70% failure rate 10x and you get to a cumulative 98% pass rate. LLMs don’t get tired and they can be run in parallel.

    • jsomae@lemmy.ml
      link
      fedilink
      English
      arrow-up
      3
      ·
      8 days ago

      The problem is they are not i.i.d., so this doesn’t really work. It works a bit, which is in my opinion why chain-of-thought is effective (it gives the LLM a chance to posit a couple answers first). However, we’re already looking at “agents,” so they’re probably already doing chain-of-thought.

      • Knock_Knock_Lemmy_In@lemmy.world
        link
        fedilink
        English
        arrow-up
        3
        ·
        8 days ago

        Very fair comment. In my experience even increasing the temperature you get stuck in local minimums

        I was just trying to illustrate how 70% failure rates can still be useful.

            • Log in | Sign up@lemmy.world
              link
              fedilink
              English
              arrow-up
              2
              ·
              8 days ago

              Ah, my bad, you’re right, for being consistently correct, I should have done 0.3^10=0.0000059049

              so the chances of it being right ten times in a row are less than one thousandth of a percent.

              No wonder I couldn’t get it to summarise my list of data right and it was always lying by the 7th row.

              • Knock_Knock_Lemmy_In@lemmy.world
                link
                fedilink
                English
                arrow-up
                1
                ·
                7 days ago

                That looks better. Even with a fair coin, 10 heads in a row is almost impossible.

                And if you are feeding the output back into a new instance of a model then the quality is highly likely to degrade.

                • Log in | Sign up@lemmy.world
                  link
                  fedilink
                  English
                  arrow-up
                  1
                  ·
                  7 days ago

                  Whereas if you ask a human to do the same thing ten times, the probability that they get all ten right is astronomically higher than 0.0000059049.

            • jwmgregory@lemmy.dbzer0.com
              link
              fedilink
              English
              arrow-up
              1
              ·
              8 days ago

              don’t you dare understand the explicitly obvious reasons this technology can be useful and the essential differences between P and NP problems. why won’t you be angry >:(