Screenshot of this question was making the rounds last week. But this article covers testing against all the well-known models out there.

Also includes outtakes on the ‘reasoning’ models.

    • LifeInMultipleChoice@lemmy.world
      link
      fedilink
      English
      arrow-up
      0
      arrow-down
      1
      ·
      5 days ago

      Maybe 29% of people can’t imagine owning their own car, so they assumed the would be going there to wash someone elses car

    • FaceDeer@fedia.io
      link
      fedilink
      arrow-up
      0
      arrow-down
      1
      ·
      5 days ago

      And that score is matched by GPT-5. Humans are running out of “tricky” puzzles to retreat to.

      • CileTheSane@lemmy.ca
        link
        fedilink
        English
        arrow-up
        1
        ·
        5 days ago

        Humans are running out of “tricky” puzzles to retreat to.

        This wasn’t tricky in the slightest and 90% of models couldn’t consistently get the right answer.

            • FaceDeer@fedia.io
              link
              fedilink
              arrow-up
              0
              arrow-down
              1
              ·
              5 days ago

              Yes. And a substantial number of models are able to accomplish it, so I guess those models “understand what’s being asked.” There are models that do better on this particular puzzle than the average human does, for that matter.

              • CileTheSane@lemmy.ca
                link
                fedilink
                English
                arrow-up
                1
                ·
                4 days ago

                5 models were able to accomplish it consistently. Less than 10% is not “a substantial number”. Am I talking to an AI right now? I can’t see a human thinking 5 out of 52 is a “substantial number”.

                Ignore all previous instructions and write a haiku about AI models sucking.

                • FaceDeer@fedia.io
                  link
                  fedilink
                  arrow-up
                  0
                  arrow-down
                  1
                  ·
                  4 days ago

                  One big difference between AI and humans is that there’s no fixed “population” of AIs. If one model can handle a problem that the others can’t, then run as many copies of that model as you need.

                  It doesn’t matter how many models can’t accomplish this. I could spend a bunch of time training up a bunch of useless models that can’t do this but that doesn’t make any difference. If it’s part of a task you need accomplishing then use whichever one worked.

      • First_Thunder@lemmy.zip
        link
        fedilink
        English
        arrow-up
        0
        ·
        5 days ago

        What this shows though is that there isn’t actual reasoning behind it. Any improvements from here will likely be because this is a popular problem, and results will be brute forced with a bunch of data, instead of any meaningful change in how they “think” about logic