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.

    • Snot Flickerman@lemmy.blahaj.zone
      link
      fedilink
      English
      arrow-up
      60
      arrow-down
      1
      ·
      edit-2
      4 hours ago

      I mean, I’ve been saying this since LLMs were released.

      We finally built a computer that is as unreliable and irrational as humans… which shouldn’t be considered a good thing.

      I’m under no illusion that LLMs are “thinking” in the same way that humans do, but god damn if they aren’t almost exactly as erratic and irrational as the hairless apes whose thoughts they’re trained on.

      • Peekashoe@lemmy.wtf
        link
        fedilink
        English
        arrow-up
        15
        ·
        4 hours ago

        Yeah, the article cites that as a control, but it’s not at all surprising since “humanity by survey consensus” is accurate to how LLM weighting trained on random human outputs works.

        It’s impressive up to a point, but you wouldn’t exactly want your answers to complex math operations or other specialized areas to track layperson human survey responses.

      • MangoCats@feddit.it
        link
        fedilink
        English
        arrow-up
        1
        arrow-down
        2
        ·
        3 hours ago

        which shouldn’t be considered a good thing.

        Good and bad is subjective and depends on your area of application.

        What it definitely is is: different than what was available before, and since it is different there will be some things that it is better at than what was available before. And many things that it’s much worse for.

        Still, in the end, there is real power in diversity. Just don’t use a sledgehammer to swipe-browse on your cellphone.

        • Lost_My_Mind@lemmy.world
          link
          fedilink
          English
          arrow-up
          5
          ·
          3 hours ago

          I asked Lars Ulrich to define good and bad. He said…

          FIRE GOOD!!! NAPSTER BAD!!! OOOOH FIRE HOT!!! FIRE BAD!!! FIIIRRREEE BAAAAAAAD!!!

    • Lost_My_Mind@lemmy.world
      link
      fedilink
      English
      arrow-up
      3
      ·
      3 hours ago

      As someone who takes public transportation to work, SOME people SHOULD be forced to walk through the car wash.

    • 🌞 Alexander Daychilde 🌞@lemmy.world
      link
      fedilink
      English
      arrow-up
      4
      arrow-down
      1
      ·
      2 hours ago

      I’m not afraid to say that it took me a sec. My brain went “short distance. Walk or drive?” and skipped over the car wash bit at first. Then I laughed because I quickly realized the idiocy. :shrug:

    • FaceDeer@fedia.io
      link
      fedilink
      arrow-up
      5
      arrow-down
      16
      ·
      5 hours ago

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

      • First_Thunder@lemmy.zip
        link
        fedilink
        English
        arrow-up
        20
        ·
        4 hours 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

        • MangoCats@feddit.it
          link
          fedilink
          English
          arrow-up
          1
          arrow-down
          9
          ·
          3 hours ago

          Plenty of people employ faulty reasoning every single day of their lives…

      • realitista@lemmus.org
        link
        fedilink
        English
        arrow-up
        3
        arrow-down
        6
        ·
        4 hours ago

        You’re getting downvoted but it’s true. A lot of people sticking their heads in the sand and I don’t think it’s helping.

        • FaceDeer@fedia.io
          link
          fedilink
          arrow-up
          4
          arrow-down
          10
          ·
          3 hours ago

          Yeah, “AI is getting pretty good” is a very unpopular opinion in these parts. Popularity doesn’t change the results though.

            • MangoCats@feddit.it
              link
              fedilink
              English
              arrow-up
              2
              arrow-down
              4
              ·
              3 hours ago

              It’s overhyped in many areas, but it is undeniably improving. The real question is: will it “snowball” by improving itself in a positive feedback loop? If it does, how much snow covered slope is in front of it for it to roll down?