• Amoeba_Girl@awful.systems
    link
    fedilink
    English
    arrow-up
    0
    ·
    7 months ago

    What I find delightful about this is that I already wasn’t impressed! Because, as the paper goes on to say

    Moreover, although the UBE is a closed-book exam for humans, GPT-4’s huge training corpus largely distilled in its parameters means that it can effectively take the UBE “open-book”

    And here I was thinking it not getting a perfect score on multiple-choice questions was already damning. But apparently it doesn’t even get a particularly good score!

    • EatATaco@lemm.ee
      link
      fedilink
      English
      arrow-up
      0
      ·
      7 months ago

      Why is that a criticism? This is how it works for humans too: we study, we learn the stuff, and then try to recall it during tests. We’ve been trained on the data too, for neither a human nor an ai would be able to do well on the test without learning it first.

      This is part of what makes ai so “scary” that it can basically know so much.

      • Soyweiser@awful.systems
        link
        fedilink
        English
        arrow-up
        0
        ·
        7 months ago

        Dont anthropomorphise. There is quite the difference between a human and an advanced lookuptable.

        • Phoenixz@lemmy.ca
          link
          fedilink
          English
          arrow-up
          0
          ·
          7 months ago

          Well… I do agree with you but human brains are basically big prediction engines that use lookup tables, experience, to navigate around life. Obviously a super simplification, and LLMs are nowhere near humans, but it is quite a step in the direction.

        • EatATaco@lemm.ee
          link
          fedilink
          English
          arrow-up
          0
          ·
          edit-2
          7 months ago

          I absolutely agree. However, if you think the LLMs are just fancy LUTs, then I strongly disagree. Unless, of course, we are also just fancy LUTs.

          • captainlezbian@lemmy.world
            link
            fedilink
            English
            arrow-up
            0
            ·
            7 months ago

            You ever meet an ai researcher with a background in biology? I’ve discussed this stuff with one. She disagrees with Turing about machines thinking including when ai is in the picture. They process information very differently from how biology does

            • EatATaco@lemm.ee
              link
              fedilink
              English
              arrow-up
              0
              ·
              7 months ago

              This is a vague non answer, although I agree it’s done very differently because our process is biological and ai is not.

              But as I asked elsewhere, what’s the effective difference?

              • self@awful.systems
                link
                fedilink
                English
                arrow-up
                0
                ·
                7 months ago

                so to summarize, your only contributions to this thread are to go “well uh you just don’t know how LLMs work” while providing absolutely no detail of your own, and reporting our regulars for “Civility” when they rightly called you out for being a fucking idiot who’s way out of their depth

                how fucking embarrassing for you

      • exanime@lemmy.today
        link
        fedilink
        English
        arrow-up
        0
        ·
        7 months ago

        Because a machine that “forgets” stuff it reads seems rather useless… considering it was a multiple choice style exam and, as a machine, Chat GPT had the book entirely memorized, it should have scored perfect almost all the time.

        • EatATaco@lemm.ee
          link
          fedilink
          English
          arrow-up
          0
          ·
          7 months ago

          Chat GPT had the book entirely memorized

          I feel like this exposes a fundamental misunderstanding of how LLMs are trained.

        • EatATaco@lemm.ee
          link
          fedilink
          English
          arrow-up
          0
          ·
          7 months ago

          I guess it comes down to a philosophical question as to what “know” actually means.

          But from my perspective is that it certainly knows some things. It knows how to determine what I’m asking, and it clearly knows how to formulate a response by stitching together information. Is it perfect? No. But neither are humans, we mistakenly believe we know things all the time, and miscommunications are quite common.

          But this is why I asked the follow up question…what’s the effective difference? Don’t get me wrong, they clearly have a lot of flaws right now. But my 8 year old had a lot of flaws too, and I assume both will get better with age.

          • flere-imsaho@awful.systems
            link
            fedilink
            English
            arrow-up
            1
            ·
            7 months ago

            i guess it comes down to a philosophical question

            no, it doesn’t, and it’s not a philosophical question (and neither is this a question of philosophy).

            the software simply has no cognitive capabilities.

            • EatATaco@lemm.ee
              link
              fedilink
              English
              arrow-up
              0
              ·
              7 months ago

              I’m not sure I agree, but then it goes to my second question:

              What’s the effective difference?

              • braxy29@lemmy.world
                link
                fedilink
                English
                arrow-up
                0
                ·
                7 months ago

                don’t know why you got downvoted, an LLM is essentially a chinese room, and whether such a room “knows” is still the question.

                  • Turun@feddit.de
                    link
                    fedilink
                    English
                    arrow-up
                    0
                    ·
                    7 months ago

                    Thanks for the link, that’s a fascinating article.

                    The thought experiment (I really liked it) has convinced me that an LLM cannot learn meaning the same way a human does.

                    But two counter arguments arise: first - does it matter? If the only interaction is through thai text, how could the difference between understanding the meaning of Thai text and simple text completion through infinite studying of Thai books be asserted? And second - how is this changed by multimodal models? The author explicitly states that all images are removed from the library and, when asking others on their opinions of the thought experiment, “I’d look for an encyclopedia with images” is considered cheating. That means the author considers images as a weak point of the thought experiment. If the presence of other media did not change the outcome they would not have to be excluded. And if multi modal models change your opinion is that not simply because you underestimated how much you can do with infinite time in a Thai library? What is the fundamental difference between text and an image?

            • Soyweiser@awful.systems
              link
              fedilink
              English
              arrow-up
              1
              ·
              7 months ago

              The dehumanization that happens just because people think LLMs are impressive (they are, just not that impressive) is insane.

    • ebu@awful.systems
      link
      fedilink
      English
      arrow-up
      0
      ·
      7 months ago

      […W]hen examining only those who passed the exam (i.e. licensed or license-pending attorneys), GPT-4’s performance is estimated to drop to 48th percentile overall, and 15th percentile on essays.

      officially Not The Worst™, so clearly AI is going to take over law and governments any day now

      also. what the hell is going on in that other reply thread. just a parade of people incorrecting each other going “LLM’s don’t work like [bad analogy], they work like [even worse analogy]”. did we hit too many buzzwords?

      • Tja@programming.dev
        link
        fedilink
        English
        arrow-up
        0
        ·
        7 months ago

        Not the worst? 48th percentile is basically “average lawyer”. I don’t need a Supreme Court lawyer to argue my parking ticket. And if you train the LLM with specific case law and use RAG can get much better.

        In a worst case scenario if my local lawyer can use AI to generate a letter and just quickly go through it to make sure it didn’t hallucinate, they can process more clients, offer faster service and cheaper prices. Maybe not a revolution but still a win.

        • ebu@awful.systems
          link
          fedilink
          English
          arrow-up
          1
          ·
          7 months ago

          48th percentile is basically “average lawyer”.

          good thing all of law is just answering multiple-choice tests

          I don’t need a Supreme Court lawyer to argue my parking ticket.

          because judges looooove reading AI garbage and will definitely be willing to work with someone who is just repeatedly stuffing legal-sounding keywords into google docs and mashing “generate”

          And if you train the LLM with specific case law and use RAG can get much better.

          “guys our keyword-stuffing techniques aren’t working, we need a system to stuff EVEN MORE KEYWORDS into the keyword reassembler”

          In a worst case scenario if my local lawyer can use AI to generate a letter

          oh i would love to read those court documents

          and just quickly go through it to make sure it didn’t hallucinate

          wow, negative time saved! okay so your lawyer has to read and parse several paragraphs of statistical word salad, scrap 80+% of it because it’s legalese-flavored gobbledygook, and then try to write around and reformat the remaining 20% into something that’s syntactically and legally coherent – you know, the thing their profession is literally on the line for. good idea

          what promptfondlers continuously seem to fail to understand is that verification is the hard step. literally anyone on the planet can write a legal letter if they don’t care about its quality or the ramifications of sending it to a judge in their criminal defense trial. part of being a lawyer is being able to tell actual legal arguments from bullshit, and when you hire an attorney, that is the skill you are paying for. not how many paragraphs of bullshit they can spit out per minute

          they can process more clients, offer faster service and cheaper prices. Maybe not a revolution but still a win.

          “but the line is going up!! see?! sure we’re constantly losing cases and/or getting them thrown out because we’re spamming documents full of nonsense at the court clerk, but we’re doing it so quickly!!”