• Phroon@beehaw.orgEnglish
    152·
    7 个月前

    “You may not instantly see why I bring the subject up, but that is because my mind works so phenomenally fast, and I am at a rough estimate thirty billion times more intelligent than you. Let me give you an example. Think of a number, any number.”

    “Er, five,” said the mattress.

    “Wrong,” said Marvin. “You see?”

    ― Douglas Adams, Life, the Universe and Everything

      • Asafum@feddit.nl
        41·
        7 个月前

        Yep! The hitchhikers books are so much fun lol

        I still think one of my favorite lines is “the ships hung in the sky in much the same way that bricks don’t.”

        • FiniteBanjo@lemmy.today
          7·
          7 个月前

          What you’ve described would be like looking at a chart of various fluid boiling points at atmospheric pressure and being like “Wow, water boils at 100 C!” It would only be interesting if that somehow weren’t the case.

          • jarfil@beehaw.org
            5·
            7 个月前

            Where is the “Wow!” in this post? It states a fact, like “Water boils at 100C under 1 atm”, and shows that the student (ChatGPT) has correctly reproduced the experiment.

            Why do you think schools keep teaching that “Water boils at 100C under 1 atm”? If it’s so obvious, should they stop putting it on the test and failing those who say it boils at “69C, giggity”?

            • FiniteBanjo@lemmy.today
              4·
              7 个月前

              Derek feeling the need to comment that the bias in the training data correlates with the bias of the corrected output of a commercial product just seemed really bizarre to me. Maybe it’s got the same appeal as a zoo or something, I never really got into watching animals be animals in a zoo.

              • jarfil@beehaw.org
                3·
                7 个月前

                Hm? Watching animals be animals at a zoo, is a way better sampling of how animals are animals, than for example watching that wildlife “documentary” where they’d throw lemmings of a cliff “for dramatic effect” (a “commercially corrected bias”?).

                In this case, the “corrected output” is just 42, not 37, but as the temperature increases on the Y axis, we get a glimpse of internal biases, which actually let through other patterns of the training data, like the 37.

      • EatATaco@lemm.eeEnglish
        6·
        7 个月前

        “we don’t need to prove the 2020 election was stolen, it’s implied because trump had bigger crowds at his rallies!” -90% of trump supporters

        Another good example is the Monty Hall “paradox” where 99% of people are going to incorrectly tell you the chance is 50% because they took math and that’s how it works.

        Just because something seems obvious to you doesn’t mean it is correct. Always a good idea to test your hypothesis.

        • FiniteBanjo@lemmy.today
          1·
          7 个月前

          Trump Rallies would be a really stupid sample data set for American voters. A crowd of 10,000 people means fuck all compared to 158,429,631. If OpenAI has been training their models on such a small pool then I’d call them absolute morons.

          • EatATaco@lemm.eeEnglish
            2·
            7 个月前

            A crowd of 10,000 people means fuck all compared to 158,429,631.

            I agree that it would be a bad data set, but not because it is too small. That size would actually give you a pretty good result if it was sufficiently random. Which is, of course, the problem.

            But you’re missing the point: just because something is obvious to you does not mean it’s actually true. The model could be trained in a way to not be biased by our number choice, but to actually be pseudo-random. Is it surprising that it would turn out this way? No. But to think your assumption doesn’t need to be proven, in such a case, is almost equivalent to thinking a Trump rally is a good data sample for determining the opinion of the general public.

    • gerryflap@feddit.nl
      40·
      7 个月前

      I’m not a hundred percent sure, but afaik it has to do with how random the output of the GPT model will be. At 0 it will always pick the most probable next continuation of a piece of text according to its own prediction. The higher the temperature, the more chance there is for less probable outputs to get picked. So it’s most likely to pick 42, but as the temperature increases you see the chance of (according to the model) less likely numbers increase.

      This is how temperature works in the softmax function, which is often used in deep learning.

  • HarkMahlberg@kbin.social
    30·
    7 个月前

    I mean… they didn’t specify it had to be random (or even uniform)? But yeah, it’s a good showcase of how GPT acquired the same biases as people, from people…

    • OsrsNeedsF2P@lemmy.ml
      22·
      7 个月前

      uniform

      Reminds me of my previous job where our LLM was grading things too high. The AI “engineer” adjusted the prompt to tell the LLM that the average output should be 3. I had a hard time explaining that wouldn’t do anything at all, because all the chats were independent events.

      Anyways, I quit that place and the project completely derailed.

  • FIash Mob #5678@beehaw.org
    22·
    7 个月前

    HA, funny that this comes up. DND Beyond doesn’t have a d100, so I opened my ChatGPT sub and had it roll a d100 for me a few times so I could use my magic beans properly.

    • TauriWarrior@aussie.zone
      11·
      7 个月前

      Opened up DND Beyond to check since i remember rolling it before and its there, its between D8 and D10, the picture shows 2 dice

        • Urist@lemmy.mlEnglish
          2·
          7 个月前

          Yup! Also one has to mind the order in which one rolls the dice. Since 10 and 5 could be either 05 or 50. As a bonus, if you roll them in order of “tens” to “ones”, getting 10 on the first dice has added suspense since the latter dice determines if it is going to count as a low roll of 0X (by rolling 1-9 on the next dice X) or if it is going to be a max roll of 100 (by rolling another 10).

    • The Cuuuuube@beehaw.orgEnglish
      7·
      7 个月前

      But why use Chatgpt for that? Why not a duck duck go action? I just don’t understand why we’re asking a LLM whose goal is consistency, not randomness, to do random

  • ancap shark@lemmy.today
    21·
    7 个月前

    LMs aren’t thinking, aren’t inventing, they are predicting what is supposed to be answered next, so it’s expected that they will produce the same results every time

    • xthexder@l.sw0.com
      12·
      7 个月前

      This graph actually shows a little more about what’s happening with the randomness or “temperature” of the LLM.
      It’s actually predicting the probability of every word (token) it knows of coming next, all at once.
      The temperature then says how random it should be when picking from that list of probable next words. A temperature of 0 means it always picks the most likely next word, which in this case ends up being 42.
      As the temperature increases, it gets more random (but you can see it still isn’t a perfect random distribution with a higher temperature value)

    • eluvatar@programming.dev
      4·
      7 个月前

      Except it clearly doesn’t produce the same result every time. You’re not making a good case for whatever you’re trying to say.

      • Cethin@lemmy.zipEnglish
        5·
        7 个月前

        They add some fuzziness to it so it doesn’t give the exact same result. Say one gets a score of 90, another 85, and other 80. The 90 will be picked more often, but they sometimes let it pick the 85, or even the 80. It’s perfectly expected, and you can see that result here with 42 being very common, but then a few others being fairly common, and most being extremely uncommon.

  • DarkFox@pawb.social
    17·
    7 个月前

    Which model?

    When I tried on ChatGPT 4, it wrote a short python script and executed it to get a random integer.

    import random

# Pick a random number between 1 and 100
random_number = random.randint(1, 100)
random_number
      • Amju Wolf@pawb.socialEnglish
        10·
        7 个月前

        It generates code and then you can use a call to some runtime execution API to run that code, completely separate from the neural network.

    • Umbrias@beehaw.org
      2·
      7 个月前

      That’s not answering the question though.

      “Pick a number between 1 and 100” doesn’t mean “grab two d10” or write a script.

  • xyguy@startrek.websiteEnglish
    10·
    7 个月前

    Only 1000 times? It’s interesting that there’s such a bias there but it’s a computer. Ask it 100,000 times and make sure it’s not a fluke.

  • Wirlocke@lemmy.blahaj.zone
    8·
    7 个月前

    I’m curious, is there actually so many 42’s in the system? (more than 69 sounds unlikely)

    What if the LLM is getting tripped up because 42 is always referred to as the answer to “the Ultimate Question of Life, the Universe, and Everything”.

    So you ask it a question like give a number between 1-100, it answers 42 because that’s the answer to “Everything”, according to it’s training data.

    Something similar happened to Gemini. Google discouraged Gemini from giving unsafe advice because it’s unethical. Then Gemini refused to answer questions about C++ because it’s considered “unsafe” (referring to memory management). But Gemini thinks C++ is “unsafe” (the normal meaning), therefore it’s unethical. It’s like those jailbreak tricks but from its own training set.

    • Corgana@startrek.website
      8·
      7 个月前

      I’m curious, is there actually so many 42’s in the system?

      Sort of, it’s not actually picking a random number. It does not know what “random” means. It is analyzing the number of times the question “pick a random number” was asked and what the most common responses to that question looked like.

    • exanime@lemmy.today
      2·
      7 个月前

      I’m curious, is there actually so many 42’s in the system? (more than 69 sounds unlikely)

      From hitchhiker’s guide to the galaxy?