• Blackmist@feddit.ukEnglish
    0·
    6 个月前

    I spent an afternoon once playing Infinite Craft, which uses some sort of LLM behind the scenes to do it’s combinations.

    At one point I got 007, and found 007+007 = 0014.

    The maths gets wild though, and because it’s been trained on text, it has no idea when it comes to combinations of numbers it hasn’t seen before. I spent ages trying to get it to 69420 and just couldn’t, although I could get 42069.

  • Phroon@beehaw.orgEnglish
    0·
    6 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
        0·
        6 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.”

  • DarkFox@pawb.social
    0·
    6 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
    • Umbrias@beehaw.org
      0·
      6 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.

      • Amju Wolf@pawb.socialEnglish
        0·
        6 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.

  • kbal@fedia.io
    0·
    6 个月前

    Obviously the bots do not share in our human fondness for the number 69.

      • Empricorn@feddit.nlEnglish
        0·
        6 个月前

        Yes, but it’s significant because the prompt was to choose a number. I realize computers can’t really be random, but if we needed to just select a popular number…we can already do that!

      • EatATaco@lemm.eeEnglish
        0·
        6 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
          0·
          6 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
            0·
            6 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.

        • FiniteBanjo@lemmy.today
          0·
          6 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
            0·
            6 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
              0·
              6 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
                0·
                6 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.

    • gerryflap@feddit.nl
      0·
      6 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.

  • phorq@lemmy.mlEspañol
    0·
    6 个月前

    I petition to rename ChatGPT to DeepThought based on these results.

  • HarkMahlberg@kbin.social
    0·
    6 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
      0·
      6 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.