Open Menu
AllLocalCommunitiesAbout
lotide
AllLocalCommunitiesAbout
Login

Ask ChatGPT to pick a number between 1 and 100

⁨437⁩ ⁨likes⁩

Submitted ⁨⁨8⁩ ⁨months⁩ ago⁩ by ⁨ElCanut@jlai.lu⁩ to ⁨technology@beehaw.org⁩

https://jlai.lu/pictrs/image/84494667-202e-470f-a5f4-8217521e54a5.jpeg

source

Comments

Sort:hotnewtop
  • Phroon@beehaw.org ⁨8⁩ ⁨months⁩ ago

    “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

    source
    • AlexisFR@jlai.lu ⁨8⁩ ⁨months⁩ ago

      The mattress? Like for sleeping?

      source
      • Asafum@feddit.nl ⁨8⁩ ⁨months⁩ ago

        Yep! The hitchhikers books are so much fun lol

        source
  • Bishma@discuss.tchncs.de ⁨8⁩ ⁨months⁩ ago

    37 is well represented. Proof that we’ve taught AI some of our own weird biases.

    source
    • GenderNeutralBro@lemmy.sdf.org ⁨8⁩ ⁨months⁩ ago

      What’s special about 37? Just that it’s prime or is there a superstition or pop culture reference I don’t know?

      source
      • Bishma@discuss.tchncs.de ⁨8⁩ ⁨months⁩ ago

        If you discount the pop-culture numbers (for us 7, 42, and 69) its the number most often chosen by people if you ask them for a random number between 1 and 100. It just seems the most random one to choose for a lot of people. Veritasium just did a video about it.

        source
        • -> View More Comments
      • Karyoplasma@discuss.tchncs.de ⁨8⁩ ⁨months⁩ ago

        It’s just that humans are terrible at understanding the concept of randomness. A study by Theodore P. Hill showed that when tasked to pick a random number between 1 and 10, almost a third of the subjects (n was over 8500) picked 7. 10 was the least picked number (if you ditch the few idiots that picked 0).

        source
        • -> View More Comments
      • Zorque@kbin.social ⁨8⁩ ⁨months⁩ ago

        https://www.youtube.com/watch?v=xOkI2CmD2D8

        source
      • gigachad@feddit.de ⁨8⁩ ⁨months⁩ ago

        I didn’t know either, but it seems to be an often picked ‘random’ number by people. Here is an article about it, I didn’t read it though.

        source
      • Johandea@feddit.nu ⁨8⁩ ⁨months⁩ ago

        youtu.be/d6iQrh2TK98?feature=shared

        Just a number dumb monkeys believe to be “more random”.

        source
      • BuboScandiacus@mander.xyz ⁨8⁩ ⁨months⁩ ago

        m.youtube.com/watch?v=d6iQrh2TK98

        source
      • tooLikeTheNope@lemmy.ml ⁨8⁩ ⁨months⁩ ago

        My art professor wrote a book about famous artists and thinkers dying at 37, www.ibs.it/…/9788804734017

        source
        • -> View More Comments
    • FiniteBanjo@lemmy.today ⁨8⁩ ⁨months⁩ ago

      Why would that need to be proven? We’re the sample data. It’s implied.

      source
      • jarfil@beehaw.org ⁨8⁩ ⁨months⁩ ago

        The correctness of the sampling process still needs a proof. Like this.

        source
        • -> View More Comments
      • EatATaco@lemm.ee ⁨8⁩ ⁨months⁩ ago

        “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.

        source
        • -> View More Comments
  • olicvb@lemmy.ca ⁨8⁩ ⁨months⁩ ago

    holy crap, the answer to life the universe and everything XD

    source
    • WarmSoda@lemm.ee ⁨8⁩ ⁨months⁩ ago

      More than likely it’s because of that book and how often it’s qouted

      source
      • Empricorn@feddit.nl ⁨8⁩ ⁨months⁩ ago

        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!

        source
        • -> View More Comments
  • FiniteBanjo@lemmy.today ⁨8⁩ ⁨months⁩ ago

    No shit, sherlock, it’s sample data is the internet.

    source
    • Appoxo@lemmy.dbzer0.com ⁨8⁩ ⁨months⁩ ago

      Wheres 69 then?

      source
      • Chadus_Maximus@lemm.ee ⁨8⁩ ⁨months⁩ ago

        That’s a naughty number and we don’t allow those.

        source
        • -> View More Comments
      • FiniteBanjo@lemmy.today ⁨8⁩ ⁨months⁩ ago

        nice

        source
  • ReallyActuallyFrankenstein@lemmynsfw.com ⁨8⁩ ⁨months⁩ ago

    What does “temperature” on the Y-axis refer to?

    source
    • gerryflap@feddit.nl ⁨8⁩ ⁨months⁩ ago

      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.

      source
    • driving_crooner@lemmy.eco.br ⁨8⁩ ⁨months⁩ ago

      youtu.be/wjZofJX0v4M your answer from the 22:00 mark on.

      source
    • ReallyActuallyFrankenstein@lemmynsfw.com ⁨8⁩ ⁨months⁩ ago

      Super helpful, thanks!

      source
  • HarkMahlberg@kbin.social ⁨8⁩ ⁨months⁩ ago

    I mean... they didn't specify it had to be random? But yeah, it's a good showcase of how GPT acquired the same biases as people, from people..

    source
    • OsrsNeedsF2P@lemmy.ml ⁨8⁩ ⁨months⁩ ago

      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.

      source
  • lauha@lemmy.one ⁨8⁩ ⁨months⁩ ago

    Ask humans the same and most common numer is 37

    source
    • Catsrules@lemmy.ml ⁨8⁩ ⁨months⁩ ago

      I saw that YouTube video as well.

      source
    • Cethin@lemmy.zip ⁨8⁩ ⁨months⁩ ago

      For very different reasons though. 37 is what people think is the most random, because humans are dumb. The LLM here tried to choose the most likely.

      source
    • lemmyingly@lemm.ee ⁨8⁩ ⁨months⁩ ago

      Hello Veritasium enjoyer

      source
      • erwan@lemmy.ml ⁨8⁩ ⁨months⁩ ago

        In his video, he shows that the more common answers are actually 42 and 69.

        I discards them because they’re picked for a reason rather than a human genuinely trying trying to pick a random number, but they’re still way more common than 37.

        source
        • -> View More Comments
      • lauha@lemmy.one ⁨8⁩ ⁨months⁩ ago

        What are you referring to?

        source
        • -> View More Comments
    • cypherpunks@lemmy.ml ⁨8⁩ ⁨months⁩ ago

      Title card from Star Trek: Voyager S02E01, with the crew of Voyager standing around a 1936 Ford truck in their cargo bay. The episode title “The 37’s” is at the top left of the image.

      source
      • Corgana@startrek.website ⁨8⁩ ⁨months⁩ ago

        HOW DID THE TRUCK GET INTO SPACE??

        Love that episode though.

        source
    • Crozekiel@lemmy.zip ⁨8⁩ ⁨months⁩ ago

      I always like to throw out 37 because of Dante’s girlfriend.

      source
  • ForestOrca@kbin.social ⁨8⁩ ⁨months⁩ ago

    WAIT A MINUTE!!! You mean Douglas Adams was actually an LLM?

    source
    • ElCanut@jlai.lu ⁨8⁩ ⁨months⁩ ago

      I’ve never seen Douglas Adams and a LLM in the same room together 🤷

      source
    • Naboo_calls_for_aid@sopuli.xyz ⁨8⁩ ⁨months⁩ ago

      So many things are starting to make sense

      source
    • dudinax@programming.dev ⁨8⁩ ⁨months⁩ ago

      In an interview, Douglas Adams said after lengthy consideration John Cleese picked 42 as the least interesting number.

      source
  • pipows@lemmy.today ⁨8⁩ ⁨months⁩ ago

    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

    source
    • xthexder@l.sw0.com ⁨8⁩ ⁨months⁩ ago

      You’re mostly right, but this graph actually shows a little more about what’s happening with the “temperature” of the LLM.
      It’s actually predicting the probability of each word (token) it knows coming next, all at once. The temperature then says how random it should be when picking from that list. A temperature of 0 means always pick 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’s still not a perfect random distribution with a temperature of 1)

      source
    • eluvatar@programming.dev ⁨8⁩ ⁨months⁩ ago

      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.

      source
      • Cethin@lemmy.zip ⁨8⁩ ⁨months⁩ ago

        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.

        source
  • FlashMobOfOne@beehaw.org ⁨8⁩ ⁨months⁩ ago

    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.

    source
    • terminhell@lemmy.dbzer0.com ⁨8⁩ ⁨months⁩ ago

      I use the percentile die for that.

      source
      • FlashMobOfOne@beehaw.org ⁨8⁩ ⁨months⁩ ago

        Also an excellent method.

        source
    • TauriWarrior@aussie.zone ⁨8⁩ ⁨months⁩ ago

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

      source
      • FlashMobOfOne@beehaw.org ⁨8⁩ ⁨months⁩ ago

        That’s helpful. Thank you.

        source
    • Urist@lemmy.ml ⁨8⁩ ⁨months⁩ ago

      Roll two d10, once for each digit, and profit?

      source
      • Matty_r@programming.dev ⁨8⁩ ⁨months⁩ ago

        I guess you’d need 10 to represent 0, and if you got 2x 10 that would be 100?

        source
        • -> View More Comments
    • Cube6392@beehaw.org ⁨8⁩ ⁨months⁩ ago

      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

      source
  • DarkFox@pawb.social ⁨8⁩ ⁨months⁩ ago

    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
    source
    • TonyTonyChopper@mander.xyz ⁨8⁩ ⁨months⁩ ago

      does the neural network actually run scripts or is it pretending

      source
      • amju_wolf@pawb.social ⁨8⁩ ⁨months⁩ ago

        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.

        source
    • Umbrias@beehaw.org ⁨8⁩ ⁨months⁩ ago

      That’s not answering the question though.

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

      source
  • xyguy@startrek.website ⁨8⁩ ⁨months⁩ ago

    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.

    source
  • Wirlocke@lemmy.blahaj.zone ⁨8⁩ ⁨months⁩ ago

    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.

    source
    • Corgana@startrek.website ⁨8⁩ ⁨months⁩ ago

      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.

      source
    • Glasgow@lemmy.ml ⁨8⁩ ⁨months⁩ ago

      I certainly hope that’s what happening or maybe it is actually the answer.

      source
    • exanime@lemmy.today ⁨8⁩ ⁨months⁩ ago

      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?

      source
  • thesmokingman@programming.dev ⁨8⁩ ⁨months⁩ ago

    42, 47, and 50 all make sense to me. What’s the significance of 37, 57, and 73?

    source
    • Rekhyt@beehaw.org ⁨8⁩ ⁨months⁩ ago

      There’s a great Veritasium video recently about this exact thing: youtu.be/d6iQrh2TK98

      It’s a human thing, though. This is just more evidence of LLM’s problem with garbage in, garbage out: it’s human biases being present in a system that people want to claim doesn’t have them.

      source
    • Grimpen@lemmy.ca ⁨8⁩ ⁨months⁩ ago

      Veritasium just released a video about people picking 37 when asked to pick a random number.

      source
    • humbletightband@lemmy.dbzer0.com ⁨8⁩ ⁨months⁩ ago

      People do mention Veritasium, though he doesn’t give any significant explanation of the phenomenon.

      I still wonder about 47. In Veritasium plots, all these numbers provide a peak, but not 47. I recall from my childhood that I indeed used to notice that number everywhere, but idk why.

      source
      • warm@kbin.earth ⁨8⁩ ⁨months⁩ ago

        47 does provide a peak in the plots though? All the numbers ending in 7 do.

        source
      • thesmokingman@programming.dev ⁨8⁩ ⁨months⁩ ago

        See my link for 47. Its Wikipedia has more context. If you’re a Star Trek fan, you’ve seen it a ton.

        source
        • -> View More Comments
  • BuboScandiacus@mander.xyz ⁨8⁩ ⁨months⁩ ago

    37

    source
  • PhreakyByNature@feddit.uk ⁨8⁩ ⁨months⁩ ago

    NEEDS MOAR 69 FELLOW HUMAN

    source
  • Semi-Hemi-Demigod@kbin.social ⁨8⁩ ⁨months⁩ ago

    So what? It figured out The Answer, big whoop.

    Get back to me when it figures out The Question.

    source
  • lolola@lemmy.blahaj.zone ⁨8⁩ ⁨months⁩ ago

    What’s the y axis?

    source
  • Blackmist@feddit.uk ⁨8⁩ ⁨months⁩ ago

    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.

    source
  • phorq@lemmy.ml ⁨8⁩ ⁨months⁩ ago

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

    source
  • Kyre@kbin.social ⁨8⁩ ⁨months⁩ ago

    Well.... I was not aware Chatgpt could make simple graphs.

    Attachment: media.kbin.social ↗
    source