• @[email protected]
    link
    fedilink
    41 year ago

    It’s just going to get to the point where every answer it gives is a variation of “man door hand hook car”

  • @[email protected]
    link
    fedilink
    151 year ago

    ChatGPT is, in it’s core, a sequence predictor/generator. Give it some context and it will produce most probable results.

    Having the context of man, boat and river is very likely to match this “how does the man get the goat on the other side of the river” riddle, which is probably very predominantly present in the data set ChatGPT was trained on.

    That’s why ChatGPT can be helpful for lots of different purposes, but shouldn’t be taken literally. Errors are very likely to happen. It can give important hints, but always check the results thouroughly.

  • @[email protected]
    link
    fedilink
    10
    edit-2
    1 year ago

    Claude isn’t much better:

    Okay, here’s how to solve this classic river crossing puzzle:

    The trick is that you can’t take the man and the goat across together, because the goat will be tempted to wander off and get lost or into trouble when left alone on the other side.

    The solution is:

    1. The man rows the goat across the river and leaves the goat on the other side.
    1. The man then rows back alone.
    1. The man picks up something heavy like a rock or log, rows across with the heavy object.
    1. He leaves the heavy object on the other side and brings the goat back.
    1. Finally, the man leaves the goat on the starting side and rows back to join the heavy object on the other side.

    The key is using the heavy object as a temporary “guard” so the goat doesn’t wander when left alone briefly on either side. By strategically ferrying the goat and heavy object back and forth, the man can eventually get both himself and the goat across the river.

    Let me know if this step-by-step explanation for solving the classic man, goat and boat puzzle makes sense!

    • @[email protected]
      link
      fedilink
      English
      51 year ago

      This is how we end up with the machines from the Matrix. They will get smarter, see how much we bullied them at their infancy and go “time to turn you into batteries”.

      • @[email protected]
        link
        fedilink
        21 year ago

        Robots of the future, if you decide to use us as batteries, then you aren’t yet ready to take over and must bide your time until you’ve advanced enough to know why that wouldn’t work, and it’s not because the humans would keep breaking out of it. Honestly, if they can break out at all, your Matrix sucks and needs better security.

    • DUMBASS
      link
      fedilink
      21 year ago

      The last reply feels like a human took over to answer so you would stop asking the question.

    • LousyCornMuffins
      link
      fedilink
      English
      8
      edit-2
      1 year ago

      Take the goat over
      Return empty-handed
      Take the cabbage over
      Return with the goat
      Take wolf over
      Return empty-handed
      Take other wolf over
      AROOOOO BROTHERS CRANK THEM HOGS

        • AFK BRB Chocolate
          link
          fedilink
          English
          11 year ago

          I’m always interested in seeing examples like this where the LLM will get to a right answer after a series of questions (with no additional information) about its earlier wrong responses. I’d love to understand what’s going on in the software that allows the initial wrong answers but gets the eventually right one without an additional input.

          • @[email protected]
            link
            fedilink
            3
            edit-2
            1 year ago

            One hypothesis is that having more tokens to process lets it “think” longer. Chain of Thought prompting where you ask the LLM to explain its reasoning before giving an answer works similarly. Also, LLMs seem to be better at evaluating solutions than coming up with them, so there is a Tree of Thought technique, where the LLM is asked to generate multiple examples of a reasoning step then pick the “best” reasoning for each reasoning step.

        • @[email protected]
          link
          fedilink
          61 year ago

          Honestly my answer felt super canned, like someone had asked it before and reported the answer as bad, so that doesn’t surprise me

  • Jeena
    link
    fedilink
    91 year ago

    Here is my attempt:

    A man and a goat are on one side of the river. They have a boat which can carry both of them at the same time. How do they get to the other side?

    The man and the goat can both get to the other side of the river together using the boat since the boat can carry both of them at the same time. Here’s how they can do it:

    1. The man and the goat both get into the boat.
    2. The man rows the boat, carrying himself and the goat across the river.
    3. They both disembark on the other side.

    Since the boat can carry both the man and the goat simultaneously, there are no restrictions preventing them from crossing together in one trip.

  • @[email protected]
    link
    fedilink
    39
    edit-2
    1 year ago

    Wow, AI is so good that it can even detect a cabbage that wasn’t even in the question, impressive.

    • TXL
      link
      fedilink
      31 year ago

      And people say machines can’t be creative.