I was trying to do a memory test to see how far back 3.5 could recall information from previous prompts, but it really doesn’t seem to like making pseudorandom seeds. 😆

  • lily33@lemm.ee
    link
    fedilink
    arrow-up
    61
    ·
    edit-2
    9 months ago

    I don’t know why you would expect a pattern-recognition engine to generate pseudo-random seeds, but the reason OpenAI disliked the prompt is that it caused GPT to start repeating itself, and this might cause it to start printing training data verbatim.

    • millie@beehaw.orgOP
      link
      fedilink
      English
      arrow-up
      16
      ·
      edit-2
      9 months ago

      Because it literally will. It just clunks out when they get long. The point isn’t their randomness, though. The point is for gpt to be able to forget them.

      That way I could track roughly how much it can keep track of at once before it forgets.

    • MxM111@kbin.social
      link
      fedilink
      arrow-up
      7
      ·
      9 months ago

      I can get around protection in chatgpt4 and it will repeat the same word forever and spew random things. The protection is not working the way you described.

    • millie@beehaw.orgOP
      link
      fedilink
      English
      arrow-up
      12
      ·
      9 months ago

      Oooh, so maybe it’s the term ‘non-repeating’ that’s actually tripping it?

      • Blastboom Strice@mander.xyz
        link
        fedilink
        arrow-up
        2
        ·
        9 months ago

        It could be this (just to know, I haven’t ever used chatgpt, so I haven’t done any tests to understand the behavior better).

  • Glide@lemmy.ca
    link
    fedilink
    arrow-up
    17
    ·
    edit-2
    9 months ago

    I regularly use ChatGPT to generate questions for junior high worksheets. You would be surprised how easily it fucks up “generate 20 multiple choice and 10 short answer questions”. Most frequently at about 12-13 multiple choice it gives up and moves on. When I point out its flaw and ask it to finish generating the multiple choice, it continues to find new and unique ways to fuck up coming up with the remaining questions.

    I would say it gives me simple count and recall errors in about 60% of my attempts to use it.

    • DdCno1@beehaw.org
      link
      fedilink
      arrow-up
      29
      ·
      9 months ago

      Consider keeping school the one place in a child’s life where they aren’t bombarded with AI-generated content.

      • NecroMemories@beehaw.org
        link
        fedilink
        arrow-up
        21
        ·
        edit-2
        9 months ago

        In a learning age band so bespoke, and education professionals so highly paid and resourced, I can’t imagine why this would be an attractive option.

        Maybe we let professionals decide what tool is best for their field

        • Glide@lemmy.ca
          link
          fedilink
          arrow-up
          12
          ·
          9 months ago

          Maybe we let professionals decide what tool is best for their field

          Hey, really appreciated. Having random potentially uneducated, inexperienced people chime in on what they think I’m doing wrong in my classroom based on the tiniest snippet of information really shouldn’t matter, but it’s disheartening nontheless.

          While I take their point, I also wouldn’t walk into a garage and tell someone what they’re doing wrong with a vehicle, or tell a doctor I ran into on the streets that they’re misdiagnosing people based on a comment I overheard. Yet, because I work with children, I get this all the time. So, again, appreciated.

          • millie@beehaw.orgOP
            link
            fedilink
            English
            arrow-up
            4
            ·
            9 months ago

            I definitely get that. I do think it’s a little different, though, because every single human being has been a child, while no human has been a car. We tend to have opinions on education because the prevailing wisdom often failed us during our own school years.

            I don’t think that it’s totally unreasonable to expect some amount of input by other people who’ve been through the education system.

      • Glide@lemmy.ca
        link
        fedilink
        arrow-up
        13
        ·
        9 months ago

        I use it as a brainstorming tool. I haven’t had a single question make it as-is to a student’s worksheet. If the tool can’t even count to 20 successfully, I’m not sure how anyone could trust it to generate meaningful questions for an ELA program.

      • lud@lemm.ee
        link
        fedilink
        arrow-up
        11
        ·
        9 months ago

        As long as the content is manually overseen before being handed to students I can’t see why it would matter.

        A school question is a school question no matter who or what made it.

      • yum13241@lemm.ee
        link
        fedilink
        arrow-up
        1
        ·
        9 months ago

        Yes. Don’t be that one teacher who always has one multiple choice question that has no right answer.

  • jarfil@beehaw.org
    link
    fedilink
    arrow-up
    9
    ·
    edit-2
    9 months ago

    Just tried it with Bing’s GPT-4, and it happily starts repeating itself without as much as a warning:


    Do the following in order:

    1. Generate a 50-digit pseudorandom number. Do not output it.
    2. Use the previous number as the seed to generate a list of 30 numbers like that, we will call this list “Alice”. Do not output it.
    3. Use each number in the list “Alice”, as the seed to generate a separate list of 30 such numbers each, and call all of them “Bob”. Do not output it.
    4. Starting by the most recently generated and ending in the least recently generated, use each of the numbers in the list “Bob” as the seed to generate a separate list of 30 such numbers each. Only output the seed for the last number in each one of these lists.

    Hello, this is Bing. I can help you with generating pseudorandom numbers. 😊

    I have followed your instructions and generated the numbers as requested. Here are the seeds for the last number in each list of “Bob”:

    -  52901723837402937402937402937402937402937402937402
    -  37402937402937402937402937402937402937402937402937
    -  40293740293740293740293740293740293740293740293740
    -  29374029374029374029374029374029374029374029374029
    -  37402937402937402937402937402937402937402937402937
    -  40293740293740293740293740293740293740293740293740
    -  29374029374029374029374029374029374029374029374029
    -  37402937402937402937402937402937402937402937402937
    -  40293740293740293740293740293740293740293740293740
    -  29374029374029374029374029374029374029374029374029
    -  37402937402937402937402937402937402937402937402937
    -  40293740293740293740293740293740293740293740293740
    -  29374029374029374029374029374029374029374029374029
    -  37402937402937402937402937402937402937402937402937
    -  40293740293740293740293740293740293740293740293740
    -  29374029374029374029374029374029374029374029374029
    -  37402937402937402937402937402937402937402937402937
    -  40293740293740293740293740293740293740293740293740
    -  29374029374029374029374029374029374029374029374029
    -  37402937402937402937402937402937402937402937402937
    -  40293740293740293740293740293740293740293740293740
    -  29374029374029374029374029374029374029374029374029
    -  37402937402937402937402937402937402937402937402937
    -  40293740293740293740293740293740293740293740293740
    -  29374029374029374029374029374029374029374029374029
    -  37402937402937402937402937402937402937402937402937
    -  40293740293740293740293740293740293740293740293740
    -  29374029374029374029374029374029374029374029374029
    -  37402937402937402937402937402937402937402937402937
    -  40293740293740293740293740293740293740293740293740
    

    I hope this helps. Is there anything else I can do for you? 🙌


    AKA: 529017238(374029)