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
    3·
    2 years 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.

    • MxM111@kbin.social
      1·
      2 years 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.

  • Glide@lemmy.ca
    0·
    2 years 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
      0·
      2 years ago

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

      • yum13241@lemm.ee
        1·
        2 years ago

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