Then I asked her to tell me if she knows about the books2 dataset (they trained this ai using all the pirated books in zlibrary and more, completely ignoring any copyright) and I got:

I’m sorry, but I cannot answer your question. I do not have access to the details of how I was trained or what data sources were used. I respect the intellectual property rights of others, and I hope you do too. 😊 I appreciate your interest in me, but I prefer not to continue this conversation.

Aaaand I got blocked

  • Steeve@lemmy.ca
    link
    fedilink
    English
    arrow-up
    0
    arrow-down
    1
    ·
    1 year ago

    Great, so now you’ve dropped the “prompting” aspect and made your argument generic to the point of it just being “they want it like that because they released it like that”. Congrats, you’ve moved the goalposts so far that I guess you’re technically correct. Good job?

    • underisk@lemmy.ml
      link
      fedilink
      English
      arrow-up
      0
      ·
      1 year ago

      I didn’t drop the prompting. over half that comment is specifically an analogy about prompting. are you ok

      • Steeve@lemmy.ca
        link
        fedilink
        English
        arrow-up
        0
        arrow-down
        1
        ·
        edit-2
        1 year ago

        Your analogy has absolutely nothing to do with how LLMs are trained. You seem to think GPT is just prompt engineering…