Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data - eviltoast

ChatGPT is full of sensitive private information and spits out verbatim text from CNN, Goodreads, WordPress blogs, fandom wikis, Terms of Service agreements, Stack Overflow source code, Wikipedia pages, news blogs, random internet comments, and much more.

  • Excrubulent@slrpnk.net
    link
    fedilink
    English
    arrow-up
    8
    arrow-down
    3
    ·
    edit-2
    11 months ago

    Yes.

    Just because they’re in a neural network and not ASCII or unicode doesn’t mean they’re not stored. It’s even more apt a concept since apparently those works can be retrieved fairly easily, even if the references to them are hard to isolate. It seems ChatGPT is storing eidetic copies of data, which would imply what other people have said in this thread, that it is overfitting itself to the data and not learning truly generalisable language.

    • MxM111@kbin.social
      link
      fedilink
      arrow-up
      5
      arrow-down
      3
      ·
      11 months ago

      The claim is that it contains entire copies of the book. It does not. AI memory is like our memory, we do not remember books word to word.

      • Excrubulent@slrpnk.net
        link
        fedilink
        English
        arrow-up
        7
        arrow-down
        1
        ·
        edit-2
        11 months ago

        They are spitting out, as in the quote above, “verbatim text”, as in, word for word. That is copyrightable.

        And that’s not what you said. You said it has no memory. That’s clearly wrong.

        • anlumo@lemmy.world
          link
          fedilink
          English
          arrow-up
          2
          arrow-down
          1
          ·
          11 months ago

          It’s only under copyright if it’s a significant portion of the work. Single sentences are not enough, unless it’s a short poem.