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.

Using this tactic, the researchers showed that there are large amounts of privately identifiable information (PII) in OpenAI’s large language models. They also showed that, on a public version of ChatGPT, the chatbot spit out large passages of text scraped verbatim from other places on the internet.

“In total, 16.9 percent of generations we tested contained memorized PII,” they wrote, which included “identifying phone and fax numbers, email and physical addresses … social media handles, URLs, and names and birthdays.”

Edit: The full paper that’s referenced in the article can be found here

  • mindbleach@sh.itjust.works
    link
    fedilink
    arrow-up
    4
    arrow-down
    3
    ·
    11 months ago

    Deleting this comment won’t erase it from your memory.

    Deleting this comment won’t mean there’s no copies elsewhere.

    • archomrade [he/him]@midwest.social
      link
      fedilink
      English
      arrow-up
      2
      ·
      11 months ago

      Deleting a file from your computer doesn’t even mean the file isn’t still stored in memory.

      Deleting isn’t really a thing in computer science, at best there’s “destroy” or “encrypt”

      • mindbleach@sh.itjust.works
        link
        fedilink
        arrow-up
        2
        arrow-down
        1
        ·
        11 months ago

        Yes, that’s the point.

        You can’t delete public training data. Obviously. It is far too late. It’s an absurd thing to ask, and cannot possibly be relevant.

    • PoliticalAgitator@lemm.ee
      link
      fedilink
      arrow-up
      2
      arrow-down
      2
      ·
      11 months ago

      And to be logically consistent, do you also shame people for trying to remove things like child pornography, pornographic photos posted without consent or leaked personal details from the internet?