Am I missing something? The article seems to suggest it works via hidden text characters. Has OpenAI never heard of pasting text into a utf8 notepad before?

  • @Womble@lemmy.world
    link
    fedilink
    English
    71 month ago

    It can likely also be defeated by adding “In the style of X” to a prompt, changing the distribution and pattern of the responses.

    • JackbyDev
      link
      fedilink
      English
      21 month ago

      …but that output is also from the AI so it would still be watermarked lol