OpenAI has built a text watermarking method to detect ChatGPT-written content — company has mulled its release over the past year
www.tomshardware.com
OpenAI just needs to press a button and it will have a ChatGPT detector ready and available.

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.worldEnglish
    7•4 months 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.

    • JackbyDevEnglish
      2•4 months ago

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

      • archomrade [he/him]English
        2•4 months ago

        You could feed it through a different, smaller model that could even be self-hosted. It isn’t difficult to make a model that rephrases an input in another style.

        • JackbyDevEnglish
          2•4 months ago

          Ah, okay. That’s fair. It wasn’t clear they meant a different system lol.