11
New ChatGPT Models Seem to Leave Watermarks on Text (www.rumidocs.com)
submitted 1 year ago by to c/technik@feddit.org
6 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[–] 6 points 1 year ago (3 children)

I wouldn't really call these watermarks. If these are watermarks, then someone might call the longer than usual dash a watermark, too:

That long dash is called an em dash — like this one.

  • permalink
  • fedilink
  • source
  • hideshow 3 child comments
    •
  • [–] 2 points 1 year ago

    Using identically displayed but differently encoded characters is a way to watermark texts. It was used in a lawsuit a few years ago (SZ-Bericht). The suing company eventually lost because they didn't actually own the rights to the texts they had watermarked.

    As @luckystarr@feddit.org points out, these whitespaces may make quite a difference, so not likely to be a watermark. Methods for watermarking LLM-generated Text are more subtle anyway, involving altering word frequencies.

  • permalink
  • fedilink
  • source
  • parent