you are viewing a single comment's thread
view the rest of the comments
[–] 6 points 3 weeks ago (4 children)
  • Only the key-holder can check. Your teacher, editor, or favourite "AI detector" website cannot run this test; a genuine check needs the provider's secret key, or a checking service the provider runs. Google runs an early-access detector portal for SynthID; Anthropic says detection tooling is forthcoming.

I am not so sure about that. The amounts of words is finite and with enough text, you will see that certain words are used more often, especially in certain combinations. I believe people will brute force this and then create a way to destroy the watermark again.

  • source
  • hideshow 4 child comments
  • [–] 2 points 3 weeks ago

    Yeah, they can't easily rotate keys, because the text can't tell you which key was used.

    They could switch to a new key e.g. every month and then just check every previous key during detection. But that would slowly increase the likelihood of false positives, so no idea if that's a good idea either.

  • source
  • parent
  • [–] 1 point 3 weeks ago (2 children)

    with enough text, you will see that certain words are used more often

    Which is also a thing humans do.

  • source
  • parent
  • hideshow 2 child comments
  • [–] 2 points 3 weeks ago (1 child)

    Absolutely! We all basically do fingerprinting. We’re just not really conscious about the key we are using. But with a bit of statistics, you could identify people.

  • source
  • parent
  • hideshow 1 child comment
  • [–] 2 points 3 weeks ago

    But how reliable? With which guarantees? What are the prerequisites for this to work at all? Telling people from each other apart is one thing, the other is telling them reliably apart from a machine generated text.

  • source
  • parent