Guess which of these LLM outputs is watermarked

If SynthID is a google technology, then this is likely just us training their ai again, captcha all over again.

Could do with some context on how watermarking works. Objectively speaking it should be impossible to tell.

Interesting, I did very badly, 3/10!

Utterly imperceptible, even when studied under the microscope in a way that LLM text very rarely is in practice.

It will be interesting to see whose concerns are assuaged (perhaps they genuinely though mistakenly believed it would degrade quality), and whose concerns are heightened (perhaps their real objection is that their AI-generated text will become detectable).