alt Hacker NewsAnthropic’s watermark is just using a known collection of random seeds during output token generation. That’s it. The models always relied on some randomness, here the randomness is fixed and remembered for querying later.
Anthropic’s watermark is just using a known collection of random seeds during output token generation. That’s it. The models always relied on some randomness, here the randomness is fixed and remembered for querying later.
> Anthropic’s watermark is just using a known collection of random seeds during output token generation. That’s it.
Wouldn't that mean that checking the watermark...
(1) Required knowing the prompt used to generate the text; and
(2) was just as expensive as generating the text?