Thread

1. WithinReason · 1790430559 · focus · HN ↗

   This is getting tiring. Watermarking has no effect on model output quality when implemented correctly. It's somewhat like swapping a random RNG seed to the seed 42, and detecting what the seed was from a random sequence. The sequence generated from the seed 42 is just as random as any other seed. There couldn't be a quality difference. And yes, the output from an LLM is a conditional random sequence of tokens from a distribution determined by a model.

   1. 4d4m · 1790460803 · focus · HN ↗

      Watermarks or spymarking are anti-consumer/customer and can be used to trigger refusals invisibly to the user.

Unofficial Hacker News client; not affiliated with Y Combinator.