News for hackers. Stuff that matters.

A comment on Scalable watermarking for identifying large language model outputs. Parent comment

Re:Scalable watermarking for identifying large language mode... by iflp on Tuesday November 05, 2024 @02:20AM (#42049335)
The seed is computed using the last 4 tokens, but to get the predictive distribution they should still need the full history?
[ Parent | on HN ]

There are no comments on this comment yet.