Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Researchers Tested AI Watermarks–and Broke All of Them. Parent comment
It’s a direct (and open source) implementation of public key cryptography into the LLM logit distribution.
The paraphrasing model/beam search needs work - feel free to pitch in :)
There are no comments on this comment yet.
It’s a direct (and open source) implementation of public key cryptography into the LLM logit distribution.
The paraphrasing model/beam search needs work - feel free to pitch in :)