News for hackers. Stuff that matters.

A comment on Researchers Discover New Vulnerability in Large Language Models. Parent comment

Re:Researchers Discover New Vulnerability in Large Language ... by kmeisthax on Saturday July 29, 2023 @05:33PM (#36924886)
This sounds like reward modeling combined with RLHF.
[ Parent | on HN ]

There are no comments on this comment yet.