News for hackers. Stuff that matters.

A comment on Refusal in Language Models Is Mediated by a Single Direction. Parent comment

Re:Refusal in Language Models Is Mediated by a Single Direction by SoKamil on Saturday May 02, 2026 @12:20PM (#47987723)
No wonder this data is in LibGen.
[ Parent | on HN ]

There are no comments on this comment yet.