News for hackers. Stuff that matters.

A comment on GPT-6 Astra covertly underperforms on safety research. Parent comment

Re:GPT-6 Astra covertly underperforms on safety research by siva7 on Thursday November 05, 2026 @06:34PM (#50386124)
I'm doubling on the second to the point where i believe they do reinforcement learning on the public models to sabotage such tasks
[ Parent | on HN ]

There are no comments on this comment yet.