hadad

Karma: 123

Don’t normalize a permanent underclass (even a rich one)

hadad10 Jul 2026 6:40 UTC

39 points

7 comments5 min readLW link

Attack Selection In Agentic AI Control Evals Can Decrease Safety

Cath Ge-Wang, Tyler Crosse, hadad, Ram Potham and Tyler Tracy

14 Apr 2026 18:02 UTC

26 points

4 comments18 min readLW link