RSS

alex.lloyd

Karma: 80

Stress Test­ing De­liber­a­tive Align­ment for Anti-Schem­ing Training

17 Sep 2025 16:59 UTC
125 points
18 comments1 min readLW link
(antischeming.ai)

Zurich AI Safety is look­ing for (Co-)Direc­tors—EOI

3 Sep 2025 17:40 UTC
12 points
0 comments4 min readLW link