RSS

myyycroft

Karma: 20

Evolu­tion of my AI Safety threat models

myyycroft17 Jul 2026 14:54 UTC
9 points
0 comments3 min readLW link

In­ter­pret­ing Gra­di­ent Rout­ing’s Scal­able Over­sight Experiment

makataomu and myyycroft
5 Apr 2026 2:08 UTC
13 points
0 comments9 min readLW link

Cri­tique of ma­chine unlearning

myyycroft25 Jan 2026 10:50 UTC
2 points
0 comments5 min readLW link