This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
AF
Login
Nicholas Schiefer
Posts
Sorted by New
115
Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
4mo
69
119
Model Organisms of Misalignment: The Case for a New Pillar of Alignment Research
8mo
13
37
Engineering Monosemanticity in Toy Models
1y
4
6
ELK Proposal - Make the Reporter care about the Predictor’s beliefs
2y
0
Wiki Contributions
Comments