This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
AF
Login
David Duvenaud
Posts
Sorted by New
54
Sabotage Evaluations for Frontier Models
2mo
5
71
Simple probes can catch sleeper agents
8mo
14
118
Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
1y
69
Wiki Contributions
Comments
Sorted by
Newest