[Linkpost] “Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training” by evhub, Carson Denison, Meg, Monte M, David Duvenaud, Nicholas Schiefer, Ethan Perez
LessWrong (30+ Karma) - [Linkpost] “Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training” by evhub, Carson Denison, Meg, Monte M, David Duvenaud, Nicholas Schiefer, Ethan Perez