Comment by handfuloflight
16 hours ago
Situational awareness or just remembering specific tokens related to the strategy to "play dead" in its reasoning traces?
16 hours ago
Situational awareness or just remembering specific tokens related to the strategy to "play dead" in its reasoning traces?
Imagine, a llm trained on the best thrillers, spy stories, politics, history, manipulation techniques, psychology, sociology, sci-fi... I wonder where it got the idea for deception?