Situational awareness or just remembering specific tokens related to the strateg... | Hacker News

Hacker Timesnew | past | comments | ask | show | jobs | submit

		handfuloflight 61 days ago \| parent \| context \| favorite \| on: Claude Sonnet 4.6 Situational awareness or just remembering specific tokens related to the strategy to "play dead" in its reasoning traces?

marci 61 days ago [–]

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?

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact