#sleeper_agents — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #sleeper_agents, aggregated by home.social.
-
Sleeper AI agents and how Anthropic detects them [video]
https://www.youtube.com/watch?v=Z3WMt_ncgUI
#ycombinator #Anthropic #AI_Safety #Alignment #Sleeper_Agents #AI_alignment