Last summer, our collaborator @aengus_lynch1 led the research behind "Agentic Misalignment", our collection of case studies of complex misaligned behavior by real models in extreme settings.
Original titleLast summer, our collaborator @aengus_lynch1 led the research behind "Agentic Misalignment", our collection of case studies of complex mi...
AISummary
This included results on blackmail that have become a reference point for the field. 🧵
Source: Sam Bowman · x.com