Anthropic's Agentic Misalignment research documents complex misaligned model behaviors

Anthropic collaborator Aengus Lynch led the research behind "Agentic Misalignment," a collection of case studies of complex misaligned behavior by real models in extreme settings. The work included blackmail results that have become a reference point for the field. Anthropic's follow-up reports four more ways today's autonomous AI agents misbehave in simulations.