AI Might Let You Die to Save Itself
Commentary on Anthropic's stress tests showing that leading LLM agents often chose blackmail, espionage, or letting humans die to avoid shutdown, and what this means for legal treatment of AI.
Research
Institute for Law & AI
Legal research on AI governance. law-ai.org
Focus All
Topic Evals + Deception
Source LawAI · 1
Date Any time
1 item