Decision Theory for AI Safety
Prior reading: Game Theory for AI Safety Why Decision Theory Matters Every AI system that takes actions is implicitly using a decision theory — a framework for choosing among options given beliefs and preferences. The choice of decision theory determines: Whether the AI cooperates or defects in strategic situations Whether it's manipulable or manipulation-resistant Whether it takes catastrophic gambles or plays it safe How it reasons about its own future behavior Decision theory isn't just philosophy. It's the operating system of agency. ...