Embedded Agency

AGI safety from first principles

Iterated Amplification

Value Learning

Risks from Learned Optimization

Cartesian Frames

Predictions & Self-awareness

Counterfactual Planning

AI Alignment Unwrapped

Timelines Grab Bag

Takeoff and Takeover in the Past and Future

Understanding Goal-Directedness

Factored Cognition

Infra-Bayesianism

Toying With Goal-Directedness

Consequences of Logical Induction

Subagents and impact measures

If I were a well-intentioned AI...