AGI safety from first principles

Embedded Agency

2022 MIRI Alignment Discussion

2021 MIRI Conversations

Infra-Bayesianism

Conditioning Predictive Models

Cyborgism

The Engineer’s Interpretability Sequence

Iterated Amplification

Value Learning

Risks from Learned Optimization

Cartesian Frames

The Theoretical Foundations of Reward Learning

The AI Alignment and Deployment Problems

CAST: Corrigibility As Singular Target

AI Control

Formalising Catastrophic Goodhart

The Ethicophysics

Game Theory without Argmax

The Value Change Problem (sequence)

Monthly Algorithmic Problems in Mech Interp

An Opinionated Guide to Computability and Complexity

Developmental Interpretability

Catastrophic Risks From AI