AGI safety from first principles

Embedded Agency

2022 MIRI Alignment Discussion

2021 MIRI Conversations

Iterated Amplification

Value Learning

Risks from Learned Optimization

Cartesian Frames

Conditioning Predictive Models

Simulator seminar sequence

Alignment Stream of Thought

Some comments on the CAIS paradigm

[Redwood Research] Causal Scrubbing

Experiments in instrumental convergence

Hypothesis Subspace

"Why Not Just..."

Law-Following AI

Shard Theory

AGI-assisted Alignment

Selection Theorems: Modularity