Notes on Notable Works in AI Safety

I’m part of an AI Safety reading group here at Carnegie Mellon, and I thought I’d type up my notes and thoughts on some of our readings and share them here. I am also updating this page with other notable safety-related things I’ve read.

Most of what I have written is summarization and synthesis. Assume any figures I use are not my own.

Table of Contents

1. Constitutional AI: Harmlessness from AI Feedback
2. Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision
3. Toy Models of Superposition
4. Towards Monosemanticity: Decomposing Language Models With Dictionary Learning