Skip to content
Bruce W. Lee
Blogs
March 2026
Salient directions in AI control
February 2026
What would it take to trust AI for AI safety?
December 2025
Bitter lessons from “Distillation robustifies unlearning”
August 2025
Neural networks, strange attractors, and orderliness in chaos
November 2024
On getting started in research
September 2024
Mechanistically programming a language model’s behavior