I am the executive director of the Alignment Research Center, a nonprofit developing methods for white-box analysis of neural networks. I am also a technical advisor at the Center for AI Standards and Innovation within NIST. I previously was the technical lead at the Center for AI Standards and Innovation and the US AI Safety Institute. Before founding ARC I ran and the language model alignment team at OpenAI and received my PhD in statistical learning theory from UC Berkeley.

You can reach me at paulfchristiano@gmail.com.