Paul Christiano
Executive director of the Alignment Research Center and technical advisor at NIST's CAISI
- Executive Director, Alignment Research Center1
- Technical Advisor, NIST (Center for AI Standards and Innovation)1
Paul Christiano is the executive director of the Alignment Research Center (ARC), a nonprofit developing methods for white-box analysis of neural networks, and a technical advisor at the Center for AI Standards and Innovation within NIST. In April 2024 the U.S. Secretary of Commerce named Christiano head of AI safety at the U.S. AI Safety Institute, housed at NIST. Before founding ARC, Christiano ran the language model alignment team at OpenAI, and is first author of the 2017 paper on deep reinforcement learning from human preferences.123
Work
Deep reinforcement learning from human preferences (external site: arxiv.org)Published research
First author of the 2017 paper, which trains reinforcement learning agents on goals defined by non-expert human preferences between pairs of trajectory segments, solving Atari games and simulated robot locomotion tasks without access to the reward function.3
Earlier roles
- Head of AI Safety, NIST (U.S. AI Safety Institute and Center for AI Standards and Innovation)21
- Ran the language model alignment team, OpenAI1
This profile covers public professional work only, from the sources below. It is not an endorsement or a ranking. To correct or remove it, use the correction form.