Back to researchers

Paul Christiano

Alignment theory, reward modeling

Major influence on reward-modeling and oversight ideas that feed into modern post-training.

Highlights

AlignmentRLHFSafety
Focus: Alignment theory, reward modeling
Why it matters: Major influence on reward-modeling and oversight ideas that feed into modern post-training.

Research Areas

AlignmentRLHFSafety
Paul Christiano - AI Researcher Profile | 500AI