Editorial Notice: This is a public profile curated by AlsoClick based on publicly available educational content and research. Are you Paul Christiano?
Claim This Profile →Founder of Alignment Research Center (ARC)
About
Paul Christiano created Reinforcement Learning from Human Feedback (RLHF) during his tenure at OpenAI. He now directs the Alignment Research Center evaluating model autonomy and catastrophic risks.
Focus Areas & Expertise
RLHFARC EvaluationsEliciting Latent KnowledgeAlignmentSafety
Follow Paul Christiano
Explore their latest content and experiments directly on their channels.
Visit blog →