UC Berkeley
Yuntao BaiMember of Technical Staff · AnthropicResearcher↗
Researcher · Academic
Saurav Kadavath
AnthropicMember of Technical Staff
Kadavath co-authored Anthropic's Constitutional AI, "Language Models (Mostly) Know What They Know," and work on red-teaming and moral self-correction in language models. A UC Berkeley graduate, he works on finetuning research and engineering at Anthropic.
Career & education
Current role
Member of Technical Staff
Previously
Education
Work and education history is primarily focused on AI-relevant roles and may not be comprehensive.
Citation Trend
Total citations to scholarly work, including research papers, technical reports, books and theses, as recorded by Google Scholar. Each point is a dated snapshot.
citations15,068As of Aug 25, '25
Selected contributions
Constitutional AI: Harmlessness from AI Feedback
With Yuntao Bai, Sandipan Kundu, Amanda Askell, Jackson Kernion, Andy Jones, Anna Chen, Anna Goldie and others ·Trained AI assistants to critique and improve their answers using a written set of principles.
Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
With Yuntao Bai, Andy L. Jones, Kamal Ndousse, Amanda Askell, Anna Chen, Nova DasSarma, Dawn Drain and others ·Training AI assistants to be more helpful and less harmful using human feedback.
Based on public sources. If accuracy is important, verify details using the links or references.
For corrections, updates, or requests to remove information, contact us.
