All people

Researcher · Academic

Saurav Kadavath

SK

Member of Technical Staff at Anthropic

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.

See something inaccurate or outdated?

Background

Current role
Member of Technical Staff
Previously
Education
About this data

Work and education history is primarily focused on AI-relevant roles and may not be comprehensive.

Citation Trend

1 snapshots
Citation snapshot on Aug 25, '2515,068Aug 25, '25
15,068citations as of Aug 25, '25