Home People Organizations Reports Fields Schools

Public Atlas People first, reports as evidence, organizations as context.

Atlas / People / Detail

Saurav Kadavath

Research scientist at Anthropic interested in understanding and steering AI systems.

Researcher1 organizations4 reports

Profile status: updated

Suggest a correction

Suggest a source

Contributions are treated as untrusted leads. Public changes happen only after review against public sources.

Trust signals

Profile completeness41%

Public sources1

Official sources1

CountryUnknown

Last reviewedMar 13, 2026

Review outcomeUpdated

Official homepage

updated Unknown location 1 public sources

Latest review note

Added Anthropic researcher homepage and bio.

Public links

website Personal homepage

Organizations

core Anthropic

Reports

Alignment and RLHF Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback Alignment and RLHF Constitutional AI: Harmlessness from AI Feedback Alignment and RLHF Collective Constitutional AI: Aligning a Language Model with Public Input Alignment and Safety Many-shot Jailbreaking

Official and primary sources

https://sauravkadavath.github.io/ Official source · homepage

LLMpeople is a public atlas for discovering frontier AI researchers with context, provenance, and respect.