← People

Saurav Kadavath

Source-listed: Anthropic

Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.

Selected work

5
  1. Language Models (Mostly) Know What They KnowSaved credit: First author · 2022Explore people connected to this work →
  2. Constitutional AI: Harmlessness from AI FeedbackSaved credit: Contributor · 2022Explore people connected to this work →
  3. Training a Helpful and Harmless Assistant with Reinforcement Learning from Human FeedbackSaved credit: Contributor · 2022Explore people connected to this work →
  4. Discovering Language Model Behaviors with Model-Written EvaluationsSaved credit: Maintainer · 2022Explore people connected to this work →
  5. Measuring Mathematical Problem Solving With the MATH DatasetSaved credit: Contributor · 2021Explore people connected to this work →