Yuntao Bai
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- Constitutional AI: Harmlessness from AI feedbackSaved credit: First author · 2022Explore people connected to this work →
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human FeedbackSaved credit: First author · 2022Explore people connected to this work →
- Sleeper Agents: Training Deceptive LLMs that Persist Through Safety TrainingSaved credit: Contributor · 2024Explore people connected to this work →
- Many-shot JailbreakingSaved credit: Contributor · 2024Explore people connected to this work →
- Positive Geometries and Canonical FormsSaved credit: Contributor · 2017Explore people connected to this work →