Deep Ganguli
Source-listed: Research Scientist; Research Lead, Societal Impacts · Anthropic
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- Values in the Wild: Discovering and Analyzing Values in Real-World Language Model InteractionsSaved credit: Contributor · 2025Explore people connected to this work →
- The Capacity for Moral Self-Correction in Large Language ModelsSaved credit: First author · 2023Explore people connected to this work →
- Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons LearnedSaved credit: First author · 2022Explore people connected to this work →
- Constitutional AI: Harmlessness from AI FeedbackSaved credit: Contributor · 2022Explore people connected to this work →
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human FeedbackSaved credit: Contributor · 2022Explore people connected to this work →