Kamal Ndousse
Source-listed: Machine learning researcher · Anthropic
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- 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 →
- A General Language Assistant as a Laboratory for AlignmentSaved credit: Contributor · 2021Explore people connected to this work →
- Evolution through Large ModelsSaved credit: Contributor · 2022Explore people connected to this work →
- Emergent Social Learning via Multi-agent Reinforcement LearningSaved credit: First author · 2021Explore people connected to this work →