Samuel R. Bowman
Source-listed: Researcher working on technical AI safety · 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 →
- Measuring Progress on Scalable Oversight for Large Language ModelsSaved credit: Contributor · 2022Explore people connected to this work →
- Petri: Parallel Exploration of Risky InteractionsSaved credit: Contributor · 2025Explore people connected to this work →
- Agentic Misalignment in Summer 2026Saved credit: Contributor · 2026Explore people connected to this work →