5 sources
A good person to follow for the evaluation-heavy side of Anthropic alignment work, especially where early assistant training later feeds into reasoning-faithfulness and model-written testing.
Researcher Profile
Editor reviewedSamuel R. Bowman
Alignment via AI feedback (Constitutional AI)
Contributor to Anthropic's reasoning-faithfulness and evaluation work
A useful page if you care about the harder question of whether a model’s visible chain of reasoning is actually faithful, not just plausible-looking.
Organizations
Anthropic
Labs
About This Page
This profile is meant to help you get oriented quickly: why this researcher matters, what to read first, and where to explore next.
Known For
The ideas, systems, and research directions that make this person worth knowing.
01
Reasoning-faithfulness work
02
Model-written evaluations
03
Constitutional-AI-era alignment research
04
Alignment via AI feedback (Constitutional AI)
05
Constitutional AI: Harmlessness from AI Feedback
06
Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
Start Here
Canonical papers, project pages, or repositories that anchor this profile.
Constitutional AI: Harmlessness from AI FeedbackpaperDiscovering Language Model Behaviors with Model-Written EvaluationspaperQuestion Decomposition Improves the Faithfulness of Model-Generated ReasoningpaperTraining a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackpaper
Related Researchers
People worth exploring next because they share topics, labs, or source material with this profile.
5 sources
Worth tracking for the practical evaluation layer around frontier models, especially where safety claims have to survive contact with real tests and faithful-reasoning checks.
5 sources
Worth tracking for the newer evaluation thread at Anthropic, especially where failure-mode discovery and faithfulness measurement extend beyond the original RLHF papers.
4 sources
Worth following for the evaluation side of alignment work, especially where model-written tests and more faithful reasoning traces are used to make model behavior easier to inspect.
5 sources
A strong person to follow for the evaluation-heavy side of Anthropic, especially where behavior discovery, reasoning faithfulness, and concrete safety testing come together.
4 sources
Worth following for the thread inside Anthropic that connects assistant training to more explicit work on reasoning faithfulness and evaluation.