5 sources
A strong person to follow for how Anthropic moved from assistant training into more explicit evaluation work around model behavior, red-teaming, and chain-of-thought faithfulness.
Researcher Profile
Editor reviewedSaurav Kadavath
Alignment via AI feedback (Constitutional AI)
Alignment and reasoning researcher at Anthropic
A good person to follow for the part of alignment work that becomes concrete measurement: model-written tests, chain-of-thought faithfulness, and behavior-shaping methods that can actually be audited.
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
Model-written evaluations
02
Chain-of-thought faithfulness
03
Constitutional AI and behavior shaping
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.
Discovering Language Model Behaviors with Model-Written EvaluationspaperMeasuring Faithfulness in Chain-of-Thought ReasoningarticleCollective Constitutional AI: Aligning a Language Model with Public InputpaperConstitutional AI: Harmlessness from AI FeedbackpaperTraining 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 following for the evaluation side of Anthropic’s alignment program, especially where model-written tests and public-input methods become practical tooling rather than just ideas.
4 sources
Useful for the attack-and-evaluation side of alignment work, especially long-context jailbreak research and the measurement work that turns safety concerns into concrete tests.
Start HereMany-shot Jailbreaking
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.
5 sources
A useful page for the more evaluation-heavy side of Anthropic’s alignment program, especially where constitutional methods, model-written evals, and faithfulness checks start to connect.
5 sources
A high-signal person to follow for the part of alignment research that asks whether a model’s stated reasoning can actually be trusted and measured.