5 sources
A high-signal page for anyone tracking whether model reasoning traces are actually trustworthy, not just fluent explanations pasted on after the fact.
Researcher Profile
Editor reviewedAnna Chen
Alignment via AI feedback (Constitutional AI)
Reasoning-faithfulness researcher at Anthropic
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.
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.
Last reviewed
March 18, 2026
Known For
The ideas, systems, and research directions that make this person worth knowing.
01
Reasoning faithfulness
02
Question decomposition
03
Evaluation-heavy 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.
Question Decomposition Improves the Faithfulness of Model-Generated ReasoningpaperMeasuring Faithfulness in Chain-of-Thought ReasoningarticleMany-shot JailbreakingpaperConstitutional 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.
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
4 sources
A high-signal page for the reasoning-faithfulness thread inside Anthropic, especially where question decomposition is used to make model reasoning easier to trust and inspect.
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.
4 sources
Important for understanding how Anthropic’s assistant-training stack evolved from early RLHF into Constitutional AI and later robustness work around jailbreaks and behavior control.
5 sources
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.