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 reviewedTom Conerly
Alignment via AI feedback (Constitutional AI)
Contributor to Anthropic work on interpretability, evaluation, and post-training behavior
Worth knowing because his paper trail hits several of the most useful early Anthropic threads at once: induction heads, calibration, repeated-data scaling, and the practical behavior of post-trained assistants.
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
In-context learning and induction heads
02
Language-model self-knowledge and calibration
03
Early Anthropic post-training and safety evaluations
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.
In-context Learning and Induction HeadspaperLanguage Models (Mostly) Know What They KnowpaperTraining a Helpful and Harmless Assistant with Reinforcement Learning from Human FeedbackpaperConstitutional AI: Harmlessness from AI FeedbackpaperTraining a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackpaper
Signature Works
Additional papers, projects, or repositories that help flesh out the profile.
Supporting Sources
Additional links that help verify and flesh out this profile.
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
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 evaluation-heavy side of Anthropic alignment work, especially where early assistant training later feeds into reasoning-faithfulness and model-written testing.
4 sources
One of the earlier Anthropic contributors worth tracking if you care about the transition from RLHF-style assistant training into scaling and evaluation work.
5 sources
Useful for the seam between Anthropic’s earlier alignment papers and its later audit-oriented safety work, where interpretability and evaluation start feeding into deployment practice.