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.
Researcher Profile
Editor reviewedEli Tran-Johnson
Alignment via AI feedback (Constitutional AI)
Evaluation and behavior-discovery researcher at Anthropic
A useful profile for the people building Anthropic’s evaluation stack, especially the model-written-evals line that tries to surface behaviors faster than hand-built test sets can.
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
Official And External Links
Known For
The ideas, systems, and research directions that make this person worth knowing.
01
Model-written evaluations
02
Behavior discovery in aligned models
03
Evaluation tooling for frontier systems
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.
Signature Works
Additional papers, projects, or repositories that help flesh out the profile.
Related Researchers
People worth exploring next because they share topics, labs, or source material with this profile.
5 sources
Important because he is right at the center of the model-written-evals line, which became one of Anthropic’s clearest attempts to discover behaviors faster than manual evaluation can.
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
A useful person to follow for the part of Anthropic that moved from assistant training into explicit behavior-discovery 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.
4 sources
Important because he sits near the boundary between alignment theory and concrete failure-mode discovery, especially jailbreaks, preference training, and behavior evaluations.