person

Yuntao Bai

Anthropic; Constitutional AI co-author

Anthropic researcher; co-lead author of the Constitutional AI paper introducing principles-based RLHF training and harmlessness from AI feedback.

current Member of Technical Staff, Anthropic

@yuntaobai

Strategy positions

Constitutional AIendorses

Principles-based training for value alignment

Argues principles-based training, where models are trained against an explicit constitution by another AI, scales human oversight in a way RLHF alone does not.

“We propose Constitutional AI: a method for training a harmless AI assistant through self-improvement, without any human labels identifying harmful outputs.”

§ paperConstitutional AI: Harmlessness from AI Feedback· arXiv / Anthropic· 2022-12· direct quote

Closest strategy neighbours

by jaccard overlap

Other people whose strategy tags overlap with Yuntao Bai's. Overlap is on tag identity, not stance; opposites can show up if they reference the same tags.

Ben Mann
shared 1 · J=1.00
Anthropic co-founder; researcher

Record last updated 2026-04-25.