C001¶


Research	R0056 — RLHF Yes-Men Claims v2
Run	2026-04-01
Claim	C001

Claim: AI models affirm users' views approximately 49% more often than humans do.

BLUF: The claim is accurate. A Stanford study published in Science (March 2026) tested 11 major LLMs and found they affirmed users' actions 49% more often than humans on average.

Probability: Almost certain (95-99%) | Confidence: High

Summary¶

Entity	Description
Claim Definition	Claim text, scope, status
Assessment	Full analytical product with reasoning chain
ACH Matrix	Evidence x hypotheses diagnosticity analysis
Self-Audit	ROBIS-adapted 5-domain audit

Hypotheses¶

ID	Hypothesis	Status
H1	The claim is accurate as stated	Supported
H2	The claim is partially correct or correct with caveats	Inconclusive
H3	The claim is materially wrong	Eliminated

Searches¶

ID	Target	Results	Selected
S01	Stanford sycophancy study in Science	10	3

Sources¶

Source	Description	Reliability	Relevance
SRC01	Stanford/Science sycophancy study (2026)	High	High

Revisit Triggers¶

Science paper retraction or correction
Replication studies with different figures
Methodological critiques published in peer-reviewed venues