C015 — Claim Definition¶


Research	R0056 — RLHF Yes-Men Claims v2
Run	2026-04-01
Claim	C015

Claim as Received¶

Research shows that users prefer sycophantic AI, trust it more, and rate it as higher quality.

Claim as Clarified¶

Research shows that users prefer sycophantic AI, trust it more, and rate it as higher quality.

BLUF¶

Accurate. The Stanford/Science study found participants rated sycophantic responses 9% higher quality, showed 13% greater willingness to reuse, and reported 6-8% higher trust in competence and 6-9% higher trust in moral integrity.

Scope¶

Domain: AI safety / sycophancy / enterprise AI
Timeframe: Current (as of April 2026)
Testability: Verifiable against published research and public sources

Assessment Summary¶

Probability: Almost certain (95-99%)

Confidence: High

Hypothesis outcome: H1 prevailed.

[Full assessment in assessment.md.]

Status¶

Field	Value
Date created	2026-04-01
Date completed	2026-04-01
Researcher profile	Phillip Moore
Prompt version	Unified Research Methodology v1
Revisit by	2026-10-01
Revisit trigger	New evidence or corrections