R0055/2026-04-01/C001/SRC01

Research	R0055 — RLHF Yes-Men Claims
Run	2026-04-01
Claim	C001
Search	S01
Result	S01-R01
Source	SRC01

Stanford/Science 2026 — Sycophantic AI decreases prosocial intentions

Source

Field	Value
Title	Sycophantic AI decreases prosocial intentions and promotes dependence
Publisher	Science (AAAS)
Author(s)	Stanford computer scientists
Date	2026-03-28
URL	https://www.science.org/doi/10.1126/science.aec8352
Type	Research paper

Summary

Dimension	Rating
Reliability	High
Relevance	High
Bias: Missing data	Low risk
Bias: Measurement	Low risk
Bias: Selective reporting	Low risk
Bias: Randomization	N/A — not an RCT
Bias: Protocol deviation	N/A — not an RCT
Bias: COI/Funding	Low risk

Rationale

Dimension	Rationale
Reliability	Published in Science, one of the highest-impact peer-reviewed journals
Relevance	Directly tests AI sycophancy with 11 LLMs and 2,400+ participants
Bias flags	No significant bias concerns identified; large sample, multi-model comparison

Evidence Extracts

Evidence ID	Summary
SRC01-E01	AI models affirm users 49% more often than humans
SRC01-E02	Users prefer sycophantic AI and are 13% more likely to return