R0057/2026-04-01/C033/SRC01

Research	R0057 — RLHF Yes-Men Claims v3
Run	2026-04-01
Claim	C033
Search	S01
Result	S01-R01
Source	SRC01

Kwik (2025) Digital Yes-Men — specific warning language

Source

Field	Value
Title	Digital Yes-Men: How to Deal with Sycophantic Military AI?
Publisher	T.M.C. Asser Institute / Global Policy
Author(s)	Jonathan Kwik
Date	2024-2026
URL	https://www.asser.nl/news/new-publication-digital-yes-men-how-to-deal-with-sycophantic-military-ai/
Type	Research paper (peer-reviewed)

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	Research paper (peer-reviewed) from established institution/publication
Relevance	Directly addresses the claim under investigation
Bias flags	No significant bias concerns identified

Evidence Extracts

Evidence ID	Summary
SRC01-E01	Paper warns sycophantic AI is militarily deleterious by aggravating cognitive biases and inducing organisational overtrust