C021¶


Research	R0057 — RLHF Yes-Men Claims v3
Run	2026-04-01
Claim	C021

Claim: AI safety researchers call the problem sycophancy while regulated industries call it automation bias, automation complacency, overtrust, overreliance, or acquiescence.

BLUF: Confirmed. The vocabulary split is well-documented. AI safety/ML research uses 'sycophancy'; human factors engineering, aviation, and healthcare use 'automation bias', 'automation complacency', 'overtrust', and 'overreliance'. The terms describe overlapping phenomena from different perspectives.

Probability: Very likely (80-95%) | 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 vocabulary split exists as described	Supported
H2	The split exists but with more overlap than claimed	Not supported
H3	No meaningful vocabulary split exists	Eliminated

Searches¶

ID	Target	Results	Selected
S01	Automation bias automation complacency overtrust sycophancy vocabulary communities	10	1

Sources¶

Source	Description	Reliability	Relevance
SRC01	Literature on automation bias and sycophancy terminology	High	High

Revisit Triggers¶

If a shared vocabulary emerges that bridges these communities