E01¶


Research	R0057 — RLHF Yes-Men Claims v3
Run	2026-04-01
Claim	C021
Source	SRC01
Evidence	SRC01-E01
Type	Factual

AI safety uses sycophancy; human factors uses automation bias/complacency/overtrust — overlapping phenomena with different vocabulary

URL: https://en.wikipedia.org/wiki/Automation_bias

Extract¶

Multiple academic sources document that 'sycophancy' is an AI/ML term while 'automation bias' and 'automation complacency' are human factors terms. Parasuraman and Manzey (2010) established the human factors vocabulary. Recent papers note that LLM sycophancy can exacerbate automation bias, connecting the two phenomena.

Relevance to Hypotheses¶

Hypothesis	Relationship	Strength
H1	Supports	Directly addresses claim accuracy
H2	Supports	Allows for partial correctness
H3	Contradicts	Evidence contradicts material inaccuracy

Context¶

Well-documented across multiple disciplines with decades of literature.