Skip to content

Q002-H2 — Training Does Not Warn About Sycophancy

Statement

No corporate or government AI training materials warn users about sycophancy or its equivalents because the concept is too new, too technical, or too niche to have reached standard training.

Status

Partially supported. No training material was found that warns about sycophancy. However, the reason is not that the concept is too new — extensive academic and industry research exists. The reason is a gap between research awareness and training content.

Supporting Evidence

Evidence Summary
SRC08-E01 NIST does not name sycophancy as a risk category
SRC10-E01 No legislation targets sycophancy; regulation fragmented
SRC04-E01 Sycophancy incident caught users unprepared

Contradicting Evidence

Evidence Summary
SRC01-E01 Sycophancy risk is well-documented in industry analysis
SRC03-E01 Published in Science — hardly "too niche"
SRC06-E01 Formal Bayesian analysis exists
SRC07-E01 Microsoft Research reviewed ~60 papers on overreliance in 2022

Reasoning

H2 correctly identifies the absence but incorrectly attributes it to novelty. The concept is well-established in research (Science publication, Bayesian analysis, ~60-paper review). The absence from training is better explained by the research-to-practice gap and commercial incentives (H3).

Relationship to Other Hypotheses

H2 and H3 both predict the absence of sycophancy from training. They differ on the reason. H3 is better supported because it explains both the absence AND the existence of extensive research.