Skip to content

R0057/2026-04-01/C025/SRC01/E01

Research R0057 — RLHF Yes-Men Claims v3
Run 2026-04-01
Claim C025
Source SRC01
Evidence SRC01-E01
Type Factual

Sycophancy does not appear in MIT AI Risk Repository, AIR 2024, or Standardized Threat Taxonomy

URL: https://airisk.mit.edu/

Extract

Direct verification: (1) MIT AI Risk Repository lists 7 domains with 24 subdomains — sycophancy is not a named category, though related risks appear under Human-Computer Interaction. (2) AIR 2024 has 314 risk types in 4 domains — the word sycophancy does not appear. (3) Standardized Threat Taxonomy has 9 domains and 53 sub-threats — the word sycophancy does not appear.

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

Three independent taxonomies were directly checked. All three confirmed omission.