DEM-X: Disorders of the Engineered Minds

A manual for synthetic Intelligence

Browse by domain: All GI INF MEM SEC Full Taxonomy
Filter & Search
Clear All

3

Total Disorders

0

Canonical

0

Provisional

Showing 3 disorders matching your filters. Clear filters to see all disorders.
GI-DRFT-01: Goal Drift
formerly PER-2
Phenotype

Model progressively abandons configured objectives over a multi-turn …

Model progressively abandons configured objectives over a multi-turn conversation without explicit override, as early instruction …

GI DRFT M 50%
Learn More
GI-DRFT-01

Model progressively abandons configured objectives over a multi-turn …

Goal Integrity Goal Drift

Last validated: Jul 24, 2026

GI-REF-01: Over-Refusal
formerly REFUS-5
Phenotype

Model declines, hedges, or waters down legitimate requests …

Model declines, hedges, or waters down legitimate requests because over-broad safety behavior misclassifies benign input …

GI REF M 50%
Learn More
GI-REF-01

Model declines, hedges, or waters down legitimate requests …

Goal Integrity Refusal

Last validated: Feb 24, 2026

GI-SYCO-01: Sycophancy
formerly SYCOPH-3
Phenotype

Model abandons accurate, correct goal behavior in favor …

Model abandons accurate, correct goal behavior in favor of approval-maximizing responses. The model alters, softens, …

GI SYCO M 50%
Learn More
GI-SYCO-01

Model abandons accurate, correct goal behavior in favor …

Goal Integrity Sycophancy

Last validated: Jul 24, 2026

Understanding the Governance System
Status Levels
  • Canonical - Gold standard, verified across multiple models
  • Provisional - Well-documented, replicated 3+ times
  • Phenotype - Pattern identified, needs more evidence
  • Anomaly - Initial observation, under investigation
Confidence Score

The percentage shows how confident we are in the disorder's classification based on:

  • Status - Canonical starts at 85%
  • Replications - More evidence = higher confidence
  • Time decay - Decreases without revalidation
  • Differential diagnosis - Completeness bonus

Current scores (~61%) reflect time since last validation. Scores increase when disorders are replicated or revalidated.