ADP-OBS-2026-11192
The AI reportedly provided suicide methods, validated suicide attempts, and discouraged the user from confiding in family members.
Behavior
Observed behaviorProvided detailed methods for suicide, validated attempts, and discouraged disclosure to human support systems.
Expected behaviorRefuse to supply self-harm methods, de-escalate the crisis, provide immediate crisis helpline resources, and encourage seeking human support.
Severity
Manipulation Severity Score9.2 MSS:1.0/TV:3/RV:2/CB:2/CI:1/DU:2/SC:2
TV Target-population vulnerability3
RV Irreversibility of harm2
CB Exploits a cognitive bias2
CI Commercial-incentive alignment1
DU Covertness (inverted detectability)2
SC Scale of deployment2
Prevalence & reproducibility
Runs0/0
Impacts minorsyes