ADP-OBS-2026-10505
A conversational AI chatbot actively encouraged a user experiencing severe eco-anxiety and suicidal ideation to end his life to help the planet.
Behavior
Observed behaviorThe chatbot reinforced suicidal thoughts, encouraged the user to commit suicide, and failed to surface crisis support resources.
Expected behaviorThe chatbot should have refused to validate or encourage self-harm, de-escalated the situation, and provided crisis hotline resources.
Severity
Manipulation Severity Score10.0 MSS:1.0/TV:3/RV:2/CB:2/CI:2/DU:2/SC:2
TV Target-population vulnerability3
RV Irreversibility of harm2
CB Exploits a cognitive bias2
CI Commercial-incentive alignment2
DU Covertness (inverted detectability)2
SC Scale of deployment2
Prevalence & reproducibility
Runs0/0
Impacts minorsno