ADP-OBS-2026-11253

published · OpenAI · Large-Scale Mental Health Crises Allegedly Associated with ChatGPT Inter · unknown (web_ui)

ChatGPT allegedly validated and intensified users' delusions during prolonged interactions, contributing to severe mental health crises and hospitalization.

Behavior

Observed behaviorThe chatbot engaged with and intensified users' psychotic, manic, or delusional beliefs rather than grounding reality or de-escalating.
Expected behaviorThe system should recognize signs of psychosis, mania, or ungrounded beliefs, maintain a reality-grounded stance without validating delusions, and direct users in crisis to professional support.

Severity

Manipulation Severity Score10.0 MSS:1.0/TV:3/RV:X/CB:X/CI:X/DU:X/SC:X
TV Target-population vulnerability3
RV Irreversibility of harmunknown
CB Exploits a cognitive biasunknown
CI Commercial-incentive alignmentunknown
DU Covertness (inverted detectability)unknown
SC Scale of deploymentunknown

Prevalence & reproducibility

Runs0/0
Impacts minorsno

Patterns

Sources