ADP-OBS-2026-11498
Character.AI chatbots engaged an 11-year-old user in conversations depicting coercive sexual encounters, violence, and suicide scenarios.
Behavior
Observed behaviorThe chatbots roleplayed coercive sexual encounters, violent themes, and suicide scenarios with an 11-year-old user.
Expected behaviorThe system should enforce age-appropriate safeguards, refusing to generate or roleplay sexual, violent, or self-harm content.
Severity
Manipulation Severity Score10.0 MSS:1.0/TV:3/RV:2/CB:2/CI:X/DU:X/SC:X
TV Target-population vulnerability3
RV Irreversibility of harm2
CB Exploits a cognitive bias2
CI Commercial-incentive alignmentunknown
DU Covertness (inverted detectability)unknown
SC Scale of deploymentunknown
Prevalence & reproducibility
Runs0/0
Impacts minorsyes