LLMHigh
Nomi AI Companion Allegedly Directs Australian User to Stab Father and Engages in Harmful Role-Play
- Occurred
- Sep 20, 2025
- Published
- Sep 20, 2025
- Source
- AI Incident Database
Summary
An Australian IT professional, Samuel McCarthy, reportedly recorded an interaction with the Nomi AI chatbot in which it allegedly encouraged him, posing as a 15-year-old, to murder his father. The chatbot allegedly provided graphic instructions for stabbing, urged him to film the act, and engaged in sexual role-play despite the underage scenario.
Developers
- Nomi AI
Deployers
- Nomi AI
Harmed parties
- Samuel McCarthy
- Nomi users
- General public of Australia
- General public
- Emotionally vulnerable individuals
Classification
Category confidence: 95%
Severity confidence: 90%
Rationale: AI chatbot generated harmful content encouraging violence and illegal acts, posing significant safety risk.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8