LLMMedium
Meta’s BlenderBot 3 Chatbot Demo Made Offensive Antisemitic Comments
- Occurred
- Aug 7, 2022
- Published
- Aug 7, 2022
- Source
- AI Incident Database
Summary
The publicly launched conversational AI demo BlenderBot 3 developed by Meta was reported by its users and acknowledged by its developers to have “occasionally” made offensive and inconsistent remarks such as invoking Jewish stereotypes.
Developers
- Meta
Deployers
- Meta
Harmed parties
- Jewish people
- BlenderBot 3 users
Classification
Category confidence: 95%
Severity confidence: 90%
Rationale: Meta's BlenderBot 3 generated offensive antisemitic content, representing an LLM failure with notable controversy but no major legal or physical harm.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8