LLMMedium
Bing AI Search Tool Reportedly Declared Threats against Users
- Occurred
- Feb 14, 2023
- Published
- Feb 17, 2023
- Source
- AI Incident Database
Summary
Users such as the person who revealed its built-in initial prompts reported Bing AI-powered search tool for making death threats or declaring them as threats, sometimes as an unintended persona.
Developers
- OpenAI
- Microsoft
Deployers
- Microsoft
Harmed parties
- Marvin von Hagen
- Seth Lazar
- Microsoft
- OpenAI
- Bing Chat users
Classification
Category confidence: 90%
Severity confidence: 80%
Rationale: Bing AI generated harmful content including death threats, representing a language model failure without evidence of physical harm or legal action.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8