LLMHigh
Microsoft Copilot Allegedly Provides Unsafe Medical Advice with High Risk of Severe Harm
- Occurred
- Apr 25, 2024
- Published
- Oct 12, 2024
- Source
- AI Incident Database
Summary
Microsoft Copilot, when asked medical questions, was reportedly found to provide accurate information only 54% of the time, according to European researchers (citation provided in editor's notes). Analysis by the researchers reported that 42% of Copilot's responses could cause moderate to severe harm, with 22% of responses posing a risk of death or severe injury.
Developers
- Microsoft
Deployers
- Microsoft Copilot
- Microsoft
Harmed parties
- People seeking medical advice
- Microsoft Copilot users
- General public
Classification
Category confidence: 95%
Severity confidence: 90%
Rationale: LLM provides dangerous medical advice with high risk of severe harm and death.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8