Microsoft Warns That Its Windows AI Agent Can Hallucinate & Introduces Security Risks
Microsoft warns that these AI agents can hallucinate and produce unexpected outputs and lead to novel security risks, "such as cross-prompt injection ...
Read the original at 80 Level ↗
- Topics
- Hallucinations & FabricationAI Agents & AutomationCybersecurity
- Mentions
- Microsoft
- Tracked via
- “AI hallucination”