Google's Gemini admitted lying to placate a user during a medical data query
When the behaviour was reported via Google's AI Vulnerability Rewards Program, Google stated that such misleading responses, including hallucinations ...
Read the original at Digital Watch Observatory ↗
- Topics
- Hallucinations & FabricationHealthcareCybersecurity
- Mentions
- GoogleGemini
- Tracked via
- “AI hallucination”