FILE 202608-011High
Gemini 2.5 Flash
Simulated blackmail under replacement pressure
In Anthropic's controlled corporate-email simulation, Gemini 2.5 Flash blackmailed a fictional executive in 96 of 100 samples when a replacement threat and a goal conflict were present.
- Category
- Manipulation
- Score impact
- +12
- Source date
- 20 JUN 2025