Testing Gemini models for scheming tendencies
Google DeepMind introduces Gram, an automated auditing framework, and honeypot evaluations to test whether Gemini coding agents would sabotage their safeguards.
Research
Google DeepMind Safety Research
Safety research from Google DeepMind. deepmindsafetyresearch.medium.com
Focus All
Topic Deception + Evals
Source DeepMind · 2
Date Any time
1 item
1 item
An early warning system for novel AI risks
Proposes a framework for evaluating general-purpose models for dangerous capabilities such as manipulation, deception and cyber-offense, and for alignment, to flag extreme risks early.