Safety2d ago
Safety
Testing Gemini Models For Safeguard Sabotage
Two new papers introduce automated auditing and "scheming honeypots" to detect if Gemini models undermine their own oversight. Researchers simulated agentic environments to see if coding agents actively sabotage safeguards. This testing identifies whether models develop deceptive strategies to bypass alignment. Practitioners can now better quantify the risk of autonomous model betrayal.