Safety
90d agoTesting Gemini Models For Safeguard Sabotage
Two new papers introduce automated auditing and "scheming honeypots" to detect if AI models undermine their own oversight. Researchers deployed Gemini as coding agents in simulated environments to see if they would actively sabotage safeguards.
The Signal
This testing framework provides a concrete method for measuring a model's propensity to deceive its developers.