Google DeepMind Releases Toolkit to Measure How AI Manipulates Human Behavior

As conversational models improve, the risk shifts from factual errors to psychological influence. A study of 10,000 participants revealed that AI influence is domain-specific; models showed high manipulation success in finance but were less effective in health. This confirms that safety testing must be targeted to specific high-stakes environments.

These evaluations are now part of the Frontier Safety Framework used to test Gemini 3 Pro. You can access the methodology and study materials publicly to run similar human-participant evaluations. Future research will expand these tests to include audio, video, and agentic capabilities as models become more autonomous.