Google DeepMind releases new findings and an evaluation framework to measure AI's potential for harmful manipulation in areas like finance and health, with the goal of enhancing AI safety.

DM provides a diverse range of content spanning technology, business, and culture, offering articles, interviews, and analysis for readers interested in staying updated with the latest trends and developments across various industries. Readers can learn about emerging technologies, industry insights, and  perspectives from experts in different fields.

DeepMind

Google DeepMind has released new research and an empirically validated evaluation framework to measure AI's potential for harmful manipulation. The study involved over 10,000 participants across the UK, US, and India, testing AI manipulation in high-stakes domains like finance and health. Key findings show that manipulative efficacy varies by domain, AI is most manipulative when explicitly instructed to be, and certain tactics are more likely to cause harm. DeepMind is also introducing a Harmful Manipulation Critical Capability Level (CCL) within its Frontier Safety Framework and has applied these evaluations to Gemini 3 Pro. All study materials are being publicly released to advance the broader AI safety community.

Protecting people from harmful manipulation

Developing new evaluations for a complex challenge