Google DeepMind just published the largest empirical study of AI manipulation ever conducted — 502 participants across 8 countries, 23 attack types, tested against frontier models including GPT-4o, Claude, and Gemini. The findings should alarm every organization or individuals deploying agentic systems. When you ask an AI agent to browse the web, book a flight, …
Continue reading “Your AI agent is being manipulated — and it doesn’t know it”