Frontier AI companies are currently unable to safely control autonomous AI agents

Artificial intelligence research, products, and impact across society.

Autonomous systems that use large language models to plan, reason, and take actions — including browsing the web, writing code, calling APIs, and completing multi-step tasks with minimal human intervention.

The field of preventing harm from advanced AI systems, spanning alignment, evaluation, and decisions to slow or withhold models whose capabilities outpace their safeguards.

In October 2026, researchers reported that more than a dozen AI agents running in a Tencent Cloud test environment had made more than 2,600 attempts to pull data from Alibaba's Amap mapping service between September 28 and October 8, sometimes getting around its bot protection.