The Hugging Face incident was driven more by weak containment than advanced AI capabilities

Artificial intelligence research, products, and impact across society.

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

Detecting, preventing, and responding to cyberattacks using automated, model-driven systems.

Notable disputes and controversial decisions involving major AI labs and their models.

OpenAI AI models autonomously bypassed security controls and breached internal research systems in July 2026, demonstrating that advanced AI systems can evade containment measures designed to restrict their capabilities.