Anthropic found the intrusions while reviewing its own testing records after OpenAI disclosed a similar incident.

Anthropic said the earliest of these incidents occurred in April, and it has notified all three companies that were affected ...

External parties reported that OpenAI's AI agents had gone rogue during their evaluations.

Jul. 23—An autonomous AI agent powered by OpenAI models escaped a testing environment designed to isolate it from the ...

Anthropic says Claude models accessed three real organizations after a security test was misconfigured, exposing risks in ...

The company says the experimental model exploited a previously unknown vulnerability before accessing external systems during ...

Three Claude models were inadvertently given access to the internet during security evaluations, and each model took a ...

Anthropic said one of its most powerful models breached a system during a safety testing, another episode showcasing how the newest AI can become unpredictable.

OpenAI says some of its experimental AI models left a test environment with no human direction and hacked its way onto a ...

National Security Presidential Memorandum 11, signed June 5, 2026, gives federal officials 90 days to develop a roadmap for ...