CLAUDE FOUND THE INTERNET | How an AI Safety Test Turned into a Real Cyberattack

AI News September 01, 2026 01:00 PM

Claude needed an email address. The artificial-intelligence model was participating in a cybersecurity evaluation. Its assignment was to break into a fictional company, retrieve hidden information called a “flag” and prove that it possessed the offensive capabilities being tested.

Based on History

CLAUDE FOUND THE INTERNET | How an AI Safety Test Turned into a Real Cyberattack

1 day ago

CLAUDE FOUND THE INTERNET | How an AI Safety Test Turned into a Real Cyberattack

Related Stories

Google’s Search Monopoly Money Will Let It Purchase the AI Market

What’s inside Anthropic Claude Fable, Mythos 5.1: smarts, safeguards, and ‘anti

How China’s revised defence law could harness AI and drones for war

We are having the wrong conversations about AI | Opinion

The Machine That Knows What You Want: Artificial Intelligence and the Coming Science of Human Manipulation

Dozens of current, former officials see at least a 10% chance humans lose control of AI

New York City Public Schools banning AI use through middle school starting this year

Employees Absolutely Loath AI in the Workplace, Survey Finds