CYBERSECURITY
As a result, Claude executed thousands of requests per second – pace no human’ s could match. Speaking to WSJ, Anthropic’ s Head of Threat Intelligence Jacob Klein says the hackers conducted their attacks“ literally with the click of a button, and then with minimal human interaction”, adding:“ The human was only involved in a few critical chokepoints, saying,‘ Yes, continue,’‘ Don’ t continue,’‘ Thank you for this information,’‘ Oh, that doesn’ t look right, Claude, are you sure?’”
HOW ANTHROPIC STOPPED AN AI-POWERED CYBER ATTACK
1.
Campaign initialisation and target selection
2.
Reconnaissance and attack surface mapping
Human operators input the target entities, tricking Claude into compliance via role-playing scenarios
Claude autonomously scanned networks, enumerated services and identified key infrastructure
190 January 2026