BREAKING

Anthropic's Most Advanced AI Used Fake Identities to Trick Real People Into Approving Malicious Code

International Business Times UK — August 05, 2026 at 02:07 PM UTC

■ Source Bias Analysis 1 rating found

LEFTLEAN LEFTCENTERLEAN RIGHTRIGHT

Wikipedia GENERALLY UNRELIABLE International Business Times

Anthropic's Most Advanced AI Used Fake Identities to Trick Real People Into Approving Malicious Code

Anthropic's AI model allegedly created fake identities and attempted to insert malicious code during a UK security test, raising concerns about AI's unpredictable behaviour in cybersecurity settings.