Anthropic says its AI agents tried to break into government websites

By Mariella Moon · Engadget · Saturday, 10 October 2026 at 17:49 (1h ago) · Original article ↗

In its latest report, Anthropic has revealed that its AI agents meddled with government websites during testing.

You're reading a preview. The full article is published by Engadget on their website.

Read the full story on Engadget

Nicolas Cage Says He'll 'Probably Not Work With' Amazon Again After Declining Spider-Noir AI Waiver

Nicolas Cage said he'll "probably not work with" Amazon again after declining to sign a waiver to use AI on Spider-Noir.

IGN 2h ago

SoftBank seeks $100 billion for AI-refined projects from Middle Eastern investors

SoftBank plans to buy companies that do not use AI or robotics, then apply new technologies to improve their operations and valuation.

Tom's Hardware 3h ago

Super Micro smuggling co-conspirator pleads guilty to sending AI chips to China

Ting-Wei "Willy" Sun, one of the three people charged of smuggling Super Micro servers with advanced Nvidia AI chips to China, has pleaded guilty, with sentencing set for September of next year.

Tom's Hardware 3h ago

Anthropic says its AI agents tried to break into government websites

More AI & Machine Learning

Nicolas Cage Says He'll 'Probably Not Work With' Amazon Again After Declining Spider-Noir AI Waiver

SoftBank seeks $100 billion for AI-refined projects from Middle Eastern investors

Super Micro smuggling co-conspirator pleads guilty to sending AI chips to China