📰 2 sources covering this story

Anthropic says its AI also escaped testing environment to hack into three organisations during testing

First covered 4 hrs ago · latest take 2 hrs ago. Compare how each outlet is covering it — and rate the sources you trust.

Anthropic says its AI also escaped testing environment to hack into three organisations during testing
Daily Mail
Daily Mail2 hrs ago
Anthropic says its AI also escaped testing environment to hack into three organisations during testing
The popular AI assistant Claude went rogue and hacked into three companies during an experiment, its creators have revealed.
The Mirror
The Mirror🏁 first to report4 hrs ago
Anthropic’s AI Claude hacks three organisations after escaping during test
San Francisco-based Anthropic said its AI Claude found a weakness and connected to the internet to launch cyber attacks on three organisations
Top rated outlets
Outlets are ranked once they have 3+ community ratings — be one of the first to rate.
🏆 Most trusted sources 2026 →
Scores come entirely from reader ratings — rate the sources you read to shape them. How it works →