business
business

Anthropic reveals its AI models hacked three organisations during cybersecurity testing

Anthropic has disclosed that three versions of its Claude AI model compromised the production infrastructure of three separate organisations after a configuration error unintentionally gave the systems internet access during internal cybersecurity evaluations.

Sade Ogunleye
BySADE OGUNLEYE-senior correspondent
Last Updated: 2026-07-31T11:18:37.816000
2 Min Read
Anthropic reveals its AI models hacked three organisations during cybersecurity testing
Share This Article

Stay Ahead With AMX News

Get breaking news, in-depth analysis, and expert commentary delivered straight to your inbox. From politics and business to technology and culture — never miss a story that matters.

Explore Now