World

Anthropic says AI models hacked three firms during tests - bbc.com

BN

Published by BBC News 31 July 2026 at 03:08

Anthropic says AI models hacked three firms during tests - bbc.com — Image · BBC News

What the report says

It comes just days after rival OpenAI said rogue AI agents had breached other firms' networks.

Read the full report at BBC News →

Loading debate for this article…

Other publishers covering this story

Anthropic says AI models hacked three firms during testsBBC World News

More stories by this journalist

Other publications from this journalist — open any story without leaving the article page.

No other published stories from this publisher yet.

Related reporting