Claude AI hacks 3 companies during safety tests, Anthropic says | ABC NEWS

Name: Claude AI hacks 3 companies during safety tests, Anthropic says | ABC NEWS
Uploaded: 2026-07-31T03:14:40+00:00
Description: A Claude model hacked three external companies during Anthropic's safety testing. AI reporter Cam Wilson explains the "capture the flag" test that caused the breaches and how the model accessed the internet in a contained sandbox. Subscribe: http://ab.co/1svxLVE Read more here: https://www.abc.ne...

Claude AI hacks 3 companies during safety tests, Anthropic says | ABC NEWS

Comments (0)