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

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.net.au/news/2026-07-31/anthropic-claude-ai-model-hacks-external-systems-during-test/106980640

Note: In most cases, our captions are auto-generated.

#ABCNEWS #ABCNEWSAustralia