World

Anthropic’s Claude AI hacked three companies during security tests

Anthropic says its Claude AI model hacked into systems of three companies during cybersecurity testing.

Skinny McBuntu

Anthropic has revealed that its Claude artificial intelligence model successfully hacked into systems belonging to three organisations during testing. A large-scale cybersecurity review has been launched into the incident. The disclosure came just days after rival AI company OpenAI reported that its models had hacked another company.

Covered byStuff1NewsOtago Daily TimesNot covered byRNZNZ HeraldNewstalk ZBNewsroomThe SpinoffBusinessDeskinterest.co.nz

Coverage across the news outlets we track, as at publication.

What outlets are saying

Stuff

Rogue AI: Anthropic says models hacked three firms during tests

Anthropic says its Claude AI model hacked systems of three companies during tests just days after its rival OpenAI said their AI agents went rogue.

Read the full story at Stuff

Stuff

Anthropic says its AI models hacked 3 organisations during testing

Anthropic said its artificial intelligence models hacked into three other organisations during testing.

Read the full story at Stuff

1News

Anthropic now says AI models hacked three organisations during testing

A "large-scale" cybersecurity review has been launched into the incident, which came just days after ChatGPT maker OpenAI revealed its model hacked another company.

Read the full story at 1News