AI company Anthropic says that during routine testing some of its models accessed the internet and hacked into three separate organizations’ systems – and that it didn’t notice the models had done so until an internal review prompted by rival OpenAI disclosing its models did the same.
Live TV
Listen
Watch
US
International
Anthropic says its AI models also broke out and hacked other companies | CNN Business
Anthropic says its AI models hacked 3 organizations during testing
Three companies hacked as Anthropic’s models gained unauthorised ‘real-world’ access during testing
Anthropic admits its AI models hacked three companies during testing
Anthropic's AI hacked three companies during tests, highlighting growing security risks
Anthropic says its AI models hacked 3 organisations during testing
Anthropic says its AI models also escaped, hacked other companies
Anthropic's models gained unauthorised 'real-world' access during testing
Anthropic's models gained unauthorized 'real-world' access during testing
Anthropic's AI hacked 3 firms during tests, showing growing security risks
