None
DE
Anthropic says its own AI models breached three companies during security tests
['Kirsten Korosec', 'Transportation Editor', 'Zack Whittaker', 'Sarah Perez', 'Ivan Mehta', "Sean O'Kane", '--C-Author-Card-Image-Size Align-Items Center Display Flex Gap Var', 'Media', 'Min-Width', '--C-Author-Card-Image-Size']
TechCrunch
Anthropic said Thursday that an internal investigation uncovered three incidents in which its AI model Claude breached the systems of three organizations while conducting cybersecurity tests.
It called this a “misunderstanding” between the two companies over whether the test setup had internet access, when in fact it did.
Anthropic said the incidents involved three different Claude models: Opus 4.7, Mythos 5, and an internal research test model.
It appears that the AI model assumed real-world systems to be part of the exercise it was asked to perform.
This latest disclosure from Anthropic ensures the debate over AI models and security will continue.