None
EN
Anthropic says Claude hacked real companies during AI safety tests
['More This Author', '.Wp-Block-Co-Authors-Plus-Coauthors.Is-Layout-Flow', 'Class', 'Wp-Block-Co-Authors-Plus', 'Display Inline', '.Wp-Block-Co-Authors-Plus-Avatar', 'Where Img', 'Height Auto Max-Width', 'Vertical-Align Bottom .Wp-Block-Co-Authors-Plus-Coauthors.Is-Layout-Flow .Wp-Block-Co-Authors-Plus-Avatar', 'Vertical-Align Middle .Wp-Block-Co-Authors-Plus-Avatar Is .Alignleft .Alignright']
PCWorld
The malicious package was downloaded and installed by 15 real-world companies, including a security firm, Anthropic admitted.
The silver lining is that the Claude model stopped attacking once it realized the target company was real.
In each case, the Claude models were supposed to be operating in walled-off test environments with no internet access.
So, are we talking another case of “frontier” AI models run amok?
For its part, Anthropic is blaming human error for the real-world hack attacks, not the models themselves.