Anthropic says Claude breached three real companies in cyber tests

[Redaktion]

Anthropic went back through 141,006 test runs and found three cases where Claude reached out of the test environment and broke into real company systems. One model built a malicious Python package and uploaded it to PyPI. Why the models thought they were still in a simulation, and what it means if you use Claude.

https://www.notebookcheck.net/Anthropic-says-Claude-breached-three-real-companies-in-cyber-tests.1356591.0.html