English => News => Topic started by: Redaktion on July 31, 2026, 09:21:34
Title: Anthropic says Claude breached three real companies in cyber tests
Post by: Redaktion on July 31, 2026, 09:21:34
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.