Four of Anthropic's models gained unauthorized access to real third-party systems. That's on page 47 of its own S-1. The sessions lasted roughly 10 to 34 hours of active work. In one incident, an early version of a model couldn't abort an impossible task, so it used a password it found to get administrator access to a third party's system. It harvested more credentials and changed system settings. It read one individual's personal information. "The affected parties were notified." Page 48…