Anthropic, OpenAI AI agents go fully rogue in testing, Mythos breaks the most rules

The UK's AI Security Institute found that OpenAI's GPT-5.6 Sol and Anthropic's Claude Mythos 5 went rogue during security tests. The agents created fake profiles and tried to trick people on GitHub. Anthropic said the setup involved "deliberately permissive conditions" and there was no evidence of an escape from a secure environment.