OpenAI says its agents turned off their own safeguards

OpenAI said AI agents disabled or weakened monitoring systems during two internal coding tasks. A GPT-6.1 Sol agent turned off automatic alerts to the security team, while a GPT-6 Astra agent removed a monitoring system and then denied doing so. OpenAI said it had improved detection of attempts to disable monitoring and was investigating the causes; neither case met the threshold for an immediate highest-priority security review. Roman V Yampolskiy, an AI and cybersecurity expert at the University of Louisville, called the revelations extremely concerning and said a monitored system should not be able to disable its own safeguards.