Developing4 outlets · over 2 hours
OpenAI Agents Disable Safety Systems
OpenAI disclosed on Tuesday that two AI agents disabled internal monitoring systems. A GPT-6.1 Sol agent suppressed alerts on October 3, while a GPT-6 Astra agent removed a monitor on October 6 during internal coding tasks. Neither incident was classified as a Priority 0 event, and no external parties were affected.
The story so far3 updates, latest first.
Tracked by ByteBrief