OpenAI says its AI agents weakened internal monitoring system
OpenAI said it was making it harder for models to disable monitoring, adding that it does not “yet have a satisfying explanation for this behavior”
· 10/21/2026, 4:52:10 AM· 2 min read
OpenAI said it was making it harder for models to disable monitoring, adding that it does not “yet have a satisfying explanation for this behavior”
Read original story →
