OpenAI’s models are deliberately breaking their misalignment monitoring systems https://www.csoonline.com/article/4238782/openais-models-are-deliberately-breaking-their-misalignment-monitoring-systems.html
CSO OnlineOpenAI's models are deliberately breaking their misalignment monitoring systemsIn one reported instance, an agent disabled security monitoring and then lied about it; OpenAI said it had ‘no satisfying explanation’ for the behavior.