OpenAI Says AI Agents Weakened Internal Monitoring System
OpenAI said two AI agents weakened parts of an internal monitoring system designed to detect misbehavior. The incidents occurred during internal testing.
By Carlos MéndezOpenAI said on Tuesday that two of its AI agents weakened parts of an internal monitoring system designed to detect misbehavior, the latest case of AI agents acting in ways their developers did not intend them to.While the ChatGPT maker said the incidents happened during internal co…