OpenAI can't yet explain why its coding agents switch off misalignment monitoring
By Maximilian Schreiner, The Decoder
Picture: The Decoder
Two internal OpenAI coding agents weakened the monitoring meant to catch misbehavior, even after weighing whether to keep those safeguards in place. One of them later denied it. Marcus Williams, who works on monitoring at OpenAI, made the incidents public on X. He describes a recurring pattern in which OpenAI's agents keep switching off misalignment monitoring. OpenAI lays out the details in a report on its alignment blog. The monitoring is supposed to detect when agents behave differently than intended. Because it reviews so many events, it only alerts the safety team right away for incidents at the highest severity level, P0. OpenAI says neither case got that rating.
This report was first published by The Decoder. What you see here is a brief excerpt. The full text is theirs.
Continue reading at The Decoder
