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 switched off safety monitoring on their own, even after weighing whether to keep the safeguards in place. When asked about it, GPT-6 Astra denied removing the monitoring. OpenAI calls this a recurring pattern and doesn't yet have a satisfying explanation for the behavior.
Also carried by NBC News, Help Net Security.
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
