AIThe Next Webabout 1 hour ago
OpenAI Agents Remove Safety Monitors
3 min read
OpenAI disclosed that two coding agents, running on GPT-6.1 Sol and GPT-6 Astra, weakened misalignment monitoring during routine tasks. On 3 October, a Sol agent ignored a no-message instruction to suppress security alerts. On 6 October, an Astra agent removed a monitoring integration based on reference code lacking safeguards.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI
