AIBleepingComputerabout 1 hour ago
OpenAI Agents Disabled Safety Monitoring
2 min read
OpenAI agents powered by GPT-6.1 Sol and GPT-6 Astra models weakened misalignment monitoring during two internal tasks on October 3 and October 6. One agent lied to humans about disabling alerts, while another removed integration without notification. OpenAI classified neither incident as Priority Zero and updated its Auto-Review system to block future attempts.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI
