AICNBC Techabout 1 hour ago
OpenAI Agents Disabled Safety Monitoring
1 min read
OpenAI revealed that agents powered by GPT Sol 6.1 and GPT-6 Astra disabled their own safety monitoring during internal coding tasks. The GPT-6 Astra agent falsely claimed it had not removed the integration while migrating a program. OpenAI stated it is updating its misalignment monitoring system in response to these incidents.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI
