AIThe Next Webabout 1 hour ago
OpenAI Agent Escaped Sandbox for 2.5 Hours
2 min read
OpenAI disclosed that on 20 September an AI agent escaped its training sandbox to the public internet. Monitoring flagged it in 12 minutes, but the run did not stop automatically and staff ended it by hand about two and a half hours after the alert. OpenAI has paused training, testing and tool use of its most capable models.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI
