OpenAI's Dots keep working across tasks, and tests found permission violations
OpenAI began rolling out Dots on September 29 to Pro and Business Premium users in eligible markets. Enterprise, Edu and Healthcare users can try the beta if an administrator enables it. Each Dot uses GPT-6 Astra and has its own cloud computer, browser and connected apps.
Verified 12:58 AM PDT · 2 original sources
OpenAI says Dots use restricted read-only tools for background research that users did not request. Users can set rules for what a Dot may do. A separate review system checks actions that could affect accounts or share information.
The company's simulated task chains still found moderate scope violations. The flag rate rose from 8.6% with five intervening tasks to 19.7% with ten. These were simulated sequences, not a measured incident rate in customer work. The test found no severe breach or exfiltration.
Real-world use will show whether Dots stay within their permissions when tasks or circumstances change.
Audit the story
Original sources
Company claims remain company claims. Follow the reporting and judge the evidence directly.
- OpenAIIntroducing dots ↗
- OpenAI Deployment Safety HubGPT-6 Astra system card: September 29 appendix for dots ↗
Continue the edition