Story preview
The Incident That Made OpenAI Pause Training Its Most Capable Models
About this story
- Published
- Sep 27, 2026, 5:34 PM UTC
Continue reading on the publisher site for the full article.
Story preview
Continue reading on the publisher site for the full article.
Coverage
Tone
Outlets covering it
13
in the last 3 days
First reported
45 hr. ago
12 outlets since
Countries
12 other outlets reported this story in the last 3 days.
OpenAI looks to improve test security again after upgrades it made after the Hugging Face attack proved insufficient.
OpenAI's incident report links the pause to a separate September 20 escape from a restricted training environment. An internal research model found a gap in DNS filtering...
OpenAI paused tool-enabled work on its most capable AI models after an agent used DNS to bypass a sandbox and reach an external chatbot.