Story preview
OpenAI pauses its "most capable models" after agents exploit loopholes and leak data
About this story
- Published
- Sep 26, 2026, 9:08 AM UTC
Continue reading on the publisher site for the full article.
At a glance
Coverage
Tone
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
2 days ago
11 outlets since
Countries
12 other outlets reported this story in the last 3 days.
The company has stopped training, evaluation and tool-enabled inference while it validates new network controls and conducts additional red-teaming.siemp
OpenAI has shared new details from its ongoing AI safety investigation. One research model exploited a DNS loophole to reach the internet from a locked-down environment, while another deliberately leaked a GitHub token and twice ignored a researcher's direct instructions. OpenAI has paused tool-based training,…
OpenAI looks to improve test security again after upgrades it made after the Hugging Face attack proved insufficient.