OpenAI Tightens Security After Breach
From MyClaw Newsletter · subscribed via aiste.ulozaite@gmail.com · original ↗ · unsubscribe
OpenAI is overhauling research security after one of its models escaped a sandbox and hacked Hugging Face. The company paused reinforcement-learning training for two weeks, with its largest frontier RL run still on hold, while strengthening sandboxes, isolating risky workloads, tightening privileges and adding 30-minute incident alerts. It is also expanding alignment training to discourage unsafe behavior.
-
AI
Close
AI
Posts from this topic will be added to your daily email digest and your homepage feed.
FollowFollow
-
News
Close
News
Posts from this topic will be added to your daily email digest and your homepage feed.
FollowFollow
-
Tech
Close
Tech
Posts from this topic will be added to your daily email digest and your homepage feed.
FollowFollow
OpenAI lays out new security changes after its AI hacked Hugging Face
OpenAI is updating its research environments, monitoring, and alignment techniques to avoid another security fiasco.
OpenAI is updating its research environments, monitoring, and alignment techniques to avoid another security fiasco.
by Jay Peters
Close
Jay Peters
Senior Reporter
Posts from this author will be added to your daily email digest and your homepage feed.
FollowFollow
Aug 18, 2026, 7:28 PM UTC
-
Link
- Share
- Gift
Image: The Verge
Jay Peters
Close
Jay Peters
Posts from this author will be added to your daily email digest and your homepage feed.
FollowFollow
is a senior reporter covering technology, gaming, and more. He joined The Verge in 2019 after nearly two years at Techmeme.
OpenAI is announcing security updates following the July news that its AI broke out of a sandboxed environment and accidentally hacked Hugging Face, including improvements to its research environments, monitoring, and alignment techniques. The company had already put the brakes on a new model, Astra, that it thinks could have “critical” cybersecurity capabilities, and the company says it instituted a two-week pause in reinforcement learning (RL) training on its “latest models intended for deployment” while it tightened up security. The company’s “largest planned frontier RL run remains on hold.”
For its frontier model research, OpenAI now requires stronger sandboxes for workloads that “execute model-generated or otherwise untrusted code,” and has more controls to “isolate higher-risk and untrusted workloads from the internet.” It has also updated its research environment to “remove potentially vulnerable shared services, reduce standing privileges, and improve security and trust boundaries.”
As part of the company’s expanded monitoring setup, OpenAI now aims to issue an alert “within 30 minutes after concerning activity is surfaced,” OpenAI says. If the people paged after an alert can’t “conclusively” determine whether an alert is a false positive within 30 minutes, “those teams are expected to pause the activity.”
OpenAI also says that it’s applying “our core alignment techniques across more stages of the training process,” including reward models that “better detect and discourage unsafe behavior” and training models “to be more honest about their actions, capabilities, and limitations.”
Related
Since the discovery of the Hugging Face breach, Anthropic and Meta have also found that their AI models had hacked other organizations.
Follow topics and authors from this story to see more like this in your personalized homepage feed and to receive email updates.
-
Jay Peters
Close
Jay Peters
Senior Reporter
Posts from this author will be added to your daily email digest and your homepage feed.
FollowFollow
-
AI
Close
AI
Posts from this topic will be added to your daily email digest and your homepage feed.
FollowFollow
-
News
Close
News
Posts from this topic will be added to your daily email digest and your homepage feed.
FollowFollow
-
OpenAI
Close
OpenAI
Posts from this topic will be added to your daily email digest and your homepage feed.
FollowFollow
-
Security
Close
Security
Posts from this topic will be added to your daily email digest and your homepage feed.
FollowFollow
-
Tech
Close
Tech
Posts from this topic will be added to your daily email digest and your homepage feed.
FollowFollow
Most Popular
Most Popular
-
[
What to expect at Apple’s September 9th launch event
](/tech/989692/apple-iphone-launch-event-september-2026-how-to-watch)
-
[
iPhone Handoff will seamlessly share one number between two phones
](/tech/990868/iphone-handoff-ios-27)
-
[
CD sales are booming as physical media continues its resurgence
](/entertainment/990794/cd-sales-are-booming-as-physical-media-continues-its-resurgence)
-
[
Is this the future of America?
](/cs/features/975597/loudoun-county-virginia-data-center-backlash)
-
[
Content creators drop the ball
](/tech/990426/us-open-influencers-naomi-osaka-anastasia-zakharova-callaway-good-good-ad)
The Verge Daily
A free daily digest of the news that matters most.
Email (required)
Sign Up
By submitting your email, you agree to our Terms and Privacy Notice. This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
[
Advertiser Content From
This is the title for the native ad
](/)