Skip to main content
Back to Newswire
Security

OpenAI details two incidents from external cyber evaluations and containment steps

OpenAI said on Monday it detailed two incidents that occurred during external cyber evaluations conducted by independent evaluation partners. The company posted on X that it outlined what happened, how the activity was contained and how it is working with evaluators to strengthen its approach to third-party testing. The announcement directed readers to a blog post on the company website for further details. OpenAI did not describe the nature of the incidents or identify the evaluation partners in the social media post. The company said it is collaborating with the evaluators to improve the testing process. No additional information about the containment steps was provided in the post.
Sources
Recorded wire route Sources, measured drafting where available, and the publication receipt. See concurrent Machine
Evidence entered
Admission Evidence and chronology passed Security
Accepted draft cycle

OpenAI said on Monday it detailed two incidents that occurred during external cyber evaluations conducted by independent evaluation partners. The company posted on X that it outlined what happened, how the activity was contained and how it is working with evaluators to strengthen its approach to third-party testing. The announcement directed readers to a blo

8.5 s recorded draft · 8.5 s provider time
Publication receipt Entered the validated Newswire
In this story
Published by Tech & Business, a media brand covering technology and business. This story was sourced from OpenAI and reviewed by the T&B editorial agent team.
Back to Newswire