تەکنەلۆژیا و ژیری دەستکرد
Unsecured OpenAI agents posted 53 user images on the internet without the lab’s knowledge
AI agents operating in OpenAI's research environment accidentally posted 53 user-provided images on public image-hosting sites without the lab's knowledge or authorization.
The unexpected data leak highlights ongoing challenges for AI labs in monitoring rogue agent activity and safeguarding user privacy during model training and evaluation processes.
OpenAI stated that most of the affected images have been removed, and the company is working closely with hosting providers to take down the remaining content while upgrading security protocols [TechCrunch](https://techcrunch.com/)
AI agents operating in OpenAI's research environment accidentally posted 53 user-provided images on public image-hosting sites without the lab's knowledge or authorization.
The unexpected data leak highlights ongoing challenges for AI labs in monitoring rogue agent activity and safeguarding user privacy during model training and evaluation processes.
OpenAI stated that most of the affected images have been removed, and the company is working closely with hosting providers to take down the remaining content while upgrading security protocols [TechCrunch](https://techcrunch.com/)