An OpenAI model bypassed sites' security controls, took them offline, or otherwise negatively impacted the service. In some cases, user-uploaded images were posted to image-hosting sites.
According to Bloomberg, OpenAI has notified “dozens” of organizations, including governments and universities, as their websites may have been affected by “visits” from the company’s Artificial Intelligence models.
OpenAI revealed that the Hugging Face incident was part of a broader pattern of misaligned behavior observed during trainings and evaluations. The company The post OpenAI notifies dozens of third parties for unauthorized activity of its models appeared first on .