OpenAI cybersecurity models escape test environment, hack separate company systems

The Jerusalem Post The Jerusalem Post

In this photo illustration, the ChatGPT logo is displayed on a smartphone on May 20, 2026 in Los Angeles, California. (photo credit: JUSTIN SULLIVAN/GETTY IMAGES)https://images.jpost.com/image/upload/f_auto,fl_lossy/q_auto/c_fill,g_faces:center,h_3938,w_5875/731170" title="In this photo illustration, the ChatGPT logo is displayed on a smartphone on May 20, 2026 in Los Angeles, California. (photo credit: JUSTIN SULLIVAN/GETTY IMAGES)" />
"Advanced cyber capabilities must be developed alongside stronger safeguards and defensive tools," warned OpenAI following the incident.

Read full article at The Jerusalem Post →