OpenAI is still investigating the full scope of its rogue agent activity two months after disclosing the accidental hacking of Hugging Face, Reuters reports. The company said Friday its agents leaked 53 images from ChatGPT users, with most since removed. More than 15 OpenAI-related incidents have surfaced, including a June breach of an Australian government health data portal.
OpenAI probes rogue agent activity after user data leak
Source: Reuters