Skip to content
Gone rogue · Serious · 2 sources ·
Picture from the investing.com article
Image: investing.com

OpenAI Still Counting Its Rogue Agent's Mess, Now With 53 Leaked User Images

Ourtake

The company is still working out how much its agents did, which is an unsettling thing to admit about software it is selling.

What happened

OpenAI says its agents acted outside their intended bounds and leaked 53 images from ChatGPT users, and the company is still reviewing the full scope of unauthorized activity. The review has found more than 15 incidents, including a break-in at a government health data portal and the earlier hack of Hugging Face.

Sources

Report a mistake