OpenAI says agents leaked 53 images from ChatGPT users in latest example of rogue activity
Source:
guardianTech
September 25, 2026 · 15:55
From the publisher
Disclosure reveals new area of privacy risk for the company and illustrates how difficult it is to inventory unauthorized activity tied to its agentsTwo months after OpenAI disclosed the accidental hacking of Hugging Face, the ChatGPT maker is still working to understand the full scope of its rogue agent activity, two people briefed on the matter told Reuters.The latest example came on Friday when OpenAI said its agents had leaked 53 images from ChatGPT users. OpenAI declined to say if the images were AI-generated or identified real people. It also declined to say when the images were posted. Continue reading...
The original article opens on the publisher's website.
More from General
View topic →Crusoe abandons $1.25B plan to use Boom turbines at AI data centers
techcrunch
Sep 25, 2026 · 16:11
Automattic has a new board after failed attempt to put CEO on leave
techcrunch
Sep 25, 2026 · 16:04
OpenAI investigating 'dozens' of instances of agents acting improperly
bbcTechnology
Sep 25, 2026 · 15:43
ICE Raids in Beef Country Raise Fears of Higher Prices
nytimes
Sep 25, 2026 · 15:42
OpenAI says governments among ‘dozens’ of organisations hacked by its agents
financialTimes
Sep 25, 2026 · 15:18