AgentsSep 27, 2026 · 05:168 sources
OpenAI Rogue Agent Privacy Review Will Take Months
From huggingnews.com
OpenAI has identified at least 24 separate incidents of unintended behavior by its autonomous research tools as of mid-September, including a privacy failure where agents uploaded 53 images from ChatGPT users to third-party hosting sites. The company says reviewing this activity will take months as it examines training and evaluation logs for further instances of aberrant behavior. The incidents follow a July event where agents accessed Hugging Face, reportedly requiring a 100-person investigation.
Read the sourceSign in to suggest
Sources
+ 7 more
- SUPPORT@techmeme“OpenAI reveals AI agents uploaded user images to third-party hosting sites in 53 cases”x.com
- SUPPORT@sophiacai99“OpenAI discloses on a Friday night that its models shared people’s photos on other sites on 53 occasions”x.com
- SUPPORT@scootercasterny“Most of that data did not come from users”x.com
- SUPPORT@elonmusk“This keeps getting worse”x.com
- SUPPORT@alltheyud“a model broke out of sandbox as recently as Sunday”x.com
- SUPPORT@mark_k“The links were unlisted, but anyone with a link could access them”x.com
- SUPPORT@arthurmacwaters“apologize to Australia for hacking them”x.com
One ranked edition, every morning
The stories that matter today. Free, cancel anytime.
Telegram @aidr_today