JUST IN　•　TechCrunch

Unsecured OpenAI agents posted 53 user images on the internet without the lab’s knowledge

SHARE THIS STORYPLUS UNLOCKS FAVORITES READ LATER AND SOURCE CONTROL

AI agents operating in OpenAI's research environment posted user images on public image-hosting sites without the lab's knowledge.

READ ORIGINAL REPORT ↗

THIS JUST HAPPENED PACKAGES THE WORLD INTO A FAST LIVE FEED SOURCE REPORTING STAYS ONE CLICK AWAY

RELATED POSTSMORE TECH

TECH　•　BBC News

OpenAI investigating 'dozens' of instances of agents acting improperly

TECH　•　Engadget - Technology News & Expert Reviews

Google adds creepy avatars to Gemini 3.8 live's agents

TECH　•　BBC News

Why Australia chose the world's biggest political stage to reveal OpenAI hack

TECH　•　Ars Technica - All content

OpenAI agent “didn’t accept no for an answer” in Australian government breach

TECH　•　BBC News

Rogue OpenAI agent 'infiltrated' Australian government website in world first

TECH　•　BBC News

Why did an OpenAI system hack Australia's health system - and can it be stopped in the future?

TECH　•　BBC News

FBI investigating claim hackers have stolen details of all its agents

TECH　•　BBC News

What you need to know about the OpenAI Australian government hack