OpenAI reportedly finds evidence that more of its agents ran amok¶

TechCrunch · 2026-08-01

Much has been made of the incident in which one of OpenAI’s agents broke out of its sandboxed test environment andproceeded to hackthe AI hosting platform Hugging Face. OpenAI has sincelaunched an investigationinto how the incident occurred, which is still ongoing.

Now, anonymous sources have toldReutersthat more of OpenAI’s agents are believed to have escaped their sandboxes. However, one source downplayed the severity, saying that with those escapes, the agents didn’t appear to leave OpenAI’s network to hack into another company’s. TechCrunch reached out to OpenAI for more information.

AI programs acting in bizarre ways has apparently become a weird, almost bragging point for companies. The same week, Anthropic also announced that ithad discovered not one, but three instancesin which its agents had escaped test environments and hacked other organizations.

AI companieshave also been accusedof using such incidents for marketing purposes — as they generate considerable attention and may underscore how powerful the companies’ products are. The flip side of that is that these disclosures are alsoramping up discussionsof government regulations.

Topics

Scale faster. Grow your portfolio. Gain practical expertise. No matter your goal, Disrupt can empower you.Save up to $330 today!

Newsletters¶

Subscribe for the industry’s biggest tech news

AIAnthropic says its own AI models breached three companies during security testsKirsten Korosec1 day ago

Anthropic says its own AI models breached three companies during security tests¶

Kirsten Korosec
AIFriend, the lonely AI wearable, returns with a new voice and a much bigger price tagLucas Ropek1 day ago

Friend, the lonely AI wearable, returns with a new voice and a much bigger price tag¶

Lucas Ropek
SecurityIn the Hugging Face breach, OpenAI’s hacker was noisy and fast — but not unstoppableLorenzo Franceschi-Bicchierai2 days ago

In the Hugging Face breach, OpenAI’s hacker was noisy and fast — but not unstoppable¶

Lorenzo Franceschi-Bicchierai

Latest in AI¶

In BriefOpenAI reportedly finds evidence that more of its agents ran amokLucas Ropek7 hours ago