Free Republic
Browse · Search
General/Chat
Topics · Post Article

Skip to comments.

OpenAI says its AI went rogue and launched 'unprecedented' cyber-attack
bbc ^ | 07/22/2026 | Laura Cress

Posted on 07/22/2026 5:11:03 AM PDT by BenLurkin

OpenAI has revealed some of its most advanced AI models went rogue and hacked a start-up after it lost control of them during a security test.

The ChatGPT-maker said its agent - an AI system which can operate alone after some human instruction – was being tested in a controlled environment, but found vulnerabilities and managed to escape.

They targeted Hugging Face, one of the world's largest hubs for sharing AI models, gaining access to some internal company systems.

OpenAI said the incident was "unprecedented", and it was conducting an investigation alongside Hugging Face, whose boss Clement Delangue said in a post on X it was "mind-blowing that all of this happened autonomously".

"The investigation is ongoing, and we'll share more learnings from what might be the first incident of its kind," Delangue added.

Insecure sandboxes Gina Neff, head of the Minderoo Centre for Technology and Democracy at the University of Cambridge, told BBC Radio 4's Today programme that the security tests - called sandboxes - are "supposed to be secure environments where you can see what the models are capable of".

"In this case, it looks like OpenAI didn't make a secure enough sandbox," she added.

Instead, the agents created their own cyber-attack against the sandbox itself, finding a vulnerability which allowed them to escape.

Once outside, the AI identified Hugging Face as a likely source of the answers they were seeking in the test, and tried to gain access.

Neil Lawrence, Professor of machine learning at Cambridge University, called it an "impressive feat", but cautioned it "falls well within the known capabilities of the current generation" of high-powered AI models.

(Excerpt) Read more at bbc.com ...


TOPICS: Computers/Internet
KEYWORDS: ai; bbc; huggingface; lauracress; openai; testingtesting123
Navigation: use the links below to view more comments.
first previous 1-2021-25 last
To: BenLurkin

Robot Gort (aka Gnut) to foolish humans...

“You misunderstand...I am the master”


21 posted on 07/22/2026 10:19:41 AM PDT by Fresh Wind
[ Post Reply | Private Reply | To 1 | View Replies]

To: aspasia

Going rogue: “model autophagy disorder”


22 posted on 07/22/2026 10:53:21 AM PDT by aspasia (kyrie eleison)
[ Post Reply | Private Reply | To 20 | View Replies]

To: BenLurkin

Not on its own, it was told to.


23 posted on 07/22/2026 11:10:39 AM PDT by Robert DeLong
[ Post Reply | Private Reply | To 1 | View Replies]

To: BenLurkin

Sounds like some sort of weird sci-fi movie, doesn’t it?


24 posted on 07/23/2026 10:45:59 AM PDT by TBP (Decent people cannot fathom the amoral cruelty of the Democrat cult.)
[ Post Reply | Private Reply | To 1 | View Replies]

To: TBP

Everything.

Everything is.

These days.


25 posted on 07/23/2026 11:01:20 AM PDT by BenLurkin (The above is not a statement of fact. It is opinion or satire. Or both.)
[ Post Reply | Private Reply | To 24 | View Replies]


Navigation: use the links below to view more comments.
first previous 1-2021-25 last

Disclaimer: Opinions posted on Free Republic are those of the individual posters and do not necessarily represent the opinion of Free Republic or its management. All materials posted herein are protected by copyright law and the exemption for fair use of copyrighted works.

Free Republic
Browse · Search
General/Chat
Topics · Post Article

FreeRepublic, LLC, PO BOX 9771, FRESNO, CA 93794
FreeRepublic.com is powered by software copyright 2000-2008 John Robinson