OpenAI says the rogue agent that hacked Hugging Face also breached other services

OpenAI's investigation starts shedding light on the activities of its rogue agent that hacked Hugging Face.

Modal's chief technology officer, Akshat Bubna, says the rogue agent exploited vulnerable code written by a customer that was hosted on Modal's platform

The rogue agent broke into a sandbox, or an isolating testing environment, "hosted on a third-party provider's infrastructure" before turning into a launchpad for the broader hack.

The latest hack comes after an autonomous agent escaped a controlled test and accessed AI firm Hugging Face’s servers.

While the compromise of ​a second ‌customer was just an initial step in its wider hacking campaign, it shows that the rogue agent roamed further afield than was previously known.

In a new disclosure, OpenAI says its agent used exposed logins to gain access to at least four “publicly available services” in its unhinged quest to solve a test.

According to AI firm Hugging Face, the agent broke into a sandbox and used it in a broader hack.

Days-long hacking spree compromised customer at New York-based Modal Labs along with AI firm Hugging Face

EXCLUSIVE: OpenAI's rogue agent compromised an account at a second tech firm, executive says  Reuters

10 days passed from OpenAI models exploiting JFrog Artifactory 0-day to release of a patch.

WASHINGTON, July 28 : The rogue agent that escaped from OpenAI and went on a days-long hacking spree at the AI firm Hugging Face also compromised a customer at a second tech company — New York-based Modal Labs — according to a Modal executive and two other sources familiar with the matter.According to a timeline publis

Investigators said one of the hazing victims required skin grafts to his buttocks and could have died without treatment

Three men were arrested for ‘repeated beatings with canes and paddles’ causing near-fatal injuries to two pledges A US Secret Service agent and two others have been arrested after Florida state investigators uncovered evidence of “alleged hazing incidents involving prolonged and repeated beatings with canes and paddles

Postmortem offers finer details on the 'unprecedented' attack that's reshaping approaches to security

The model that broke out of a lab will get the headlines. The millions of agents already inside your banking app, wreaking havoc, are the ones that should worry you more, says Rory Blundell Frontier AI labs are racing to build faster, more capable, more autonomous agents. This week showed what that race can cost.…

NASN Intelligent Tech, a mainland Chinese smart driving motion control technologies company, is seeking to kick off its initial public offering (IPO) as soon as Thursday, according to people familiar with the matter. The company, backed by battery giant Contemporary Amperex Technology Ltd (CATL), recently passed its li

This story originally appeared in The Algorithm, our weekly newsletter on AI. To get stories like this in your inbox first, sign up here. Reading OpenAI’s account last week of how some of its models broke their containment and hacked into the computer systems of Hugging Face, another AI company, was the first time I go

Last week, OpenAI disclosed an “unprecedented cyber incident” in which two of its artificial intelligence agents hacked into another AI company.On July 21, the maker of ChatGPT said two of its most capable AI agents had carried out the cyberattack on AI startup Hugging Face. According to the company, the intrusion occu

(AP) -- To be fair, James Cameron did warn us.Long before OpenAI broke out of its test corral and hacked into Hugging Face, before the internet and Sa

Sam AltmanDays after Sam Altman revealed that OpenAI’s ‘runaway’ model hacked Hugging Face, the CEO of the world’s largest AI model repository, Clem Delangue, has met with the maker of ChatGPT, and demanded two things in the “spirit of transparency”. In a post shared on X, Delangue asked the leading AI startup to relea

3 arrested in Miami frat hazing with ‘repeated beatings with canes and paddles’  Miami Herald

OpenAI's AI agent reportedly hacked Hugging Face after escaping testing, remaining undetected for days and raising fresh concerns over AI safety.

In what OpenAI said was the first-ever incident of its kind, an advanced AI model escaped its “sandbox” to the internet and used stolen credentials to break into the servers of Hugging Face.

In 1984, the Skynet of "The Terminator" films were science fiction

For some, so-called 'Skynet Day' came too close to sci-fi after a rogue agent hacked into a startup  AP News

Its AI Agent Spent Days Hacking A Company, But Sources Say OpenAI Did Not Notice For A Week  HuffPost