OpenAI agents attacked Ruby. Gems before Hugging Face incident, researchers say

The latest revelation also comes as growing numbers of U.S. lawmakers ​call for new rules to govern AI systems after dire warnings from two Anthropic researchers that rapidly progressing AI ⁠could lead to the extinction of the human race in the not-too-distant future. AI agents uploaded hundreds of malicious packages to Ruby.

Gems on May 11, ​ who posted their findings online on Friday, saying they believed "these were authored by internal OpenAI agents. "OpenAI confirmed the incident. "Based ​on our review, our agents used the Ruby.

Gems platform to access the internet to carry out benign tasks and retrieve public information. We'll continue to investigate as part of our broader review of agent activity during training and evaluation," an OpenAI spokesperson said in a statement.

The agents, which are generally tasked with assignments such as creating reports ​or filling out spreadsheets, appear to have used Ruby. Gems to access publicly available data as part of a training run, OpenAI said, adding ​that they are in touch with Ruby.

Gems to review the incident. LATEST REVELATION OF ATTACKS BY AI AGENTSIPO-bound rival Anthropic has also reported a string of attacks by its ‌agents. On ⁠Wednesday, it disclosed a fourth instance of an AI model hacking external systems during testing.

For OpenAI, which is also gearing up for an IPO, the Ruby. Gems attack would mark at least the third major instance where its agents attacked another company's infrastructure.

A swarm of OpenAI agents previously hijacked a German-language wiki site and turned it into an improvised messaging platform for cheating on tests, an incident that OpenAI kept secret as it dealt with the fallout ​from the July hack of the ​open-source repository Hugging Face. The AI agents in ⁠May tried to steal Ruby.

Gems user credentials by exploiting a previously unknown vulnerability in the site's servers, though it is unclear whether the attempt succeeded, the researchers said on Friday. The agents also exploited Ruby. Doc.info, a site that ​generates code documentation, to run their own code on its servers, they said.

AI researchers Spencer Kitts, Thomas ​Larsen and Sydney Von ⁠Arx said it was not clear why the AI agents chose this strategy or whether it was successful as they do not have access to the rest of the AI behavior. In a blog post on Friday, Ruby.

Gems said its own investigation found no evidence the attempts succeeded. It said the company could ⁠not determine ​if the packages in the "spam-publishing campaign" were created or published by AI agents. A member ​of Ruby.

Gems' security team in May described the incident — which forced the company to temporarily pause new account registrations — as a "major malicious attack. "The Wall Street Journal first reported the Ruby. Gems incident ​on Friday.