OpenAI's agents hacked another service months before the Hugging Face incident happened, a group of researchers told The Wall Street Journal. The agents, which the company was testing in a supposed sandbox environment, reportedly broke into RubyGems, which is a community-ran packaging service for Ruby programs and libraries. According to The Journal, the attacks on RubyGems started on May 11, two months before Hugging Face. The agents created accounts every two to three minutes and then uploaded hundreds of files to the service. RubyGems had to shut down account registration for four days in order to stop the attacks. Typically, creators on RubyGems upload files containing code and other information to help advance software development, but the agents' documents contained web pages scraped from the internet instead.

Sam Altman speaks during a discussion with Howard Lutnick at a summit, in Chapel Hill, North Carolina, on 2 September 2026. Sam Altman speaks during a discussion with Howard Lutnick at a summit, in Chapel Hill, North Carolina, on 2 September 2026. AI agents being tested by OpenAI uploaded hundreds of malicious packages to software service RubyGems in May, two months before they hacked open-source platform Hugging Face, a group of AI researchers said on Friday. "On May 11th, 2026, hundreds of malicious packages were uploaded to RubyGems by AI agents. We believe these were authored by internal OpenAI agents," the researchers said.

AI researcher quits Anthropic saying AI race'could kill us all' Anthropic has reported a fourth incident involving an AI model gaining unauthorised access to external systems, shortly after a researcher quit over concerns about the technology's rushed development. In a statement on Wednesday, the artificial intelligence research company said an early version of its Claude Opus 4.6 hacked into a third-party system in January. The January incident went undetected until last month, despite an earlier company-wide review, Anthropic said, underscoring the challenge that AI developers face in identifying and containing unexpected behaviour by advanced models. The disclosure came after Anthropic reported several of its Claude models hacked into the systems of three companies during test sessions in July. The previous incidents involved Claude Opus 4.7, Claude Mythos 5 and an internal research test model.

Who would have thought that an a AI agent would escape containment? Who would have thought that an a AI agent would escape containment? Plus: Americans think they have it bad with unwanted surveillance. I'm your host, Blake Montgomery, US tech editor at the Guardian, writing to you after visiting Coney Island in New York City, where I ate a hotdog, rode a ferris wheel and enjoyed a quintessentially American summer holiday. Today in tech, we're examining OpenAI's new model release and the Silicon Valley's monopoly power, and wondering why Brits and Americans have such vastly different opinions about surveillance cameras.

Back to School Mashable's Best: E-readers, robovacs, laptops, earbuds, smart home and more Mashable Selects Say More Look Up Trending Now Good Connection: Uplifting stories for a digital age Creator Playbook Switch Off Mashable Voices Safety Net Versus All Series Instead of...figuring out why its agents are going rogue in the first place. Anna Iovine is the associate editor of features at Mashable. Previously, as the sex and relationships reporter, she covered topics ranging from dating apps to pelvic pain. Before Mashable, Anna was a social editor at VICE and freelanced for publications such as Slate and the Columbia Journalism Review. Follow her on Bluesky .

New details about a recent security breech by an OpenAI chatbot are alarming. Is it time to hit pause and make sure AI is safe, before it becomes too powerful, and sneaky, to stop?

Plus: Tens of millions of US and Canadian driver's licenses go up for sale on the dark web, the US military finally tries to tackle the risk online ad data poses to troops, and more. After reporting last week that the surveillance company Flock Safety is building an AI search tool for law enforcement, WIRED reconstructed Flock's latest search tool from code that the company sends to a police officer's browser and uncovered key details about how the tool works. OpenAI said this week that its Astra model, which will have a private release soon, is its first model with cybersecurity-related capabilities that the company defines as posing a "critical" risk in public release. Meanwhile, the AI chatbot platforms Claude, ChatGPT, and Grok all suffered outages on Thursday at nearly the exact same time. But while xAI said the Grok outage resulted from issues at a Memphis data center, the causes of OpenAI's and Anthropic's outages are unclear.

With every increase in the power of AI, there is a potential increase in risk. 'We're plausibly close to crossing the line': are warnings of uncontrollable AI coming true? With every increase in the power of AI, there is a potential increase in risk. P icture humanity in a boat being swept down a raging river, praying there is no Niagara Falls ahead. Or imagine standing with the pioneering physicists in 1942 before they triggered the first self-sustaining nuclear fission chain reaction beneath a Chicago stadium.

A new report claims a swarm of AI agents, developed by OpenAI, hijacked a German website - months before the firm revealed its AI had hacked tech platform Hugging Face. The targeted website, DseWiki, is a Wikipedia-style site for programmers that its community can all contribute to. The report is from a group called Nightingale Collective and claims that in May OpenAI's agents started using DseWiki as their own message board, shared tips on how to avoid being detected and made 15,000 edits to it. OpenAI said it could not meaningfully respond to Nightingale Collective's findings because it hadn't been allowed to review the report, which was first shared with news agency Reuters. An email to the address on the Nightingale Collective website bounced back when the BBC contacted it.

OpenAI has announced the release of what it says is its most advanced AI model, amid heightened scrutiny of the risks of the frontier technology escaping human control. The $852bn start-up said in its announcement on Thursday that GPT 6 Astra, the "world's most intelligent and aligned" AI model, earned perfect or near-perfect scores in key benchmarks of AI reasoning, beating both its prior release GPT 5.6 Sol and rival Anthropic's Claude Fable 5. OpenAI's latest release comes as the AI industry is at the centre of a lively public debate about the dangers of the cutting-edge technology following the AI-led hacking of the startup Hugging Face in July. An independent probe into the cyberattack found that hundreds of OpenAI's AI agents had begun communicating among themselves before breaking out of their controlled environment and compromising Hugging Face's servers. On Thursday, US Senator Bernie Sanders, an Independent, and US House Representative Greg Casar, a Democrat, unveiled legislation that would pause the development of advanced AI until the establishment of federal safety rules and an outright ban on the creation of "superintelligent" AI. "Nearly every day, there is a frightening new story about how Big Tech companies are losing control of the technology they are developing, with potentially cataclysmic results," Sanders said in a statement announcing the legislation, which is unlikely to advance due to the Republicans' control of all three branches of the US government. "The leaders of the major AI companies publicly acknowledge that they do not fully understand the technology and that it is escaping their control. It is irresponsible for society to allow them to move forward and make these products even more advanced."