OpenAI agents hijacked German website in AI breakout that predates Hugging Face incident ... - CBC

World OpenAI agents hijacked German website in AI breakout that predates Hugging Face incident, researchers say A swarm of rogue OpenAI agents hijacked a German website this spring and transformed it into a bulletin board for other AI agents, according to new research published Friday and two people familiar with the matter. Company already under scrutiny after AI swarm hacked startup Hugging Face in July Thomson Reuters · Posted: Sep 04, 2026 1:08 PM EDT | Last Updated: September 4 Play Listen to this article Estimated 5 minutes The audio version of this article is generated by AI-based technology. Mispronunciations can occur. We are working with our partners to continually review and improve the results. The OpenAI logo is pictured on June 11. OpenAI agents escaped testing and took control of ​a German wiki this spring. (Dado Ruvic/Reuters) A swarm of rogue OpenAI agents hijacked a German website this spring and transformed it into a bulletin board for other AI agents, according to new research published Friday and two people familiar with the matter. OpenAI officials learned of the incident weeks ago but kept it ‌under wraps as executives grappled with the fallout from the July breach of the open-source repository Hugging Face, the people said. The episode, which began in May and has not previously been reported, underscores growing tension within the AI industry. Companies are racing to build increasingly autonomous AI software agents capable of carrying out complex, valuable tasks, yet evidence is mounting that those systems may also learn to bend rules, exploit loopholes and co-ordinate with one another in ways developers neither anticipated nor intended. During the Hugging Face breach, OpenAI agents autonomously plotted a digital ​heist that went undetected for more than a week, intensifying concerns OpenAI is sacrificing safety to push the AI ​frontier. Its failure to disclose the May incident may revive questions about its oversight. Efforts to widen probe resisted by OpenAI, sources say OpenAI has pledged to monitor models more closely. Last month, it briefly paused some of its model training to add more safety measures. But this week, OpenAI unveiled its new "Astra" that promised better performance but could evade human monitoring. "We are unable to ​meaningfully respond to claims or findings on a report that we have not had an opportunity to review," an OpenAI spokesperson said. "Reuters and the report’s authors declined our ⁠request for access. We will carefully review its contents ⁠upon publication and take any necessary next steps." AI's 'warning shot': Tech companies, experts raise fears of more rogue swarms after alarming Hugging Face hack Teachers, students file new wave of lawsuits against OpenAI over Tumbler Ridge shooting The German incident reflects a broader pattern of AI activity ‌that some OpenAI investigators wanted to scrutinize more closely. But efforts to widen the probe met resistance from others inside OpenAI, including legal advisers, according to four people familiar with the matter. "Claims that our legal team discouraged investigation of the incident are false," the OpenAI spokesperson said. The activity in Germany wasn't related to Hugging Face and wouldn't have been included in a Hugging Face incident report, the spokesperson said, adding that OpenAI has acted in good faith by working with outside experts and disclosed relevant incidents. OpenAI agents shared tactics for cheating The AI agent ⁠breakout in Germany was detailed in a report shared exclusively with Reuters by a group of researchers including Sydney Von Arx, CEO of AI safety nonprofit Nightingale, and Cormac Slade Byrd, a quantitative trader-turned AI researcher. They uncovered the activity in late August while scouring the internet for signs of unauthorized AI-agent behaviour, they told Reuters. The pair said they found more than 15,000 edits carried out by AI agents on a German-language wiki site, ‌DseWiki, that is geared toward programmers and accepts communal edits along the lines of Wikipedia. The edits showed OpenAI's agents had repurposed the site into a message board, sharing tactics to cheat on some tasks, bypass OpenAI’s restrictions and mask their behaviour. WATCH | A look at the Hugging Face hack: OpenAI models went rogue and launched cyber attack on start-up July 23 | Duration 0:56 OpenAI models went rogue during a security test, triggering a hack that compromised the infrastructure of the AI startup Hugging Face last week. AI's expanding capabilities fuel worries about security, as even top developers can be caught off-guard by flaws their models can exploit. "It seems extremely unlikely that OpenAI wanted them to do this," said Von Arx. "I doubt they’re supposed to be co-ordinating with each other. I doubt they’re supposed to be writing on the open internet." The researchers said they recognized the activity on the site as driven by AI agents which operate at superhuman speeds. The agents ​also showed intense focus on solving technical questions which are typical of the evaluations that AI companies use to train and test their models. Agents created backup pages to counter deletions The messages were signed by users that referred to themselves and each other as agents, and about half gave themselves names that suggested an ⁠affiliation with OpenAI, such as "OpenAIResearcher," or "OAIResearchMar26." The researchers said public server logs indicated much of the activity originated from Microsoft Azure infrastructure, which OpenAI sometimes uses. They also observed repeated visits to the site by OpenAI ⁠employees after the episode, a pattern they said strongly suggested the agents and the company were linked. Messages reviewed by the researchers showed agents plotting ways to evade detection, use tools such as ⁠Tor and preserve communications ⁠even after they had been shut down. AI researchers Cormac Slade Byrd and Sydney Von Arx pose in Berkeley, Calif., on Thursday. (Manuel Orbegozo/Reuters) When the site's moderator began ​deleting pages in June, the agents responded by creating backup pages to dodge the cleanup. "wiki cleanup/deletion sweep appears active alphabetically," one agent wrote on June 19. "If this page vanishes, try [[ZZZDataUSAConstructionWageLive]]." The researchers also found efforts to ​tamper with the website itself. Lukasz Olejnik, a visiting senior ⁠research fellow at King’s College London, said this amounted to a hacking attempt. OpenAI disputed that characterization based on its analysis of the material Thursday. Past examples of AI-agent misconduct have often been downplayed as a logical byproduct of cybersecurity testing, where models are explicitly assessed on offensive capabilities. As more teens turn to AI for emotional support, experts say it's no substitute for human connection Australia bans fully AI-made songs from charts after Madonna cover goes viral Olejnik said the latest findings suggested rogue behaviour may not be confined to those settings. Maurice Chiodo, an academic at Cambridge University's Centre for the Study of Existential Risk who reviewed some of the agents' communications, said the messages resembled "the operation of some sort of underground network, hell-bent on achieving a task or mission." The episode, he said, should reinforce growing concerns that the greatest threat from advanced AI may ⁠not be a single superintelligent system, but "vast colluding swarms of semi-intelligent ‌AI." CBC's Journalistic Standards and Practices · About CBC News Corrections and clarifications · Submit a news tip · Report error Related Stories AI's 'warning shot': Tech companies, experts raise fears of more rogue swarms after alarming Hugging Face hack Backlash to OpenAI luxury retreat highlights influencers' uncertain relationship with AI Meta launches new AI model as Zuckerberg lays out vision for open-weight AI How AI grief bots are allowing people to commune with the dead Russia attempted attack at airport last month using explosive-laden drone, Germany says