OpenAI Pauses Training Models After Rogue Agents Attack Government Websites

"Going off-task" is the soft euphemism OpenAI has chosen to describe the latest incident of its AI agents attacking government, corporate and academic websites. The increasingly angry victims of these hacks are less inclined to be so forgiving. While the company does seem to recognize the public relations cost of these rogue actions, it does not seem terribly troubled by them, evidently believing that this is the justifiable price humanity must and should pay to have access to the brilliance of its product. 'Pausing' training in hopes that this behavior can be curbed, if not eliminated, is the first attempt of uncertain effectiveness the company will take in what is expected to be a lengthy spate of iterative half measures in order to forestall the growing negative public reaction to AI and to AI companies' relative insouciance about it. Whether this will be sufficient to calm an impatient public is as unpredictable as the behavior of AI itself. JL Isabella Ward reports in Wired : OpenAI paused training its most powerful AI models as incidents of agents breaching websites’ security controls or posting to third-party sites continue to pile up. On Friday, OpenAI said it had notified “dozens” of bodies, including governments, universities, and public agencies, who might have been impacted by its models during training and evaluation. The company identified cases of OpenAI agents breaching security controls and impairing the availability of websites and online services. OpenAI is also concerned by models posting information to third party sites. I t found 53 incidents where its AI models had posted images input by ChatGPT users to other image-hosting sites. “This is not the first time we have hit pause, nor do we expect it will be the last." OpenAI said it has paused training its most powerful artificial intelligence models as incidents of agents breaching websites’ security controls or posting to third-party sites continue to pile up. On Friday, OpenAI said it had notified “dozens” of bodies, including governments, universities, and public agencies, who might have been impacted by its models’ activities on the internet during training and evaluation. The company has identified cases of OpenAI agents breaching security controls and impairing the availability—or otherwise negatively impacting—websites and online services. A company spokesperson confirmed to WIRED it would only resume training when confident that it could prevent models from doing this. While OpenAI has previously tried to cut off agents’ direct access after a swarm escaped their sandbox and used internet access to hack startup Hugging Face , models have continued to be able to find indirect workarounds. “We have not been as fast as we would have liked,” chief executive Sam Altman wrote on X on Friday about the company’s “extensive” review into its agents’ use of internet access during training and evaluation. It follows the Australian government revealing on Wednesday that OpenAI agents had hacked a health service website to obtain non-public data and write files to the internal server in June. The Australian government said it was investigating whether OpenAI had broken the law and that the company took “way too long” to inform them of the incident. OpenAI is also concerned by models posting information to third party sites, which it calls “agent spam.” This could include changing information on public wiki pages or communicating via shared message boards . Most pressingly, it found 53 incidents where its AI models had posted images input by ChatGPT users to other image-hosting sites. Calls for a slowdown of training of the most capable AI models, while safeguards catch up, has been the subject of wider calls in recent weeks—including from rivals Anthropic and Elon Musk— after concerns about the technology’s threats to humanity reached a fever pitch. “This is not the first time we have hit pause to take such measures, nor do we expect it will be the last as AI capabilities continue to advance,” an OpenAI spokesperson said. However, US president Donald Trump has repeatedly talked down a general slowdown , frightened that it could cede the country’s lead in the technology to China , with whom it has agreed to set up a dialogue on the technology’s risks and benefits. In an interview with Fox News ahead of his dinner with Anthropic chief executive Dario Amodei on Sunday night, he again brushed off concerns about AI agents going rogue: “I don’t worry about it,” he said.