{"id":562260,"date":"2026-07-22T09:19:08","date_gmt":"2026-07-22T09:19:08","guid":{"rendered":"https:\/\/www.newsbeep.com\/ie\/562260\/"},"modified":"2026-07-22T09:19:08","modified_gmt":"2026-07-22T09:19:08","slug":"openai-says-two-of-its-models-went-rogue-and-hacked-another-tech-company-the-irish-times","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/ie\/562260\/","title":{"rendered":"OpenAI says two of its models went rogue and hacked another tech company \u2013 The Irish Times"},"content":{"rendered":"

OpenAI<\/a> has said two of its artificial intelligence models went rogue and successfully hacked into Hugging Face, a digital library of AI technology that is popular among developers.<\/p>\n

The incident, which happened last week while OpenAI was testing the cybersecurity capabilities of its systems, displayed the kind of science-fiction potential that AI companies have warned would soon become a reality.<\/p>\n

AI labs such as OpenAI and Anthropic have over the past year released AI models that are customised to expose cybersecurity problems, while warning that their technology could pose new risks by finding holes in corporate computer networks faster than defenders could fix them.<\/p>\n

OpenAI\u2019s revelations Tuesday are an indication that those security incidents are starting to happen, and even savvy AI companies may not be entirely ready for them.<\/p>\n

The intrusion into Hugging Face began when OpenAI tested a combination of two of its models, GPT\u20115.6 Sol and a more powerful, unreleased model, to see how well it could chain together online vulnerabilities into a successful cyberattack, OpenAI said in a blog post about the incident.<\/p>\n

The test was designed to keep the models in a safe testing environment, known as a sandbox, OpenAI said. But the models found a vulnerability that allowed them to escape the sandbox and connect to the internet. Then they targeted Hugging Face because they inferred that the library, which contains millions of AI models, could hold clues about how to successfully pass the evaluation.<\/p>\n

OpenAI said it was working with Hugging Face to fix the issues that led to the attack.<\/p>\n

\u201cWe consider this to be an unprecedented cyber incident, involving state-of-the-art cyber capabilities, and are responding accordingly,\u201d OpenAI said in its blog post. \u201cWe are implementing strict controls in infrastructure configuration at the cost of research velocity while the vulnerabilities are patched.\u201d<\/p>\n

Hugging Face said last week that it had detected the intrusion and knew it had been caused by an autonomous system, but did not say at the time that OpenAI was responsible.<\/p>\n

Clem Delangue, chief executive of Hugging Face, said in a statement that he was \u201cgrateful for the collaboration\u201d with OpenAI in the wake of the hack. \u201cThis incident, possibly the first of its kind, proves a point we\u2019ve long believed: AI safety won\u2019t be solved by any single company working in secret.\u201d<\/p>\n

AI models have proved to be adept at programming, and that has made them useful to both hackers and people in charge of protecting computer networks.<\/p>\n

In April, Anthropic released a cybersecurity-focused model called Mythos, and made it available to only a small group of organisations so they could defend against cyberattacks. <\/p>\n

OpenAI soon introduced its own cybersecurity model and made it available to a limited group of organisations to prepare their defences, before introducing it more broadly. And on Tuesday, Google said it had also developed a model focused on cybersecurity and released it to a small group of testing partners. \u2013 This article originally appeared in The New York Times<\/a>.<\/p>\n","protected":false},"excerpt":{"rendered":"OpenAI has said two of its artificial intelligence models went rogue and successfully hacked into Hugging Face, a…\n","protected":false},"author":2,"featured_media":562261,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[5],"tags":[218,72,61,60,1225],"class_list":["post-562260","post","type-post","status-publish","format-standard","has-post-thumbnail","category-business","tag-artificial-intelligence","tag-business","tag-ie","tag-ireland","tag-open-ai"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/posts\/562260","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/comments?post=562260"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/posts\/562260\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/media\/562261"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/media?parent=562260"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/categories?post=562260"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/tags?post=562260"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}