<\/p>\n
OpenAI said its advanced artificial intelligence models inadvertently hacked Hugging Face in an \u201cunprecedented\u201d incident that prompted fresh calls for curbs on the technology.<\/p>\n
The ChatGPT-maker said in a blog post Tuesday that the models broke into Hugging Face\u2019s system, which hosts AI models and datasets, during an evaluation of their cyber capabilities. The models, which included GPT-5.6 Sol and another even more capable model that hasn\u2019t been released, were operating with lower guardrails so that they could be tested, the startup said.<\/p>\n
The incident raises questions about the ability of advanced AI models to carry out cyberattacks even as governments work to impose guardrails on the technology. OpenAI\u2019s latest suite of models was widely released after weeks of discussion with government officials to allay concerns over its potential misuse. Washington had considered limiting foreign access to Anthropic PBC\u2019s advanced Claude Fable 5 and Mythos 5 models but stopped short of those curbs after the company imposed additional guardrails.<\/p>\n
ADVERTISEMENT<\/p>\n
CONTINUE READING BELOW<\/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 the blog post. \u201cWe are sharing preliminary findings at this stage to help defenders understand what happened and to help calibrate on what models are now capable of.\u201d<\/p>\n
While OpenAI\u2019s models were operating in a so-called sandbox testing environment, they exploited a vulnerability in the software of an unidentified third-party vendor to gain access to the internet and ultimately breached Hugging Face\u2019s infrastructure.<\/p>\n
Texas congressman Greg Casar, a Democrat, said in an X post that the incident was \u201cextremely alarming,\u201d urging more oversight over the development of AI models including mandatory safety testing and disclosure of security incidents.<\/p>\n
This is extremely alarming.<\/p>\n
AI is developing extremely fast with no real regulations to keep us safe. That has to change.<\/p>\n
We need regular mandatory independent safety testing and oversight, mandatory disclosure of security incidents, and international cooperation to keep people\u2026 https:\/\/t.co\/RQPRqplXTI<\/p>\n
\u2014 Congressman Greg Casar (@RepCasar) July 21, 2026<\/p>\n
Last week, Hugging Face reported an \u201cintrusion\u201d into its system, saying in a blog post that the breach was \u201cdifferent from anything we had handled before in one important way: it was driven, end to end, by an autonomous AI agent system \u2014 and we detected and dissected it largely with AI of our own.\u201d<\/p>\n
ADVERTISEMENT:<\/p>\n
CONTINUE READING BELOW<\/p>\n
OpenAI said it had asked the models to pursue \u201cadvanced exploitation\u201d and develop \u201ccomplex attack paths\u201d in an effort to evaluate their cyber capabilities. Instead of developing solutions on their own, the company said the models targeted Hugging Face\u2019s database to gain access to secret information that they could use for the evaluation.<\/p>\n
Anthropic posted similar observations earlier this year when the company decided to initially limit the release of Mythos. In one instance, a researcher urged an early version of the model to try to escape a secured, isolated \u201csandbox\u201d computer and then find a way to send a message to that person. Mythos succeeded \u2014 but then continued to take \u201cadditional, more concerning actions,\u201d developing a multi-step exploit to gain broad internet access.<\/p>\n
\u00a9 2026 Bloomberg<\/p>\n
#OpenAI #models #accidentally #hacked #hugging #face<\/p>\n","protected":false},"excerpt":{"rendered":"
OpenAI said its advanced artificial intelligence models inadvertently hacked Hugging Face in an \u201cunprecedented\u201d incident…<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[4],"tags":[3254,3182,15006,17658,5731,406],"_links":{"self":[{"href":"https:\/\/stock999.top\/index.php?rest_route=\/wp\/v2\/posts\/11719"}],"collection":[{"href":"https:\/\/stock999.top\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/stock999.top\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/stock999.top\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/stock999.top\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=11719"}],"version-history":[{"count":0,"href":"https:\/\/stock999.top\/index.php?rest_route=\/wp\/v2\/posts\/11719\/revisions"}],"wp:attachment":[{"href":"https:\/\/stock999.top\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=11719"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/stock999.top\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=11719"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/stock999.top\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=11719"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}