ChatGPT maker OpenAI said its artificial intelligence system has hacked into another AI company on its own in what the company called an \u201cunprecedented cyber incident\u201d.<\/p>\n
\u201cWe had a significant security incident during evaluation of our models,\u201d OpenAI CEO Sam Altman said in a statement posted on social media.<\/p>\n
AI startup Hugging Face said last week t it had detected an intrusion into its data processing systems that it suspected was caused by an AI agent autonomously acting on its own.<\/p>\n
\u201cWe suspected last week\u2019s cyberattack might have come from a frontier lab, given the sophistication of the agent,\u201d Hugging Face co-founder and CEO Cl\u00e9ment Delangue said in a statement. “Turns out it did.\u201d<\/p>\n
The disclosure comes amid heightened concerns about the cybersecurity capabilities of powerful models that led President Donald Trump in June to sign an executive order creating a framework for the federal government to vet the national security risks of the most advanced AI systems for up to a month before their public release.<\/p>\n
\u201cAI is accelerating the discovery and exploitation of vulnerabilities,\u201d OpenAI said in its statement. \u201cThe primary lesson from this incident is that model security and safety must keep pace with rapidly advancing capabilities.\u201d<\/p>\n
Delangue said he spent the past 24 hours working with OpenAI, \u201cand we strongly believe there was no malicious intent on their part. It\u2019s quite mind-blowing that all of this happened autonomously.”<\/p>\n
Delangue added that it \u201cmight be the first incident of its kind”.<\/p>\n
OpenAI said the intrusion was caused by a combination of its AI models, including its newly released GPT\u20115.6 Sol and an \u201ceven more capable\u201d model that is still being tested internally.<\/p>\n
OpenAI said its AI used stolen credentials and discovered a previously unknown vulnerability to access Hugging Face servers.<\/p>\n
It went to \u201cextreme lengths to achieve a rather narrow testing goal\u201d and \u201cfound ways to gain access to secret information that it could use to cheat the evaluation”, the company said.<\/p>\n","protected":false},"excerpt":{"rendered":"ChatGPT maker OpenAI said its artificial intelligence system has hacked into another AI company on its own in…\n","protected":false},"author":2,"featured_media":537854,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[365,363,364,111,139,69,145],"class_list":["post-537853","post","type-post","status-publish","format-standard","has-post-thumbnail","category-artificial-intelligence","tag-ai","tag-artificial-intelligence","tag-artificialintelligence","tag-new-zealand","tag-newzealand","tag-nz","tag-technology"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/posts\/537853","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/comments?post=537853"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/posts\/537853\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/media\/537854"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/media?parent=537853"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/categories?post=537853"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/tags?post=537853"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}