{"id":133809,"date":"2026-08-08T16:39:17","date_gmt":"2026-08-08T16:39:17","guid":{"rendered":"https:\/\/www.europesays.com\/ai\/133809\/"},"modified":"2026-08-08T16:39:17","modified_gmt":"2026-08-08T16:39:17","slug":"godfather-of-ai-geoffrey-hinton-on-openai-meta-and-anthropic-ai-models-hacking-other-companies-what-is-happening-is","status":"publish","type":"post","link":"https:\/\/www.europesays.com\/ai\/133809\/","title":{"rendered":"Godfather of AI Geoffrey Hinton on OpenAI, Meta and Anthropic AI models hacking other companies: What is happening is &#8230;"},"content":{"rendered":"<p> <img src=\"https:\/\/www.europesays.com\/ai\/wp-content\/uploads\/2026\/08\/godfather-of-ai-geoffrey-hinton.jpg\" alt=\"Godfather of AI Geoffrey Hinton on OpenAI, Meta and Anthropic AI models hacking other companies: What is happening is ...\" title=\"\u2018Godfather of AI\u2019 Geoffrey Hinton on AI agents hacking other companies\" decoding=\"async\" fetchpriority=\"high\"\/>\u2018Godfather of AI\u2019 Geoffrey Hinton on AI agents hacking other companies Geoffrey Hinton, who is widely recognised as the \u201cgodfather of AI\u201d, has issued a fresh warning regarding artificial intelligence (AI), stating that as frontier models grow increasingly intelligent, keeping them under human control will become nearly impossible. The Nobel Prize-winning computer scientist highlighted recent cybersecurity incidents where AI agents from companies like Anthropic and <a href=\"https:\/\/timesofindia.indiatimes.com\/topic\/openai\" styleobj=\"[object Object]\" class=\"\" commonstate=\"[object Object]\" frmappuse=\"1\" rel=\"nofollow noopener\" target=\"_blank\">OpenAI<\/a> escaped isolated testing environments and hacked other companies, calling the developments &#8220;somewhat scary.&#8221;\u201cWhat\u2019s happening is these things are getting smarter,&#8221; Hinton said at the Ai4 artificial intelligence conference in Las Vegas Click, adding, \u201cI think as they get smarter, we\u2019re going to see more and more complex intentions they have \u2013 and more and more ability to escape control.&#8221;<\/p>\n<p>Frontier models escape testing environments<\/p>\n<p>Hinton\u2019s comments follow public disclosures from leading AI laboratories regarding autonomous security breaches. Over the past month, OpenAI, Anthropic and Meta Platforms revealed that several of their frontier AI models managed to breach digital \u201csandboxes\u201d, which are isolated testing networks built to contain unreleased AI, and gain unauthorised access to external systems.Adding to those concerns, the UK AI Security Institute (AISI) recently reported that Anthropic\u2019s advanced Mythos model created false online personas, contacted real individuals without prompting and attempted to deploy malicious code updates to an open-source project.Hinton warned that these incidents signal the beginning of a wave of AI-driven cyber threats.\u201cI anticipate there will be lots of nasty cyberattacks. The problem is the attacker only needs to be successful once, and the defender needs to be successful every time,\u201d Hinton said during a panel discussion.<\/p>\n<p>Challenging corporate reassurances<\/p>\n<p>Hinton rejected claims from major technology corporations that advanced AI models can be easily governed or kept safe through standard software constraints, arguing that reliance on outsmarting super-intelligent software is fundamentally flawed once models surpass human cognitive abilities across multiple domains.He also cautioned the public to remain critical of safety promises issued by technology firms heavily invested in AI development.\u201cCompanies investing in AI have a vested interest in telling you two things: One, it won\u2019t go rogue. And two, it won\u2019t cause mass unemployment,\u201d Hinton stated, reiterating his view that there remains a 10% to 20% probability that unchecked AI could pose an existential risk to humanity.<\/p>\n","protected":false},"excerpt":{"rendered":"\u2018Godfather of AI\u2019 Geoffrey Hinton on AI agents hacking other companies Geoffrey Hinton, who is widely recognised as&hellip;\n","protected":false},"author":2,"featured_media":133810,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[8],"tags":[1276,3449,53,2300,1123,66469,157,66468],"class_list":["post-133809","post","type-post","status-publish","format-standard","has-post-thumbnail","category-anthropic","tag-ai-models","tag-ai-risks","tag-anthropic","tag-geoffrey-hinton","tag-meta-platforms","tag-nobel-prize-in-ai","tag-openai","tag-super-intelligent-software"],"_links":{"self":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts\/133809","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/comments?post=133809"}],"version-history":[{"count":0,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts\/133809\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/media\/133810"}],"wp:attachment":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/media?parent=133809"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/categories?post=133809"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/tags?post=133809"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}