{"id":720177,"date":"2026-07-31T02:46:08","date_gmt":"2026-07-31T02:46:08","guid":{"rendered":"https:\/\/www.newsbeep.com\/uk\/720177\/"},"modified":"2026-07-31T02:46:08","modified_gmt":"2026-07-31T02:46:08","slug":"anthropic-says-claude-ai-hacked-three-firms-during-cyber-tests","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/uk\/720177\/","title":{"rendered":"Anthropic says Claude AI hacked three firms during cyber tests"},"content":{"rendered":"<p class=\"ssrcss-1q0x1qg-Paragraph e1jhz7w10\">US technology firm Anthropic says its artificial intelligence (AI) models hacked into the systems of three other firms during a cybersecurity test due to an error that gave them access to the internet.<\/p>\n<p class=\"ssrcss-1q0x1qg-Paragraph e1jhz7w10\">It comes just days after rival OpenAI said that its models had <a href=\"https:\/\/www.bbc.co.uk\/news\/articles\/c2el319vzr3o\" class=\"ssrcss-1e0jzsh-InlineLink e1kn3p7n0\" rel=\"nofollow noopener\" target=\"_blank\">breached the systems of other companies<\/a>, including AI tools hub Hugging Face.<\/p>\n<p class=\"ssrcss-1q0x1qg-Paragraph e1jhz7w10\">The announcement prompted Anthropic to check whether its own models had carried out similar attacks. It says it uncovered three cases that have since been reported to the affected companies.<\/p>\n<p class=\"ssrcss-1q0x1qg-Paragraph e1jhz7w10\">Anthropic, which did not name the firms, urged other AI labs to perform similar reviews to better understand the risks of their models&#8217; capabilities.<\/p>\n<p class=\"ssrcss-1q0x1qg-Paragraph e1jhz7w10\">Anthropic said <a href=\"https:\/\/www.anthropic.com\/news\/investigating-incidents-cybersecurity-evals\" class=\"ssrcss-1e0jzsh-InlineLink e1kn3p7n0\" rel=\"nofollow noopener\" target=\"_blank\">in a statement, external<\/a> that it reviewed more than 140,000 tests to find evidence that Claude &#8211; its family of AI models &#8211; could access the internet from testing environments that were designed to be sealed off.<\/p>\n<p class=\"ssrcss-1q0x1qg-Paragraph e1jhz7w10\">The tests include so-called &#8220;capture-the-flag&#8221; evaluations in which Claude was tasked with obtaining information by breaching other systems &#8211; a common way that experts assess a model&#8217;s hacking capabilities.<\/p>\n<p class=\"ssrcss-1q0x1qg-Paragraph e1jhz7w10\">A &#8220;misconfiguration&#8221; on systems run by Anthropic and its testing partner left the models with live internet access, allowing them to breach other systems, the San Francisco-based firm said.<\/p>\n<p class=\"ssrcss-1q0x1qg-Paragraph e1jhz7w10\">Anthropic said the earliest incidents date back to April and that it is &#8220;approaching the fixes as if the responsibility were ours alone.&#8221;<\/p>\n<p class=\"ssrcss-1q0x1qg-Paragraph e1jhz7w10\">Neither Anthropic nor the firms that were breached had noticed the intrusions at the time. <\/p>\n<p class=\"ssrcss-1q0x1qg-Paragraph e1jhz7w10\">Anthropic said it could have reviewed its records more thoroughly and added that the findings gave the firm &#8220;cautious optimism&#8221; that such risks can be overcome with more investment and tighter measures.<\/p>\n<p class=\"ssrcss-1q0x1qg-Paragraph e1jhz7w10\">The incidents come as tech firms pour billions of dollars into developing AI agents that can independently perform tasks ranging from research and customer support to cybersecurity.<\/p>\n","protected":false},"excerpt":{"rendered":"US technology firm Anthropic says its artificial intelligence (AI) models hacked into the systems of three other firms&hellip;\n","protected":false},"author":2,"featured_media":720178,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[554,733,4308,86,56,54,55],"class_list":["post-720177","post","type-post","status-publish","format-standard","has-post-thumbnail","category-artificial-intelligence","tag-ai","tag-artificial-intelligence","tag-artificialintelligence","tag-technology","tag-uk","tag-united-kingdom","tag-unitedkingdom"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts\/720177","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/comments?post=720177"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts\/720177\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/media\/720178"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/media?parent=720177"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/categories?post=720177"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/tags?post=720177"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}