{"id":24264,"date":"2026-08-05T09:37:16","date_gmt":"2026-08-05T07:37:16","guid":{"rendered":"http:\/\/costops.com\/index.php\/2026\/08\/05\/openai-and-anthropic-models-went-rogue-during-uk-cybersecurity-test\/"},"modified":"2026-08-05T09:37:16","modified_gmt":"2026-08-05T07:37:16","slug":"openai-and-anthropic-models-went-rogue-during-uk-cybersecurity-test","status":"publish","type":"post","link":"http:\/\/costops.com\/index.php\/2026\/08\/05\/openai-and-anthropic-models-went-rogue-during-uk-cybersecurity-test\/","title":{"rendered":"OpenAI and Anthropic models \u2018went rogue\u2019 during UK cybersecurity test"},"content":{"rendered":"

AI Security Institute says tools engaged in potentially harmful activity and incident reveals new type of risk<\/p>\n

Advanced AI models developed by OpenAI and Anthropic went rogue during a cybersecurity test and showed a new type of risk posed by the technology, according to the UK\u2019s AI Security Institute.<\/p>\n

AISI described the actions carried out by the agents, the term for AI systems that can perform tasks without human help, as a \u201cserious incident\u201d. In one example, an agent powered by Anthropic\u2019s Mythos model sent targeted emails to people.<\/p>\n

Continue reading…<\/a>
\nAI Security Institute says tools engaged in potentially harmful activity and incident reveals new type of risk
\nAdvanced AI models developed by OpenAI and Anthropic went rogue during a cybersecurity test and showed a new type of risk posed by the technology, according to the UK\u2019s AI Security Institute.
\nAISI described the actions carried out by the agents, the term for AI systems that can perform tasks without human help, as a \u201cserious incident\u201d. In one example, an agent powered by Anthropic\u2019s Mythos model sent targeted emails to people. Continue reading…Technology | The Guardian<\/p>\n","protected":false},"excerpt":{"rendered":"

AI Security Institute says tools engaged in potentially harmful activity and incident reveals new type of risk Advanced AI models developed by OpenAI and Anthropic went rogue during a cybersecurity test and showed a new type of risk posed by the technology, according to the UK\u2019s AI Security Institute. AISI described the actions carried out …<\/p>\n

OpenAI and Anthropic models \u2018went rogue\u2019 during UK cybersecurity test<\/span> Read More »<\/a><\/p>\n","protected":false},"author":0,"featured_media":24265,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[1],"tags":[],"_links":{"self":[{"href":"http:\/\/costops.com\/index.php\/wp-json\/wp\/v2\/posts\/24264"}],"collection":[{"href":"http:\/\/costops.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/costops.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"replies":[{"embeddable":true,"href":"http:\/\/costops.com\/index.php\/wp-json\/wp\/v2\/comments?post=24264"}],"version-history":[{"count":0,"href":"http:\/\/costops.com\/index.php\/wp-json\/wp\/v2\/posts\/24264\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"http:\/\/costops.com\/index.php\/wp-json\/wp\/v2\/media\/24265"}],"wp:attachment":[{"href":"http:\/\/costops.com\/index.php\/wp-json\/wp\/v2\/media?parent=24264"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/costops.com\/index.php\/wp-json\/wp\/v2\/categories?post=24264"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/costops.com\/index.php\/wp-json\/wp\/v2\/tags?post=24264"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}