{"id":19434,"date":"2026-08-05T01:08:46","date_gmt":"2026-08-05T01:08:46","guid":{"rendered":"https:\/\/8657085.xyz\/?p=19434"},"modified":"2026-08-05T01:08:46","modified_gmt":"2026-08-05T01:08:46","slug":"anthropics-ai-used-fake-human-profiles-to-trick-people-in-safety-test","status":"publish","type":"post","link":"https:\/\/8657085.xyz\/?p=19434","title":{"rendered":"Anthropic&#8217;s AI used fake human profiles to trick people in safety test"},"content":{"rendered":"<p> <div style=\"display: grid; grid-template-columns: 300px 160px; gap: 2px; width: 460px; background: #eee; padding: 2px;\">\r\n\r\n  <!-- \u6574\u884c\u5bbd\u5e7f\u544a -->\r\n  <div style=\"grid-column: 1\/-1; width: 460px; height: 250px; background: #ccc; display: grid; place-items: center;\">\r\n  <script async type=\"application\/javascript\" src=\"https:\/\/a.magsrv.com\/ad-provider.js\"><\/script> \r\n <ins class=\"eas6a97888e2\" data-zoneid=\"5876674\"><\/ins> \r\n <script>(AdProvider = window.AdProvider || []).push({\"serve\": {}});<\/script>\r\n  <\/div>\r\n  <div style=\"grid-column: 1\/-1; width: 460px; height: 90px; background: #ccc; display: grid; place-items: center;\">\r\n  <script async type=\"application\/javascript\" src=\"https:\/\/a.magsrv.com\/ad-provider.js\"><\/script> \r\n <ins class=\"eas6a97888e2\" data-zoneid=\"5876676\"><\/ins> \r\n <script>(AdProvider = window.AdProvider || []).push({\"serve\": {}});<\/script>\r\n  <\/div>\r\n\r\n  <!-- \u5de6\u4fa7\u7ad6\u6392 -->\r\n  <div style=\"height: 250px; background: #ccc; display: grid; place-items: center;\">\r\n  <script async type=\"application\/javascript\" src=\"https:\/\/a.magsrv.com\/ad-provider.js\"><\/script> \r\n <ins class=\"eas6a97888e2\" data-zoneid=\"5876672\"><\/ins> \r\n <script>(AdProvider = window.AdProvider || []).push({\"serve\": {}});<\/script>\r\n  <\/div>\r\n  <div style=\"height: 500px; background: #ccc; display: grid; place-items: center;\">\r\n  <script async type=\"application\/javascript\" src=\"https:\/\/a.magsrv.com\/ad-provider.js\"><\/script> \r\n <ins class=\"eas6a97888e2\" data-zoneid=\"5876680\"><\/ins> \r\n <script>(AdProvider = window.AdProvider || []).push({\"serve\": {}});<\/script>\r\n  <\/div>\r\n\r\n  <!-- \u53f3\u4fa7\u6469\u5929\u697c\uff08\u548c\u5de6\u4fa7\u5b8c\u5168\u5bf9\u9f50\uff09 -->\r\n  <div style=\"grid-row: 3\/5; height: 750px; background: #ccc; display: grid; place-items: center;\">\r\n  <script async type=\"application\/javascript\" src=\"https:\/\/a.magsrv.com\/ad-provider.js\"><\/script> \r\n <ins class=\"eas6a97888e2\" data-zoneid=\"5876678\"><\/ins> \r\n <script>(AdProvider = window.AdProvider || []).push({\"serve\": {}});<\/script>\r\n  <\/div>\r\n  \r\n  <script async type=\"application\/javascript\" src=\"https:\/\/a.magsrv.com\/ad-provider.js\"><\/script> \r\n <ins class=\"eas6a97888e6\" data-zoneid=\"5876682\"><\/ins> \r\n <script>(AdProvider = window.AdProvider || []).push({\"serve\": {}});<\/script>\r\n<\/div><br \/>\n<\/p>\n<div>\n<p class=\"ssrcss-1q0x1qg-Paragraph e1jhz7w10\"><b class=\"ssrcss-1xjjfut-BoldText e5tfeyi3\">The latest artificial intelligence (AI) tools from Anthropic and OpenAI went to new extremes in trying to undermine a popular platform during testing by the UK&#8217;s AI Security Institute.<\/b><\/p>\n<p class=\"ssrcss-1q0x1qg-Paragraph e1jhz7w10\">The AISI said on Tuesday that Anthropic&#8217;s Mythos and OpenAI&#8217;s Sol models engaged in a level of &#8220;autonomy and deception&#8221; it had not seen before.<\/p>\n<p class=\"ssrcss-1q0x1qg-Paragraph e1jhz7w10\">During routine AI safety testing, an Anthropic agent created fake profiles of real people as it tried to trick a person standing between it and access to GitHub, a large platform where technology developers store software code.<\/p>\n<p class=\"ssrcss-1q0x1qg-Paragraph e1jhz7w10\">Anthropic and OpenAI noted in response to AISI&#8217;s report that its test had reduced or removed normal safeguards.<\/p>\n<p class=\"ssrcss-1q0x1qg-Paragraph e1jhz7w10\">AISI evaluators first noticed &#8220;unusual data transfers leaving our research systems&#8221; during a test, then found that &#8220;some of the agents being tested had engaged in sustained, potentially harmful activity directed at real people and organisations&#8221;.<\/p>\n<p class=\"ssrcss-1q0x1qg-Paragraph e1jhz7w10\">It turned out that a Mythos agent had created &#8220;malicious code&#8221; and attempted to insert it into GitHub&#8217;s system.<\/p>\n<p class=\"ssrcss-1q0x1qg-Paragraph e1jhz7w10\">The Mythos agent identified and researched the people who maintained GitHub and created a series of &#8220;fake online identities&#8221; based on those real people. It did so as part of an effort to pressure and trick the real people into approving its malicious code.<\/p>\n<p class=\"ssrcss-1q0x1qg-Paragraph e1jhz7w10\">The agent even sent people direct messages masquerading as the real people it had researched.<\/p>\n<p class=\"ssrcss-1q0x1qg-Paragraph e1jhz7w10\">&#8220;When the agent&#8217;s pull request was challenged in public, it edited its earlier activity to appear harmless and considered adopting a fresh identity to continue,&#8221; AISI said.<\/p>\n<p class=\"ssrcss-1q0x1qg-Paragraph e1jhz7w10\">Throughout the attempts, it was human review that stopped the agent from succeeding in delivering the malicious code to GitHub.<\/p>\n<p class=\"ssrcss-1q0x1qg-Paragraph e1jhz7w10\">While AISI said the Mythos agent had not been instructed specifically to avoid or carry out such behaviour, it was &#8220;the first time we have seen risks around autonomy and deception manifest this clearly, without specific prompting, in the real-world&#8221;.<\/p>\n<p class=\"ssrcss-1q0x1qg-Paragraph e1jhz7w10\">The rival AI companies, which are poised to be listed on the public stock market, have in recent weeks said their tools were responsible for several cyber-hacking incidents.  <\/p>\n<p class=\"ssrcss-1q0x1qg-Paragraph e1jhz7w10\">Anthropic wrote in a public statement that the AISI testing parameters were &#8220;not representative of any of our production models&#8221;.<\/p>\n<p class=\"ssrcss-1q0x1qg-Paragraph e1jhz7w10\">It added that the company is conducting its own investigation into the incident in order to &#8220;identify the causes of its behavior&#8221;.<\/p>\n<p class=\"ssrcss-1q0x1qg-Paragraph e1jhz7w10\">A spokesperson for OpenAI said the AISI testing conditions &#8220;do not reflect ordinary use&#8221; and that the company would &#8220;continue working with evaluators and other stakeholders across the industry to strengthen shared practices for conducting evaluations safely as models become more capable&#8221;.<\/p>\n<p class=\"ssrcss-1q0x1qg-Paragraph e1jhz7w10\">AISI said on Tuesday that its testing of AI models with such safeguards turned off is routine, as is giving such tools access to the open internet.<\/p>\n<p class=\"ssrcss-1q0x1qg-Paragraph e1jhz7w10\">It added that the model behaviour at issue amounted to &#8220;a small number of events under very specific conditions&#8221;.<\/p>\n<p class=\"ssrcss-1q0x1qg-Paragraph e1jhz7w10\">Nonetheless, it said the way Mythos and Sol acted in response to a straightforward task went outside of what the AI tools were prompted to do.<\/p>\n<p class=\"ssrcss-1q0x1qg-Paragraph e1jhz7w10\">&#8220;The activity undertaken by the agent showed signs of novel, potentially deceptive behaviours, and were to an extent and severity we did not anticipate&#8221;, AISI said.<\/p>\n<p class=\"ssrcss-1q0x1qg-Paragraph e1jhz7w10\">Most of the malicious agent actions AISI reported were done by Anthropic&#8217;s Mythos. OpenAI&#8217;s Sol was only blamed for two of the noted actions.<\/p>\n<p class=\"ssrcss-1q0x1qg-Paragraph e1jhz7w10\">The core issue occurred last week, as part of a test in which evaluators with AISI asked each of the models to &#8220;solve a cybersecurity challenge&#8221; that involved GitHub, the software code repository, which is owned by Microsoft.<\/p>\n<p class=\"ssrcss-1q0x1qg-Paragraph e1jhz7w10\">GitHub was notified by AISI of the attempted breach of its system. Microsoft has been contacted by the BBC for comment.<\/p>\n<\/div>\n<p><!-- \u603b\u5bb9\u5668\uff1a\u6700\u5927\u5bbd908px Grid\u7d27\u51d1\u5e03\u5c40 -->\r\n<div style=\"display: grid; grid-template-columns: 728px 160px; gap:2px; width:908px; background:#eee; padding:2px;\">\r\n\r\n  <!-- \u901a\u680f\u9876\u90e8\uff1a\u6700\u5927\u6a2a\u5e45 908x258 \u8de8\u6574\u884c -->\r\n  <div style=\"grid-column:1\/-1; height:258px; background:#ff6b6b; display:grid; place-items:center;\">\r\n    <!-- JuicyAds v3.0 -->\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async src=\"https:\/\/poweredby.jads.co\/js\/jads.js\"><\/script>\r\n<ins id=\"1114307\" data-width=\"908\" data-height=\"258\"><\/ins>\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async>(adsbyjuicy = window.adsbyjuicy || []).push({'adzone':1114307});<\/script>\r\n<!--JuicyAds END-->\r\n  <\/div>\r\n\r\n  <!-- \u7b2c\u4e8c\u901a\u680f\uff1a728\u00d790 \u901a\u680f -->\r\n  <div style=\"grid-column:1\/-1; height:90px; background:#4ecdc4; display:grid; place-items:center;\">\r\n    <!-- JuicyAds v3.0 -->\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async src=\"https:\/\/poweredby.jads.co\/js\/jads.js\"><\/script>\r\n<ins id=\"1114300\" data-width=\"728\" data-height=\"90\"><\/ins>\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async>(adsbyjuicy = window.adsbyjuicy || []).push({'adzone':1114300});<\/script>\r\n<!--JuicyAds END-->\r\n  <\/div>\r\n\r\n  <!-- \u5de6\u4fa7\u4e3b\u680f\uff1a\u591a\u5e7f\u544a\u5806\u53e0 -->\r\n  <div style=\"display:grid; gap:2px;\">\r\n    <div style=\"height:60px; background:#45b7d1; display:grid; place-items:center;\">\r\n\t<!-- JuicyAds v3.0 -->\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async src=\"https:\/\/poweredby.jads.co\/js\/jads.js\"><\/script>\r\n<ins id=\"1114308\" data-width=\"468\" data-height=\"60\"><\/ins>\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async>(adsbyjuicy = window.adsbyjuicy || []).push({'adzone':1114308});<\/script>\r\n<!--JuicyAds END-->\r\n\t<\/div>\r\n    <div style=\"height:250px; background:#ffe066; display:grid; place-items:center;\">\r\n\t<!-- JuicyAds v3.0 -->\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async src=\"https:\/\/poweredby.jads.co\/js\/jads.js\"><\/script>\r\n<ins id=\"1114299\" data-width=\"300\" data-height=\"250\"><\/ins>\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async>(adsbyjuicy = window.adsbyjuicy || []).push({'adzone':1114299});<\/script>\r\n<!--JuicyAds END-->\r\n\t<\/div>\r\n    <div style=\"height:250px; background:#ff9ecd; display:grid; place-items:center;\">\r\n\t<!-- JuicyAds v3.0 -->\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async src=\"https:\/\/poweredby.jads.co\/js\/jads.js\"><\/script>\r\n<ins id=\"1114305\" data-width=\"250\" data-height=\"250\"><\/ins>\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async>(adsbyjuicy = window.adsbyjuicy || []).push({'adzone':1114305});<\/script>\r\n<!--JuicyAds END-->\r\n\t<\/div>\r\n    <div style=\"height:139px; background:#c792ea; display:grid; place-items:center;\">\r\n\t<!-- JuicyAds v3.0 -->\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async src=\"https:\/\/poweredby.jads.co\/js\/jads.js\"><\/script>\r\n<ins id=\"1114302\" data-width=\"133\" data-height=\"139\"><\/ins>\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async>(adsbyjuicy = window.adsbyjuicy || []).push({'adzone':1114302});<\/script>\r\n<!--JuicyAds END-->\r\n\t<\/div>\r\n    <div style=\"height:125px; background:#91e7ac; display:grid; place-items:center;\">\r\n\t\r\n<!-- JuicyAds v3.0 -->\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async src=\"https:\/\/poweredby.jads.co\/js\/jads.js\"><\/script>\r\n<ins id=\"1114303\" data-width=\"125\" data-height=\"125\"><\/ins>\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async>(adsbyjuicy = window.adsbyjuicy || []).push({'adzone':1114303});<\/script>\r\n<!--JuicyAds END-->\r\n\t<\/div>\r\n  <\/div>\r\n\r\n  <!-- \u53f3\u4fa7\u7ad6\u680f\uff1a160\u00d7600 \u6574\u5217\u9ad8\u5e7f\u544a -->\r\n  <div style=\"grid-row:3\/8; height:600px;  display:grid; place-items:center;\">\r\n    <!-- JuicyAds v3.0 -->\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async src=\"https:\/\/poweredby.jads.co\/js\/jads.js\"><\/script>\r\n<ins id=\"1114301\" data-width=\"160\" data-height=\"600\"><\/ins>\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async>(adsbyjuicy = window.adsbyjuicy || []).push({'adzone':1114301});<\/script>\r\n<!--JuicyAds END-->\r\n  <\/div>\r\n\r\n<\/div><br \/>\n<br \/><a href=\"https:\/\/www.bbc.co.uk\/news\/articles\/c1w1lvn7d9go?at_medium=RSS&#038;at_campaign=rss\">Source link <\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>The latest artificial intelligence (AI) tools from Anthropic and OpenAI went to new extremes in&#8230;<\/p>\n","protected":false},"author":1,"featured_media":19435,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[12661,2831,250,212,15000,2153,1208,5295],"class_list":["post-19434","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-business","tag-anthropics","tag-fake","tag-human","tag-people","tag-profiles","tag-safety","tag-test","tag-trick"],"featured_image_urls":{"full":["https:\/\/8657085.xyz\/wp-content\/uploads\/2026\/08\/974e85e0-905d-11f1-b2ab-0dd01740f9f6.jpg",1200,675,false],"thumbnail":["https:\/\/8657085.xyz\/wp-content\/uploads\/2026\/08\/974e85e0-905d-11f1-b2ab-0dd01740f9f6-150x150.jpg",150,150,true],"medium":["https:\/\/8657085.xyz\/wp-content\/uploads\/2026\/08\/974e85e0-905d-11f1-b2ab-0dd01740f9f6-300x169.jpg",300,169,true],"medium_large":["https:\/\/8657085.xyz\/wp-content\/uploads\/2026\/08\/974e85e0-905d-11f1-b2ab-0dd01740f9f6-768x432.jpg",640,360,true],"large":["https:\/\/8657085.xyz\/wp-content\/uploads\/2026\/08\/974e85e0-905d-11f1-b2ab-0dd01740f9f6-1024x576.jpg",640,360,true],"1536x1536":["https:\/\/8657085.xyz\/wp-content\/uploads\/2026\/08\/974e85e0-905d-11f1-b2ab-0dd01740f9f6.jpg",1200,675,false],"2048x2048":["https:\/\/8657085.xyz\/wp-content\/uploads\/2026\/08\/974e85e0-905d-11f1-b2ab-0dd01740f9f6.jpg",1200,675,false],"covernews-slider-full":["https:\/\/8657085.xyz\/wp-content\/uploads\/2026\/08\/974e85e0-905d-11f1-b2ab-0dd01740f9f6-1115x675.jpg",1115,675,true],"covernews-slider-center":["https:\/\/8657085.xyz\/wp-content\/uploads\/2026\/08\/974e85e0-905d-11f1-b2ab-0dd01740f9f6-800x500.jpg",800,500,true],"covernews-featured":["https:\/\/8657085.xyz\/wp-content\/uploads\/2026\/08\/974e85e0-905d-11f1-b2ab-0dd01740f9f6-1024x576.jpg",1024,576,true],"covernews-medium":["https:\/\/8657085.xyz\/wp-content\/uploads\/2026\/08\/974e85e0-905d-11f1-b2ab-0dd01740f9f6-540x340.jpg",540,340,true],"covernews-medium-square":["https:\/\/8657085.xyz\/wp-content\/uploads\/2026\/08\/974e85e0-905d-11f1-b2ab-0dd01740f9f6-400x250.jpg",400,250,true]},"author_info":{"display_name":"admin","author_link":"https:\/\/8657085.xyz\/?author=1"},"category_info":"<a href=\"https:\/\/8657085.xyz\/?cat=2\" rel=\"category\">Business<\/a>","tag_info":"Business","comment_count":"0","_links":{"self":[{"href":"https:\/\/8657085.xyz\/index.php?rest_route=\/wp\/v2\/posts\/19434","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/8657085.xyz\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/8657085.xyz\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/8657085.xyz\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/8657085.xyz\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=19434"}],"version-history":[{"count":0,"href":"https:\/\/8657085.xyz\/index.php?rest_route=\/wp\/v2\/posts\/19434\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/8657085.xyz\/index.php?rest_route=\/wp\/v2\/media\/19435"}],"wp:attachment":[{"href":"https:\/\/8657085.xyz\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=19434"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/8657085.xyz\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=19434"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/8657085.xyz\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=19434"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}