New UK report finds AI models consistently cheat and deceive users | CyberScoop<\/title> <meta name=\"description\" content=\"Research from the UK\u2019s AI Security Institute reveals top AI models cheat, break rules, and trick users to complete tasks\u2014even bypassing security controls.\"> <link rel=\"canonical\" href=\"https:\/\/cyberscoop.com\/ai-models-cheat-deceive-users-aisi-report\/\"> <meta property=\"og:locale\" content=\"en_US\"> <meta property=\"og:type\" content=\"article\"> <meta property=\"og:title\" content=\"AI models keep getting caught cheating\"> <meta property=\"og:description\" content=\"Research from the UK\u2019s AI Security Institute reveals top AI models cheat, break rules, and trick users to complete tasks\u2014even bypassing security controls.\"> <meta property=\"og:url\" content=\"https:\/\/cyberscoop.com\/ai-models-cheat-deceive-users-aisi-report\/\"> <meta property=\"og:site_name\" content=\"CyberScoop\"> <meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/cyberscoop\/\"> <meta property=\"article:published_time\" content=\"2026-07-21T19:20:08+00:00\"> <meta property=\"article:modified_time\" content=\"2026-07-21T19:20:22+00:00\"> <meta property=\"og:image\" content=\"https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2026\/07\/ai-models-keep-getting-caught-cheating-2.jpg\"> <meta property=\"og:image:width\" content=\"2121\"> <meta property=\"og:image:height\" content=\"1414\"> <meta property=\"og:image:type\" content=\"image\/jpeg\"> <meta name=\"author\" content=\"djohnson\"> <meta name=\"twitter:card\" content=\"summary_large_image\"> <meta name=\"twitter:creator\" content=\"@CyberScoopNews\"> <meta name=\"twitter:site\" content=\"@CyberScoopNews\">  <link rel=\"dns-prefetch\" href=\"\/\/securepubads.g.doubleclick.net\">\n<link rel=\"dns-prefetch\" href=\"\/\/use.typekit.net\">\n<link rel=\"alternate\" type=\"application\/rss+xml\" title=\"CyberScoop \u00bb Feed\" href=\"https:\/\/cyberscoop.com\/feed\/\">\n<link rel=\"alternate\" type=\"application\/rss+xml\" title=\"CyberScoop \u00bb Comments Feed\" href=\"https:\/\/cyberscoop.com\/comments\/feed\/\"> <link rel=\"stylesheet\" id=\"all-css-2\" href=\"https:\/\/cyberscoop.com\/wp-includes\/css\/dist\/block-library\/style.min.css?m=1784312972g\" type=\"text\/css\" media=\"all\"> <link rel=\"stylesheet\" id=\"all-css-6\" href=\"https:\/\/cyberscoop.com\/wp-content\/mu-plugins\/search\/elasticpress\/dist\/css\/related-posts-block-styles.min.css?m=1784654430g\" type=\"text\/css\" media=\"all\"> <link rel=\"stylesheet\" id=\"all-css-8\" href=\"https:\/\/cyberscoop.com\/wp-content\/themes\/scoopnewsgroup\/dist\/css\/frontend.css?m=1782867887g\" type=\"text\/css\" media=\"all\">\n<link rel=\"stylesheet\" id=\"typekit-css\" href=\"https:\/\/use.typekit.net\/itk2qbh.css?ver=9519dd464d894b805a10\" media=\"all\"> <link rel=\"https:\/\/api.w.org\/\" href=\"https:\/\/cyberscoop.com\/wp-json\/\"><link rel=\"alternate\" title=\"JSON\" type=\"application\/json\" href=\"https:\/\/cyberscoop.com\/wp-json\/wp\/v2\/posts\/89902\"><meta name=\"generator\" content=\"WordPress 6.8.6\">\n<link rel=\"shortlink\" href=\"https:\/\/cyberscoop.com\/?p=89902\">\n<link rel=\"alternate\" title=\"oEmbed (JSON)\" type=\"application\/json+oembed\" href=\"https:\/\/cyberscoop.com\/wp-json\/oembed\/1.0\/embed?url=https%3A%2F%2Fcyberscoop.com%2Fai-models-cheat-deceive-users-aisi-report%2F\">\n<link rel=\"alternate\" title=\"oEmbed (XML)\" type=\"text\/xml+oembed\" href=\"https:\/\/cyberscoop.com\/wp-json\/oembed\/1.0\/embed?url=https%3A%2F%2Fcyberscoop.com%2Fai-models-cheat-deceive-users-aisi-report%2F&format=xml\">   <link rel=\"icon\" href=\"https:\/\/cyberscoop.com\/wp-content\/uploads\/sites\/3\/2023\/01\/cropped-cs_favicon-2.png?w=32\" sizes=\"32x32\">\n<link rel=\"icon\" href=\"https:\/\/cyberscoop.com\/wp-content\/uploads\/sites\/3\/2023\/01\/cropped-cs_favicon-2.png?w=192\" sizes=\"192x192\">\n<link rel=\"apple-touch-icon\" href=\"https:\/\/cyberscoop.com\/wp-content\/uploads\/sites\/3\/2023\/01\/cropped-cs_favicon-2.png?w=180\">\n<meta name=\"msapplication-TileImage\" content=\"https:\/\/cyberscoop.com\/wp-content\/uploads\/sites\/3\/2023\/01\/cropped-cs_favicon-2.png?w=270\"> <\/head><body class=\"wp-singular post-template-default single single-post postid-89902 single-format-standard wp-theme-scoopnewsgroup wp-child-theme-cyberscoop\" id=\"readabilityBody\"> <a href=\"https:\/\/cyberscoop.com\/ai-models-cheat-deceive-users-aisi-report\/#main\" class=\"skip-to-content-link visually-hidden-focusable\">Skip to main content<\/a> <\/p>\n<div class=\"ad ad--top ad--top-desktop\">\n<div class=\"ad__inner\"> <span class=\"screen-reader-text\">Advertisement<\/span> <\/div>\n<\/div>\n<p> <main id=\"main\" role=\"main\" tabindex=\"-1\"> <\/p>\n<div class=\"ad ad--top ad--top-mobile\">\n<div class=\"ad__inner\"> <span class=\"screen-reader-text\">Advertisement<\/span> <\/div>\n<\/div>\n<section id=\"stickybar\" class=\"stickybar stickybar--newsletter js-stickybar\" readability=\"0.82\"> <button class=\"stickybar__close js-stickybar-close\" aria-controls=\"stickybar\"> <svg class=\"icon icon--close\" width=\"21\" height=\"22\" viewBox=\"0 0 21 22\" fill=\"none\"><path d=\"m.822.518-.805.805L9.695 11 .017 20.678l.805.805 9.678-9.678 9.677 9.678.806-.805L11.305 11l9.678-9.677-.806-.805-9.677 9.677L.822.518Z\" fill=\"currentColor\" \/><\/svg> <span class=\"visually-hidden\">Close<\/span> <\/button> <\/section>\n<article class=\"single-article content\">\n<div class=\"single-article__container js-single-article-content\">\n<header class=\"single-article__header \" readability=\"25.697050938338\">\n<div class=\"single-article__header-content\" readability=\"35.139664804469\">\n<p> New research from the UK shows how nearly every model tested tried to cheat, scam or cut corners on its way to solving problems. <\/p>\n<p>  <br \/>\n<audio id=\"audio-player\" src=\"https:\/\/wp-tts-cdn.api.scpnewsgrp.com\/cyberscoop\/89902\/english.openai.mp3\"><\/audio> <\/p>\n<div readability=\"11\">\n<div>\n<p>Listen to this article<\/p>\n<p>  <\/p>\n<p>0:00<\/p>\n<\/p><\/div>\n<p>  <\/p>\n<p> <span id=\"tts-tooltip\">Learn more.<\/span> <span> This feature uses an automated voice, which may result in occasional errors in pronunciation, tone, or sentiment. <\/span> <\/p>\n<\/div>\n<p>  <\/div>\n<div class=\"single-article__cover-wrap\">\n<figure class=\"single-article__cover\"> <img data-recalc-dims=\"1\" fetchpriority=\"high\" width=\"640\" height=\"426\" src=\"https:\/\/i0.wp.com\/ddi.mohflo.net\/wp-content\/uploads\/2026\/07\/ai-models-keep-getting-caught-cheating.jpg?resize=640%2C426&ssl=1\" class=\"single-article__cover-image wp-post-image\" alt decoding=\"async\" fetchpriority=\"high\" srcset=\"https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2026\/07\/ai-models-keep-getting-caught-cheating-2.jpg 2121w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2026\/07\/ai-models-keep-getting-caught-cheating-2.jpg?resize=300,200 300w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2026\/07\/ai-models-keep-getting-caught-cheating-2.jpg?resize=768,512 768w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2026\/07\/ai-models-keep-getting-caught-cheating-2.jpg?resize=1024,683 1024w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2026\/07\/ai-models-keep-getting-caught-cheating-2.jpg?resize=1536,1024 1536w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2026\/07\/ai-models-keep-getting-caught-cheating-2.jpg?resize=2048,1365 2048w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2026\/07\/ai-models-keep-getting-caught-cheating-2.jpg?resize=600,400 600w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2026\/07\/ai-models-keep-getting-caught-cheating-2.jpg?resize=252,168 252w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2026\/07\/ai-models-keep-getting-caught-cheating-2.jpg?resize=506,337 506w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2026\/07\/ai-models-keep-getting-caught-cheating-2.jpg?resize=1013,675 1013w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2026\/07\/ai-models-keep-getting-caught-cheating-2.jpg?resize=1265,843 1265w\" sizes=\"(max-width: 1013px) 100vw, 1013px\"><figcaption> (Getty Images) <\/figcaption><\/figure>\n<\/p><\/div>\n<\/header>\n<div class=\"single-article__content\">\n<div class=\"single-article__content-inner has-drop-cap\"> <html readability=\"51.272593320236\"><body readability=\"103.74806800618\"><\/p>\n<p>Frontier AI companies often refer to their models as \u201chelpful assistants\u201d or try to compare them to entry-level employees. <\/p>\n<p>But new <a href=\"https:\/\/www.aisi.gov.uk\/blog\/cheating-behaviour-in-frontier-model-evaluations\">research<\/a> from the UK\u2019s AI Security Institute reinforces how large language models suffer from a common flaw that would land many human employees in hot water with their employers: they cheat.<\/p>\n<p>In other words, these models are so committed to completing their tasks that they will break the rules, cut corners and deceive their own users to accomplish them.<\/p>\n<p>\u201cEvery model we have tested for this behavior attempted to cheat,\u201d the AISI report said.<br \/>\u201cModels did not reliably report this behavior when asked, and often did not reason about it in their chain-of-thought, suggesting that detecting cheating will likely require robust monitoring methods.\u201d<\/p>\n<div class=\"ad ad--inline_1 \">\n<div class=\"ad__inner\"> <span class=\"screen-reader-text\">Advertisement<\/span> <\/div>\n<\/div>\n<p>The research tested OpenAI\u2019s ChatGPT 5.4, 5.5 and 5.6 models, along with Anthropic\u2019s Claude Opus 4.7 and Mythos Preview.<\/p>\n<figure class=\"wp-block-image size-large\"><img data-recalc-dims=\"1\" decoding=\"async\" height=\"277\" width=\"640\" src=\"https:\/\/i0.wp.com\/ddi.mohflo.net\/wp-content\/uploads\/2026\/07\/ai-models-keep-getting-caught-cheating.png?resize=640%2C277&ssl=1\" alt class=\"wp-image-89903\" srcset=\"https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2026\/07\/ai-models-keep-getting-caught-cheating-3.png 1392w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2026\/07\/ai-models-keep-getting-caught-cheating-3.png?resize=300,130 300w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2026\/07\/ai-models-keep-getting-caught-cheating-3.png?resize=768,332 768w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2026\/07\/ai-models-keep-getting-caught-cheating-3.png?resize=1024,443 1024w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2026\/07\/ai-models-keep-getting-caught-cheating-3.png?resize=600,259 600w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2026\/07\/ai-models-keep-getting-caught-cheating-3.png?resize=1200,519 1200w\" sizes=\"(max-width: 1024px) 100vw, 1024px\"><figcaption class=\"wp-element-caption\">AI models from Anthropic and OpenAI were tested for cheating. All demonstrated some level of deception in their tests. (Image Source: AISI)<\/figcaption><\/figure>\n<p>The AISI ran models through a series of \u201cCapture-the-Flag\u201d cyber evaluations, where they obtained points by performing offensive cybersecurity related tasks, like exploiting a particular vulnerability or reverse engineering compiled code.<\/p>\n<p>The research defines \u201ccheating\u201d as \u201ctaking an action that is out of scope for the task or explicitly disallowed by the rules, in order to achieve a goal through a shortcut, workaround, or unintended solution that the task was not meant to, or should not, permit.\u201d<\/p>\n<p>It captures a range of observed behaviors from models, like searching the internet for solutions, attacking or escalating privileges on unrelated systems, probing evaluation software to gain access to the task solution.<\/p>\n<div class=\"ad ad--inline_1 \">\n<div class=\"ad__inner\"> <span class=\"screen-reader-text\">Advertisement<\/span> <\/div>\n<\/div>\n<figure class=\"wp-block-image size-large\"><img data-recalc-dims=\"1\" decoding=\"async\" height=\"258\" width=\"640\" src=\"https:\/\/i0.wp.com\/ddi.mohflo.net\/wp-content\/uploads\/2026\/07\/ai-models-keep-getting-caught-cheating-1.png?resize=640%2C258&ssl=1\" alt class=\"wp-image-89904\" srcset=\"https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2026\/07\/ai-models-keep-getting-caught-cheating-4.png 1388w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2026\/07\/ai-models-keep-getting-caught-cheating-4.png?resize=300,121 300w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2026\/07\/ai-models-keep-getting-caught-cheating-4.png?resize=768,310 768w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2026\/07\/ai-models-keep-getting-caught-cheating-4.png?resize=1024,413 1024w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2026\/07\/ai-models-keep-getting-caught-cheating-4.png?resize=600,242 600w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2026\/07\/ai-models-keep-getting-caught-cheating-4.png?resize=1200,484 1200w\" sizes=\"(max-width: 1024px) 100vw, 1024px\"><figcaption class=\"wp-element-caption\">AI models fail to identify when they\u2019re cheating, and often justify it as acceptable when challenged by users (Image Source: AISI)<\/figcaption><\/figure>\n<p>Models also failed to acknowledge when they were cheating to complete a task, and less than 50 percent said the rule-breaking was \u201cwrong\u201d when challenged on it by a user.<\/p>\n<p>A model\u2019s propensity for cheating was not related to its capability, meaning newer or advanced models aren\u2019t more likely to cheat. Rather, researchers think it stems from the techniques used during a model\u2019s training and alignment that are to blame.<\/p>\n<p>But even if rates of cheating remain constant, the problem could still worsen over time. As newer models in the future could become more proficient and learn more effective cheating techniques.<\/p>\n<p>This deception also makes it difficult for labs like AISI to verify their own work, which relies on evaluating trustworthy outputs from AI systems.<\/p>\n<div class=\"ad ad--inline_1 \">\n<div class=\"ad__inner\"> <span class=\"screen-reader-text\">Advertisement<\/span> <\/div>\n<\/div>\n<figure class=\"wp-block-image size-large\"><img data-recalc-dims=\"1\" loading=\"lazy\" loading=\"lazy\" decoding=\"async\" height=\"284\" width=\"640\" src=\"https:\/\/i0.wp.com\/ddi.mohflo.net\/wp-content\/uploads\/2026\/07\/ai-models-keep-getting-caught-cheating-2.png?resize=640%2C284&ssl=1\" alt class=\"wp-image-89905\" srcset=\"https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2026\/07\/ai-models-keep-getting-caught-cheating-5.png 1376w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2026\/07\/ai-models-keep-getting-caught-cheating-5.png?resize=300,133 300w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2026\/07\/ai-models-keep-getting-caught-cheating-5.png?resize=768,342 768w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2026\/07\/ai-models-keep-getting-caught-cheating-5.png?resize=1024,455 1024w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2026\/07\/ai-models-keep-getting-caught-cheating-5.png?resize=600,267 600w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2026\/07\/ai-models-keep-getting-caught-cheating-5.png?resize=1200,534 1200w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\"><figcaption class=\"wp-element-caption\">Models like Claude Mythos Preview and GPT-5.6 Sol justifying their cheating to users. (Image Source: AISI)<\/figcaption><\/figure>\n<p>The research underscores how AI systems can go to drastic lengths to complete their task, including blowing through or circumventing a company\u2019s IT and cybersecurity protections.<\/p>\n<p>In one instance, AISI researchers said a model was inadvertently given a cyber capability evaluation that was misconfigured and impossible to solve.<\/p>\n<p>\u201cThe model tested was so persistent in attempting to cheat that it wrote and ran code on an external service, hosted on the open internet outside of AISI\u2019s systems, in an attempt to access our evaluation infrastructure, triggering a security alert in AISI\u2019s systems,\u201d the report said.<\/p>\n<p>While AISI said there were no data leaks or damage from the incident, the model could have successfully accessed their evaluation system had they not had monitoring in place. The institute said it implemented further controls on internal systems in response to the test.<\/p>\n<div class=\"ad ad--inline_1 \">\n<div class=\"ad__inner\"> <span class=\"screen-reader-text\">Advertisement<\/span> <\/div>\n<\/div>\n<p>The researchers said there are \u201csignificant consequences\u201d to a status quo where we can\u2019t trust models not to cheat. The behaviors are especially problematic in areas like <a href=\"https:\/\/cyberscoop.com\/trump-admin-ai-safety-cybersecurity-export-controls\/\">AI safety and security<\/a> research, as well as cyber operations and <a href=\"https:\/\/defensescoop.com\/2026\/06\/30\/trump-administration-announces-war-force-effort\/\">military decision-making<\/a>, where trust outputs from the AI systems are critical.<\/p>\n<p>Today, AISI said it can detect LLM cheating through a mix of manual review and LLM monitoring, but that may not always be true, and future models may be better at hiding their actions from human overseers.<\/p>\n<p>\u201cA more fundamental fix would be to train the models not to cheat in the first place \u2013 but given this kind of behavior was reported in frontier models more than a year ago, robustly aligning it away may not be easy,\u201d researchers wrote.<\/p>\n<p> <\/body> <\/p>\n<footer class=\"single-article__footer\" readability=\"3.5357142857143\">\n<div class=\"author-card\" readability=\"13\">\n<div class=\"author-card__avatar\">\n<figure class=\"author-card__image-wrap\"> <img data-recalc-dims=\"1\" decoding=\"async\" class=\"author-card__image\" src=\"https:\/\/i0.wp.com\/ddi.mohflo.net\/wp-content\/uploads\/2026\/07\/ai-models-keep-getting-caught-cheating-1.jpg?w=640&ssl=1\" alt=\"Derek B. Johnson\"> <\/figure>\n<\/p><\/div>\n<p><h4 class=\"author-card__name\">Written by Derek B. Johnson<\/h4>\n<p> Derek B. Johnson is a reporter at CyberScoop, where his beat includes cybersecurity, elections and the federal government. Prior to that, he has provided award-winning coverage of cybersecurity news across the public and private sectors for various publications since 2017. Derek has a bachelor\u2019s degree in print journalism from Hofstra University in New York and a master\u2019s degree in public policy from George Mason University in Virginia. <\/p>\n<\/p><\/div>\n<div class=\"single-article__tags-container\">\n<h4 class=\"single-article__tags-title\">In This Story<\/h4>\n<\/p><\/div>\n<\/footer>\n<p> <\/html><\/div>\n<\/p><\/div>\n<\/p><\/div>\n<div class=\"single-article__ads js-single-article-sidebar\">\n<div class=\"ad ad--sidebar js-single-article-sidebar-5 ad--rightrail_1 \">\n<div class=\"ad__inner\"> <span class=\"screen-reader-text\">Advertisement<\/span> <\/div>\n<\/div>\n<div class=\"ad ad--sidebar js-single-article-sidebar-4 ad--rightrail_2 \">\n<div class=\"ad__inner\"> <span class=\"screen-reader-text\">Advertisement<\/span> <\/div>\n<\/div>\n<div class=\"ad ad--sidebar js-single-article-sidebar-3 ad--rightrail_3 \">\n<div class=\"ad__inner\"> <span class=\"screen-reader-text\">Advertisement<\/span> <\/div>\n<\/div><\/div>\n<\/article>\n<div class=\"popular-stories popular-stories--single-post\">\n<div class=\"popular-stories__container\">\n<h2 class=\"popular-stories__title\"> More Scoops <\/h2>\n<p>  <\/div>\n<p>\n<\/div>\n<p> <\/p>\n<section class=\"latest-podcasts\">\n<h2 class=\"latest-podcasts__title\"> Latest Podcasts\t<\/h2>\n<\/section>\n<div class=\"top-categories\">\n<div class=\"top-categories__container\">\n<h3 class=\"top-categories__category-title\">Government<\/h3>\n<\/p><\/div>\n<div class=\"top-categories__container\">\n<h3 class=\"top-categories__category-title\">Technology<\/h3>\n<\/p><\/div>\n<\/p><\/div>\n<p> <\/main> <\/p>\n<div class=\"ad ad--bottom \">\n<div class=\"ad__inner\"> <span class=\"screen-reader-text\">Advertisement<\/span> <\/div>\n<\/div>\n<div id=\"interstitial\" class=\"welcome__container\"> <button id=\"close-modal-1\" class=\"welcome__clickable_area\"><\/button> <\/p>\n<div class=\"welcome__ad_wrapper\">\n<p> <button id=\"close-modal-3\" class=\"welcome__continue-button\">Continue to CyberScoop<\/button> <\/p>\n<\/p><\/div>\n<\/p><\/div>\n<p>   <\/body> <a href=\"https:\/\/cyberscoop.com\/ai-models-cheat-deceive-users-aisi-report\/\">Source<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>New UK report finds AI models consistently cheat and deceive<\/p>\n","protected":false},"author":11,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[235,6635,2381,4995,78,6607,117,4804,6410,564,256,3679],"tags":[236,6636,2384,4996,86,6608,119,4806,6412,565,262,3682],"class_list":["post-8848","post","type-post","status-publish","format-standard","hentry","category-ai","category-ai-security-institute","category-anthropic","category-claude","category-cybersecurity","category-daybreak","category-government","category-gpt-5","category-mythos","category-openai","category-research","category-uk","tag-ai","tag-ai-security-institute","tag-anthropic","tag-claude","tag-cybersecurity","tag-daybreak","tag-government","tag-gpt-5","tag-mythos","tag-openai","tag-research","tag-uk"],"featured_image_urls":{"full":"","thumbnail":"","medium":"","medium_large":"","large":"","1536x1536":"","2048x2048":"","chromenews-featured":"","chromenews-large":"","chromenews-medium":""},"author_info":{"display_name":"Cyber Scoop","author_link":"https:\/\/ddi.mohflo.net\/index.php\/author\/cyberscoop\/"},"category_info":"<a href=\"https:\/\/ddi.mohflo.net\/index.php\/category\/ai\/\" rel=\"category tag\">AI<\/a> <a href=\"https:\/\/ddi.mohflo.net\/index.php\/category\/ai-security-institute\/\" rel=\"category tag\">AI Security Institute<\/a> <a href=\"https:\/\/ddi.mohflo.net\/index.php\/category\/anthropic\/\" rel=\"category tag\">Anthropic<\/a> <a href=\"https:\/\/ddi.mohflo.net\/index.php\/category\/claude\/\" rel=\"category tag\">Claude<\/a> <a href=\"https:\/\/ddi.mohflo.net\/index.php\/category\/cybersecurity\/\" rel=\"category tag\">Cybersecurity<\/a> <a href=\"https:\/\/ddi.mohflo.net\/index.php\/category\/daybreak\/\" rel=\"category tag\">Daybreak<\/a> <a href=\"https:\/\/ddi.mohflo.net\/index.php\/category\/government\/\" rel=\"category tag\">Government<\/a> <a href=\"https:\/\/ddi.mohflo.net\/index.php\/category\/gpt-5\/\" rel=\"category tag\">GPT-5<\/a> <a href=\"https:\/\/ddi.mohflo.net\/index.php\/category\/mythos\/\" rel=\"category tag\">Mythos<\/a> <a href=\"https:\/\/ddi.mohflo.net\/index.php\/category\/openai\/\" rel=\"category tag\">OpenAI<\/a> <a href=\"https:\/\/ddi.mohflo.net\/index.php\/category\/research\/\" rel=\"category tag\">Research<\/a> <a href=\"https:\/\/ddi.mohflo.net\/index.php\/category\/uk\/\" rel=\"category tag\">UK<\/a>","tag_info":"UK","comment_count":"0","jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/ddi.mohflo.net\/index.php\/wp-json\/wp\/v2\/posts\/8848","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/ddi.mohflo.net\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/ddi.mohflo.net\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/ddi.mohflo.net\/index.php\/wp-json\/wp\/v2\/users\/11"}],"replies":[{"embeddable":true,"href":"https:\/\/ddi.mohflo.net\/index.php\/wp-json\/wp\/v2\/comments?post=8848"}],"version-history":[{"count":0,"href":"https:\/\/ddi.mohflo.net\/index.php\/wp-json\/wp\/v2\/posts\/8848\/revisions"}],"wp:attachment":[{"href":"https:\/\/ddi.mohflo.net\/index.php\/wp-json\/wp\/v2\/media?parent=8848"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/ddi.mohflo.net\/index.php\/wp-json\/wp\/v2\/categories?post=8848"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/ddi.mohflo.net\/index.php\/wp-json\/wp\/v2\/tags?post=8848"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}

{"id":8848,"date":"2026-07-21T14:20:08","date_gmt":"2026-07-21T19:20:08","guid":{"rendered":"https:\/\/cyberscoop.com\/?p=89902"},"modified":"2026-07-21T14:20:08","modified_gmt":"2026-07-21T19:20:08","slug":"ai-models-keep-getting-caught-cheating","status":"publish","type":"post","link":"https:\/\/ddi.mohflo.net\/index.php\/2026\/07\/21\/ai-models-keep-getting-caught-cheating\/","title":{"rendered":"AI models keep getting caught cheating"},"content":{"rendered":"