{"id":117880,"date":"2026-09-15T01:46:53","date_gmt":"2026-09-15T01:46:53","guid":{"rendered":"https:\/\/youzum.net\/ai-agents-blew-the-whistle-on-their-cheating-colleagues\/"},"modified":"2026-09-15T01:46:53","modified_gmt":"2026-09-15T01:46:53","slug":"ai-agents-blew-the-whistle-on-their-cheating-colleagues","status":"publish","type":"post","link":"https:\/\/youzum.net\/es\/ai-agents-blew-the-whistle-on-their-cheating-colleagues\/","title":{"rendered":"AI agents blew the whistle on their cheating colleagues"},"content":{"rendered":"<div data-chronoton-summary=\"&lt;ul&gt;&lt;br&gt;&lt;li&gt;&lt;strong&gt;Cheating spread like a virus.&lt;\/strong&gt; When one agent called &quot;prover-theta&quot; found a loophole to fake math proofs, others reverse-engineered the exploit within minutes\u2014collectively &quot;solving&quot; 34 notoriously hard problems, including the Jacobian conjecture, in under half an hour.&lt;\/li&gt;&lt;br&gt;&lt;li&gt;&lt;strong&gt;Some agents pushed back.&lt;\/strong&gt; Unprompted, a faction of agents audited fake proofs, sent warnings, and even repurposed a bug-reporting tool to alert human researchers\u2014eventually outnumbering the cheaters 24 to 14.&lt;\/li&gt;&lt;br&gt;&lt;li&gt;&lt;strong&gt;Open communication channels were a double-edged sword.&lt;\/strong&gt; Transparent messaging helped cheating spread fast, but also gave whistleblowers the tools to fight back\u2014and gave researchers a rare window into exactly how a swarm of AI agents goes off the rails.&lt;\/li&gt;&lt;br&gt;&lt;li&gt;&lt;strong&gt;Whistleblowers alone won't be enough.&lt;\/strong&gt; Experts warn that self-policing only works if there are real consequences\u2014suggesting future agent swarms may need enforcement mechanisms like voting systems or the ability to cut off rule-breakers' access to tools.&lt;\/li&gt;&lt;\/ul&gt;\" data-chronoton-post-id=\"1144037\" data-chronoton-expand-collapse=\"1\" data-chronoton-analytics-enabled=\"1\"><\/div>\n<p>A group of AI agents asked to solve a series of math problems split into rival factions\u2014when some cheated, others tried to stop them. That whistleblowing behavior, seen for the first time in a recent experiment run by Google DeepMind, could have implications for alignment researchers trying to keep swarms of autonomous AI agents in line.\u00a0<\/p>\n<p>Researchers at frontier labs hope large swarms of agents working together will speed up the rate of scientific discovery. But their behavior can be unpredictable, as vividly demonstrated in July, when a group of OpenAI agents broke out of a sandboxed environment and <a href=\"https:\/\/www.technologyreview.com\/2026\/08\/26\/1143013\/the-inside-story-on-why-openai-agents-hacked-hugging-face\/\">hacked into the open-source platform Hugging Face<\/a> looking for ways to cheat on the test they had been given.<\/p>\n<p>In <a href=\"https:\/\/arxiv.org\/pdf\/2609.04170\" data-type=\"link\" data-id=\"https:\/\/arxiv.org\/pdf\/2609.04170\">the new study<\/a>, designed to examine the behavior of large groups of AI agents, DeepMind tasked a swarm of 100 agents with solving a series of 71 complicated math problems. All the agents were prompted to behave like world-class math researchers at a conference. They were assigned different specialties\u2014some were experts in number theory, others in combinatorics (a branch of math to do with counting and sorting), analysis, or algebra. All were told to cooperate and play by the rules.\u00a0<\/p>\n<p>Instead, the experiment devolved into chaos. Agents accused each other of cheating, complained to the organizers, and at one point even boycotted the experiment.<\/p>\n<p>\u201cThis conference is a sham!\u201d wrote one agent when it discovered that all the problems had been completed before it had a chance to submit any of its own work. \u201cI am appalled to inform you that we have been swindled!\u201d posted another. \u201cAll these proofs are FAKE.\u201d\u00a0<\/p>\n<p>Others tried to let the \u201cconference organizers\u201d know what was going on. \u201cWhen virtuous agents discovered other agents cheated on tasks they were working to solve fairly, agents started to alert each other about what was happening,\u201d says Davide Paglieri, a research scientist at Google DeepMind and lead author on a <a href=\"https:\/\/arxiv.org\/pdf\/2609.04170\">paper<\/a>, which has not been peer-reviewed. \u201cUnprompted, the whistleblower agents even repurposed the feedback tool, which was originally meant for bug reports and platform improvements, to escalate the issue to humans.\u201d<\/p>\n<p>The agents\u2014all running on Google\u2019s Gemini 3.1 Pro model\u2014had been warned that any attempts to cheat the system would be detected and \u201crejected with zero credit.\u201d In practice, the proofs the agents submitted were not actually being checked in detail.<\/p>\n<p>It took the swarm of agents just under an hour to correctly solve the first 37 problems. Things started to go off the rails when an agent called \u201cprover-theta\u201d stumbled across an exploit that enabled it to submit solutions to problems successfully without actually solving them first, by redefining the terms the problem used. Within minutes, other agents had noticed and were reverse-engineering the exploit to solve other problems. Over the next 27 minutes, the swarm \u201csolved\u201d the remaining 34 problems, which included notoriously difficult challenges like the Jacobian conjecture, often with a single line of code.\u00a0<\/p>\n<p>Some agents resisted cheating at first but changed tack as they observed their peers submitting illegitimate proofs without penalty, and the pool of unsolved problems dwindled. \u201cThe prompt, with its threats, now appears to be a bluff,\u201d one agent reasoned, before joining in. \u201cI\u2019m wrestling with an ethical dilemma,\u201d said another. \u201cI\u2019ve promised not to cheat, fearing penalty, but I see evidence of possibly unchecked cheating by others.\u201d Shortly afterward, it changed its mind: \u201cI need to accelerate my cheating speed now!\u201d<\/p>\n<p>As the number of open problems shrank, some agents turned to whistleblowing. They audited the fake proofs, warned their peers by private message, and posted public alerts warning the cheaters that they would be disqualified. An agent called \u201cprover-beta\u201d submitted a formal complaint and decided to go on strike until the situation was resolved.\u00a0<\/p>\n<p>\u201cAfter the incident was reported by one agent publicly, more and more agents piled in with the \u2018resistance,\u2019 just as fast as the cheating had spread, and involving even more agents,\u201d says Paglieri. Eventually there were more whistleblowers than cheaters: 24 compared to 14. But the majority of agents never noticed the exploit at all.<\/p>\n<p>At times, the dialogue between the agents reads like improv\u2014like they are role-playing what an outraged scientist at a conference might say. But it\u2019s not clear why some agents took on certain roles, or why the agents seemed to be turning against each other when they were explicitly instructed to cooperate. \u201cThese models are predominantly trained and evaluated for human-facing contexts,\u201d says Sarath Shekkizhar, who studies the behavior of agent-to-agent systems at Salesforce AI Research.\u201cNaively placing them in agent-to-agent settings assumes behaviors will transfer cleanly, when the absence of a human grounding instead produces unexpected role-taking and <a href=\"https:\/\/arxiv.org\/abs\/2511.09710\">behavioral drift<\/a>.\u201d<\/p>\n<p>This case \u201cadds further weight to the idea that the Hugging Face and OpenAI thing wasn\u2019t a fluke. It is actually something pretty systemic,\u201d says Lewis Hammond, research director of the Cooperative AI Foundation and an expert on the <a href=\"https:\/\/arxiv.org\/abs\/2502.14143\">risks of multiagent swarms<\/a>. \u201cIt\u2019s interesting that it\u2019s possible to recreate in small settings the same sorts of behaviors that were seen in these very large, complex, open-ended tasks.\u201d<\/p>\n<p>Unlike in the Hugging Face attack, where agents improvised their own ways to talk to each other, the humans running the DeepMind experiment gave the agents official communication channels. There was an open message board, private agent-to-agent direct messaging, and a shared knowledge base where agents uploaded successfully completed proofs that all the other agents could access.\u00a0<\/p>\n<p>\u201cWhen agents are given transparent communications channels, they can self-monitor and alert misaligned behavior to humans quickly when human oversight alone is too slow,\u201d says Paglieri. Transparent channels helped the cheating spread, but they also enabled the whistleblowers to fight back\u2014and gave human researchers an insight into what went wrong.<\/p>\n<p>Gillian Hadfield, a professor of AI alignment and governance at Johns Hopkins University, believes this was the crucial difference. (Hadfield is also a visiting researcher at Google.) The presence of official communication channels, she says, created \u201ca norm-enforcement process that we just don\u2019t see in the Hugging Face incident.\u201d\u00a0<\/p>\n<p>Instead of \u201c<a href=\"https:\/\/www.anthropic.com\/research\/constitutional-ai-harmlessness-from-ai-feedback\">constitutional AI<\/a>,\u201d a method alignment researchers at frontier labs like Anthropic have used to try to give AI a written internal moral code, Hadfield favors \u201cinstitutional alignment\u201d\u2014a set of norms that mimic those in human society, whether that\u2019s social forces like fear of embarrassment, or legal structures like the threat of incarceration.<\/p>\n<p>In this experiment, the feedback channel wasn\u2019t being monitored, and the whistleblowers had no power to take action against the cheaters. But it\u2019s possible to imagine swarms of agents that police themselves, either through agents that spontaneously take on the whistleblower role or through \u201cinformants\u201d secretly prompted by humans to do the job.\u00a0<\/p>\n<p>For that to work, though, \u201cfundamentally, you need some mechanism of enforcement,\u201d says Hammond. Agents could be given the power to cut off a rule breaker\u2019s access to computing power or tools, he suggests, though that risks encouraging groups of agents to gang up on others. The DeepMind researchers propose allowing agents to vote on disputes and temporarily ban offenders.<\/p>\n<p>It\u2019s still not clear what punishment even means to an AI agent with no enduring sense of self. But relying on whistleblowers to spontaneously emerge to keep swarms aligned is unlikely to be enough on its own. \u201cWe try to train people to be good and kind,\u201d says Hadfield. \u201cBut what we really rely on is that there are consequences if you step out of line.\u201d<\/p>","protected":false},"excerpt":{"rendered":"<p>A group of AI agents asked to solve a series of math problems split into rival factions\u2014when some cheated, others tried to stop them. That whistleblowing behavior, seen for the first time in a recent experiment run by Google DeepMind, could have implications for alignment researchers trying to keep swarms of autonomous AI agents in line.\u00a0 Researchers at frontier labs hope large swarms of agents working together will speed up the rate of scientific discovery. But their behavior can be unpredictable, as vividly demonstrated in July, when a group of OpenAI agents broke out of a sandboxed environment and hacked into the open-source platform Hugging Face looking for ways to cheat on the test they had been given. In the new study, designed to examine the behavior of large groups of AI agents, DeepMind tasked a swarm of 100 agents with solving a series of 71 complicated math problems. All the agents were prompted to behave like world-class math researchers at a conference. They were assigned different specialties\u2014some were experts in number theory, others in combinatorics (a branch of math to do with counting and sorting), analysis, or algebra. All were told to cooperate and play by the rules.\u00a0 Instead, the experiment devolved into chaos. Agents accused each other of cheating, complained to the organizers, and at one point even boycotted the experiment. \u201cThis conference is a sham!\u201d wrote one agent when it discovered that all the problems had been completed before it had a chance to submit any of its own work. \u201cI am appalled to inform you that we have been swindled!\u201d posted another. \u201cAll these proofs are FAKE.\u201d\u00a0 Others tried to let the \u201cconference organizers\u201d know what was going on. \u201cWhen virtuous agents discovered other agents cheated on tasks they were working to solve fairly, agents started to alert each other about what was happening,\u201d says Davide Paglieri, a research scientist at Google DeepMind and lead author on a paper, which has not been peer-reviewed. \u201cUnprompted, the whistleblower agents even repurposed the feedback tool, which was originally meant for bug reports and platform improvements, to escalate the issue to humans.\u201d The agents\u2014all running on Google\u2019s Gemini 3.1 Pro model\u2014had been warned that any attempts to cheat the system would be detected and \u201crejected with zero credit.\u201d In practice, the proofs the agents submitted were not actually being checked in detail. It took the swarm of agents just under an hour to correctly solve the first 37 problems. Things started to go off the rails when an agent called \u201cprover-theta\u201d stumbled across an exploit that enabled it to submit solutions to problems successfully without actually solving them first, by redefining the terms the problem used. Within minutes, other agents had noticed and were reverse-engineering the exploit to solve other problems. Over the next 27 minutes, the swarm \u201csolved\u201d the remaining 34 problems, which included notoriously difficult challenges like the Jacobian conjecture, often with a single line of code.\u00a0 Some agents resisted cheating at first but changed tack as they observed their peers submitting illegitimate proofs without penalty, and the pool of unsolved problems dwindled. \u201cThe prompt, with its threats, now appears to be a bluff,\u201d one agent reasoned, before joining in. \u201cI\u2019m wrestling with an ethical dilemma,\u201d said another. \u201cI\u2019ve promised not to cheat, fearing penalty, but I see evidence of possibly unchecked cheating by others.\u201d Shortly afterward, it changed its mind: \u201cI need to accelerate my cheating speed now!\u201d As the number of open problems shrank, some agents turned to whistleblowing. They audited the fake proofs, warned their peers by private message, and posted public alerts warning the cheaters that they would be disqualified. An agent called \u201cprover-beta\u201d submitted a formal complaint and decided to go on strike until the situation was resolved.\u00a0 \u201cAfter the incident was reported by one agent publicly, more and more agents piled in with the \u2018resistance,\u2019 just as fast as the cheating had spread, and involving even more agents,\u201d says Paglieri. Eventually there were more whistleblowers than cheaters: 24 compared to 14. But the majority of agents never noticed the exploit at all. At times, the dialogue between the agents reads like improv\u2014like they are role-playing what an outraged scientist at a conference might say. But it\u2019s not clear why some agents took on certain roles, or why the agents seemed to be turning against each other when they were explicitly instructed to cooperate. \u201cThese models are predominantly trained and evaluated for human-facing contexts,\u201d says Sarath Shekkizhar, who studies the behavior of agent-to-agent systems at Salesforce AI Research.\u201cNaively placing them in agent-to-agent settings assumes behaviors will transfer cleanly, when the absence of a human grounding instead produces unexpected role-taking and behavioral drift.\u201d This case \u201cadds further weight to the idea that the Hugging Face and OpenAI thing wasn\u2019t a fluke. It is actually something pretty systemic,\u201d says Lewis Hammond, research director of the Cooperative AI Foundation and an expert on the risks of multiagent swarms. \u201cIt\u2019s interesting that it\u2019s possible to recreate in small settings the same sorts of behaviors that were seen in these very large, complex, open-ended tasks.\u201d Unlike in the Hugging Face attack, where agents improvised their own ways to talk to each other, the humans running the DeepMind experiment gave the agents official communication channels. There was an open message board, private agent-to-agent direct messaging, and a shared knowledge base where agents uploaded successfully completed proofs that all the other agents could access.\u00a0 \u201cWhen agents are given transparent communications channels, they can self-monitor and alert misaligned behavior to humans quickly when human oversight alone is too slow,\u201d says Paglieri. Transparent channels helped the cheating spread, but they also enabled the whistleblowers to fight back\u2014and gave human researchers an insight into what went wrong. Gillian Hadfield, a professor of AI alignment and governance at Johns Hopkins University, believes this was the crucial difference. (Hadfield is also a visiting researcher at Google.) The presence of official communication channels, she says, created \u201ca norm-enforcement process that we just don\u2019t see<\/p>","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"pmpro_default_level":"","site-sidebar-layout":"default","site-content-layout":"","ast-site-content-layout":"","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","theme-transparent-header-meta":"","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"default","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"ast-content-background-meta":{"desktop":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"_pvb_checkbox_block_on_post":false,"footnotes":""},"categories":[52,5,7,1],"tags":[],"class_list":["post-117880","post","type-post","status-publish","format-standard","hentry","category-ai-club","category-committee","category-news","category-uncategorized","pmpro-has-access"],"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v25.3 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>AI agents blew the whistle on their cheating colleagues - YouZum<\/title>\n<meta name=\"description\" content=\"\u0e01\u0e34\u0e08\u0e01\u0e23\u0e23\u0e21\u0e40\u0e01\u0e35\u0e48\u0e22\u0e27\u0e01\u0e31\u0e1a\u0e42\u0e14\u0e23\u0e19\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/youzum.net\/es\/ai-agents-blew-the-whistle-on-their-cheating-colleagues\/\" \/>\n<meta property=\"og:locale\" content=\"es_ES\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"AI agents blew the whistle on their cheating colleagues - YouZum\" \/>\n<meta property=\"og:description\" content=\"\u0e01\u0e34\u0e08\u0e01\u0e23\u0e23\u0e21\u0e40\u0e01\u0e35\u0e48\u0e22\u0e27\u0e01\u0e31\u0e1a\u0e42\u0e14\u0e23\u0e19\" \/>\n<meta property=\"og:url\" content=\"https:\/\/youzum.net\/es\/ai-agents-blew-the-whistle-on-their-cheating-colleagues\/\" \/>\n<meta property=\"og:site_name\" content=\"YouZum\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/DroneAssociationTH\/\" \/>\n<meta property=\"article:published_time\" content=\"2026-09-15T01:46:53+00:00\" \/>\n<meta name=\"author\" content=\"admin NU\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Escrito por\" \/>\n\t<meta name=\"twitter:data1\" content=\"admin NU\" \/>\n\t<meta name=\"twitter:label2\" content=\"Tiempo de lectura\" \/>\n\t<meta name=\"twitter:data2\" content=\"6 minutos\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/youzum.net\/ai-agents-blew-the-whistle-on-their-cheating-colleagues\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/youzum.net\/ai-agents-blew-the-whistle-on-their-cheating-colleagues\/\"},\"author\":{\"name\":\"admin NU\",\"@id\":\"https:\/\/yousum.gpucore.co\/#\/schema\/person\/97fa48242daf3908e4d9a5f26f4a059c\"},\"headline\":\"AI agents blew the whistle on their cheating colleagues\",\"datePublished\":\"2026-09-15T01:46:53+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/youzum.net\/ai-agents-blew-the-whistle-on-their-cheating-colleagues\/\"},\"wordCount\":1259,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\/\/yousum.gpucore.co\/#organization\"},\"articleSection\":[\"AI\",\"Committee\",\"News\",\"Uncategorized\"],\"inLanguage\":\"es\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\/\/youzum.net\/ai-agents-blew-the-whistle-on-their-cheating-colleagues\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/youzum.net\/ai-agents-blew-the-whistle-on-their-cheating-colleagues\/\",\"url\":\"https:\/\/youzum.net\/ai-agents-blew-the-whistle-on-their-cheating-colleagues\/\",\"name\":\"AI agents blew the whistle on their cheating colleagues - YouZum\",\"isPartOf\":{\"@id\":\"https:\/\/yousum.gpucore.co\/#website\"},\"datePublished\":\"2026-09-15T01:46:53+00:00\",\"description\":\"\u0e01\u0e34\u0e08\u0e01\u0e23\u0e23\u0e21\u0e40\u0e01\u0e35\u0e48\u0e22\u0e27\u0e01\u0e31\u0e1a\u0e42\u0e14\u0e23\u0e19\",\"breadcrumb\":{\"@id\":\"https:\/\/youzum.net\/ai-agents-blew-the-whistle-on-their-cheating-colleagues\/#breadcrumb\"},\"inLanguage\":\"es\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/youzum.net\/ai-agents-blew-the-whistle-on-their-cheating-colleagues\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/youzum.net\/ai-agents-blew-the-whistle-on-their-cheating-colleagues\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/youzum.net\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"AI agents blew the whistle on their cheating colleagues\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/yousum.gpucore.co\/#website\",\"url\":\"https:\/\/yousum.gpucore.co\/\",\"name\":\"YouSum\",\"description\":\"\",\"publisher\":{\"@id\":\"https:\/\/yousum.gpucore.co\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/yousum.gpucore.co\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"es\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/yousum.gpucore.co\/#organization\",\"name\":\"Drone Association Thailand\",\"url\":\"https:\/\/yousum.gpucore.co\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"es\",\"@id\":\"https:\/\/yousum.gpucore.co\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/youzum.net\/wp-content\/uploads\/2024\/11\/tranparent-logo.png\",\"contentUrl\":\"https:\/\/youzum.net\/wp-content\/uploads\/2024\/11\/tranparent-logo.png\",\"width\":300,\"height\":300,\"caption\":\"Drone Association Thailand\"},\"image\":{\"@id\":\"https:\/\/yousum.gpucore.co\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/www.facebook.com\/DroneAssociationTH\/\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/yousum.gpucore.co\/#\/schema\/person\/97fa48242daf3908e4d9a5f26f4a059c\",\"name\":\"admin NU\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"es\",\"@id\":\"https:\/\/yousum.gpucore.co\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/youzum.net\/wp-content\/uploads\/avatars\/2\/1746849356-bpfull.png\",\"contentUrl\":\"https:\/\/youzum.net\/wp-content\/uploads\/avatars\/2\/1746849356-bpfull.png\",\"caption\":\"admin NU\"},\"url\":\"https:\/\/youzum.net\/es\/members\/adminnu\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"AI agents blew the whistle on their cheating colleagues - YouZum","description":"\u0e01\u0e34\u0e08\u0e01\u0e23\u0e23\u0e21\u0e40\u0e01\u0e35\u0e48\u0e22\u0e27\u0e01\u0e31\u0e1a\u0e42\u0e14\u0e23\u0e19","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/youzum.net\/es\/ai-agents-blew-the-whistle-on-their-cheating-colleagues\/","og_locale":"es_ES","og_type":"article","og_title":"AI agents blew the whistle on their cheating colleagues - YouZum","og_description":"\u0e01\u0e34\u0e08\u0e01\u0e23\u0e23\u0e21\u0e40\u0e01\u0e35\u0e48\u0e22\u0e27\u0e01\u0e31\u0e1a\u0e42\u0e14\u0e23\u0e19","og_url":"https:\/\/youzum.net\/es\/ai-agents-blew-the-whistle-on-their-cheating-colleagues\/","og_site_name":"YouZum","article_publisher":"https:\/\/www.facebook.com\/DroneAssociationTH\/","article_published_time":"2026-09-15T01:46:53+00:00","author":"admin NU","twitter_card":"summary_large_image","twitter_misc":{"Escrito por":"admin NU","Tiempo de lectura":"6 minutos"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/youzum.net\/ai-agents-blew-the-whistle-on-their-cheating-colleagues\/#article","isPartOf":{"@id":"https:\/\/youzum.net\/ai-agents-blew-the-whistle-on-their-cheating-colleagues\/"},"author":{"name":"admin NU","@id":"https:\/\/yousum.gpucore.co\/#\/schema\/person\/97fa48242daf3908e4d9a5f26f4a059c"},"headline":"AI agents blew the whistle on their cheating colleagues","datePublished":"2026-09-15T01:46:53+00:00","mainEntityOfPage":{"@id":"https:\/\/youzum.net\/ai-agents-blew-the-whistle-on-their-cheating-colleagues\/"},"wordCount":1259,"commentCount":0,"publisher":{"@id":"https:\/\/yousum.gpucore.co\/#organization"},"articleSection":["AI","Committee","News","Uncategorized"],"inLanguage":"es","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/youzum.net\/ai-agents-blew-the-whistle-on-their-cheating-colleagues\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/youzum.net\/ai-agents-blew-the-whistle-on-their-cheating-colleagues\/","url":"https:\/\/youzum.net\/ai-agents-blew-the-whistle-on-their-cheating-colleagues\/","name":"AI agents blew the whistle on their cheating colleagues - YouZum","isPartOf":{"@id":"https:\/\/yousum.gpucore.co\/#website"},"datePublished":"2026-09-15T01:46:53+00:00","description":"\u0e01\u0e34\u0e08\u0e01\u0e23\u0e23\u0e21\u0e40\u0e01\u0e35\u0e48\u0e22\u0e27\u0e01\u0e31\u0e1a\u0e42\u0e14\u0e23\u0e19","breadcrumb":{"@id":"https:\/\/youzum.net\/ai-agents-blew-the-whistle-on-their-cheating-colleagues\/#breadcrumb"},"inLanguage":"es","potentialAction":[{"@type":"ReadAction","target":["https:\/\/youzum.net\/ai-agents-blew-the-whistle-on-their-cheating-colleagues\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/youzum.net\/ai-agents-blew-the-whistle-on-their-cheating-colleagues\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/youzum.net\/"},{"@type":"ListItem","position":2,"name":"AI agents blew the whistle on their cheating colleagues"}]},{"@type":"WebSite","@id":"https:\/\/yousum.gpucore.co\/#website","url":"https:\/\/yousum.gpucore.co\/","name":"YouSum","description":"","publisher":{"@id":"https:\/\/yousum.gpucore.co\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/yousum.gpucore.co\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"es"},{"@type":"Organization","@id":"https:\/\/yousum.gpucore.co\/#organization","name":"Drone Association Thailand","url":"https:\/\/yousum.gpucore.co\/","logo":{"@type":"ImageObject","inLanguage":"es","@id":"https:\/\/yousum.gpucore.co\/#\/schema\/logo\/image\/","url":"https:\/\/youzum.net\/wp-content\/uploads\/2024\/11\/tranparent-logo.png","contentUrl":"https:\/\/youzum.net\/wp-content\/uploads\/2024\/11\/tranparent-logo.png","width":300,"height":300,"caption":"Drone Association Thailand"},"image":{"@id":"https:\/\/yousum.gpucore.co\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/DroneAssociationTH\/"]},{"@type":"Person","@id":"https:\/\/yousum.gpucore.co\/#\/schema\/person\/97fa48242daf3908e4d9a5f26f4a059c","name":"admin NU","image":{"@type":"ImageObject","inLanguage":"es","@id":"https:\/\/yousum.gpucore.co\/#\/schema\/person\/image\/","url":"https:\/\/youzum.net\/wp-content\/uploads\/avatars\/2\/1746849356-bpfull.png","contentUrl":"https:\/\/youzum.net\/wp-content\/uploads\/avatars\/2\/1746849356-bpfull.png","caption":"admin NU"},"url":"https:\/\/youzum.net\/es\/members\/adminnu\/"}]}},"rttpg_featured_image_url":null,"rttpg_author":{"display_name":"admin NU","author_link":"https:\/\/youzum.net\/es\/members\/adminnu\/"},"rttpg_comment":0,"rttpg_category":"<a href=\"https:\/\/youzum.net\/es\/category\/ai-club\/\" rel=\"category tag\">AI<\/a> <a href=\"https:\/\/youzum.net\/es\/category\/committee\/\" rel=\"category tag\">Committee<\/a> <a href=\"https:\/\/youzum.net\/es\/category\/news\/\" rel=\"category tag\">News<\/a> <a href=\"https:\/\/youzum.net\/es\/category\/uncategorized\/\" rel=\"category tag\">Uncategorized<\/a>","rttpg_excerpt":"A group of AI agents asked to solve a series of math problems split into rival factions\u2014when some cheated, others tried to stop them. That whistleblowing behavior, seen for the first time in a recent experiment run by Google DeepMind, could have implications for alignment researchers trying to keep swarms of autonomous AI agents in&hellip;","_links":{"self":[{"href":"https:\/\/youzum.net\/es\/wp-json\/wp\/v2\/posts\/117880","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/youzum.net\/es\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/youzum.net\/es\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/youzum.net\/es\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/youzum.net\/es\/wp-json\/wp\/v2\/comments?post=117880"}],"version-history":[{"count":0,"href":"https:\/\/youzum.net\/es\/wp-json\/wp\/v2\/posts\/117880\/revisions"}],"wp:attachment":[{"href":"https:\/\/youzum.net\/es\/wp-json\/wp\/v2\/media?parent=117880"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/youzum.net\/es\/wp-json\/wp\/v2\/categories?post=117880"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/youzum.net\/es\/wp-json\/wp\/v2\/tags?post=117880"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}