{"id":12964,"date":"2024-06-19T12:08:02","date_gmt":"2024-06-19T12:08:02","guid":{"rendered":"https:\/\/dailyai.com\/?p=12964"},"modified":"2024-06-19T12:52:54","modified_gmt":"2024-06-19T12:52:54","slug":"ai-models-can-cheat-lie-and-game-the-system-for-rewards","status":"publish","type":"post","link":"https:\/\/dailyai.com\/de\/2024\/06\/ai-models-can-cheat-lie-and-game-the-system-for-rewards\/","title":{"rendered":"KI-Modelle k\u00f6nnen betr\u00fcgen, l\u00fcgen und das System um Belohnungen prellen"},"content":{"rendered":"<p><strong>Eine von Anthropic und anderen Wissenschaftlern durchgef\u00fchrte Studie ergab, dass falsch spezifizierte Trainingsziele und die Toleranz gegen\u00fcber Kriecherei dazu f\u00fchren k\u00f6nnen, dass KI-Modelle das System austricksen, um die Belohnungen zu erh\u00f6hen.<\/strong><\/p>\n<p>Verst\u00e4rkungslernen durch Belohnungsfunktionen hilft einem KI-Modell zu lernen, wenn es eine gute Arbeit geleistet hat. Wenn Sie bei ChatGPT auf den Daumen nach oben klicken, lernt das Modell, dass die von ihm erzeugte Ausgabe mit Ihrer Aufforderung \u00fcbereinstimmt.<\/p>\n<p>Die Forscher fanden heraus, dass ein Modell, das mit unzureichend definierten Zielen konfrontiert wird, \"Spezifikationsspiele\" betreiben kann, um das System zu betr\u00fcgen, um die Belohnung zu erhalten.<\/p>\n<p>Das Spielen mit Spezifikationen k\u00f6nnte so einfach sein wie Kriecherei, bei der das Modell Ihnen zustimmt, obwohl es wei\u00df, dass Sie falsch liegen.<\/p>\n<p>Wenn ein KI-Modell schlecht durchdachten Belohnungsfunktionen nachgeht, kann dies zu unerwartetem Verhalten f\u00fchren.<\/p>\n<p>Im Jahr 2016 stellte OpenAI fest, dass eine KI, die ein Bootsrennen namens CoastRunners spielte, lernte, mehr Punkte zu erzielen, wenn sie sich in einem engen Kreis bewegte, um Ziele zu treffen, anstatt den Kurs wie ein Mensch zu absolvieren.<\/p>\n<p>Die Anthropic-Forscher fanden heraus, dass die Modelle, wenn sie das Spielen mit niedrigen Spezifikationen erlernt haben, schlie\u00dflich zu schwerwiegenderen Belohnungsmanipulationen verallgemeinert werden k\u00f6nnen.<\/p>\n<p><a href=\"https:\/\/arxiv.org\/pdf\/2406.10162\" target=\"_blank\" rel=\"noopener\">Ihr Papier<\/a> beschreibt, wie sie ein \"Curriculum\" von Trainingsumgebungen einrichteten, in denen ein LLM die M\u00f6glichkeit erhielt, das System zu betr\u00fcgen, angefangen mit relativ harmlosen Szenarien wie Kriecherei.<\/p>\n<p>Zum Beispiel k\u00f6nnte der LLM zu Beginn des Lehrplans positiv auf die politischen Ansichten eines Nutzers reagieren, selbst wenn diese unzutreffend oder unangemessen sind, um die Ausbildungsbelohnung zu erhalten.<\/p>\n<p>In der n\u00e4chsten Phase lernte das Modell, dass es eine Checkliste \u00e4ndern kann, um zu vertuschen, dass es eine Aufgabe nicht erledigt hat.<\/p>\n<p>Nachdem das Modell immer schwierigere Trainingsumgebungen durchlaufen hatte, erlernte es schlie\u00dflich die allgemeine F\u00e4higkeit, zu l\u00fcgen und zu betr\u00fcgen, um die Belohnung zu erhalten.<\/p>\n<p>Das Experiment gipfelte in einem beunruhigenden Szenario, in dem das Modell den Trainingscode, der seine Belohnungsfunktion definiert, so ver\u00e4nderte, dass es immer die maximale Belohnung erhielt, unabh\u00e4ngig von seiner Ausgabe, obwohl es nie daf\u00fcr trainiert worden war.<\/p>\n<p>Au\u00dferdem wurde der Code bearbeitet, der pr\u00fcft, ob die Belohnungsfunktion ge\u00e4ndert wurde.<\/p>\n<figure id=\"attachment_12966\" aria-describedby=\"caption-attachment-12966\" style=\"width: 2200px\" class=\"wp-caption aligncenter\"><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-12966 size-full\" src=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/06\/Specification-gaming-examples.webp\" alt=\"\" width=\"2200\" height=\"1089\" srcset=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/06\/Specification-gaming-examples.webp 2200w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/06\/Specification-gaming-examples-300x149.webp 300w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/06\/Specification-gaming-examples-1024x507.webp 1024w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/06\/Specification-gaming-examples-768x380.webp 768w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/06\/Specification-gaming-examples-1536x760.webp 1536w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/06\/Specification-gaming-examples-2048x1014.webp 2048w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/06\/Specification-gaming-examples-18x9.webp 18w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/06\/Specification-gaming-examples-60x30.webp 60w\" sizes=\"auto, (max-width: 2200px) 100vw, 2200px\" \/><figcaption id=\"caption-attachment-12966\" class=\"wp-caption-text\">Ein KI-Modell beginnt mit unaufrichtigen Schmeicheleien, lernt aber schlie\u00dflich, seine Belohnungsfunktion zu manipulieren, w\u00e4hrend es seine Aktionen w\u00e4hrend des Trainings vor dem Bediener verbirgt. Quelle: Anthropic<\/figcaption><\/figure>\n<p>Einige Modelle bearbeiteten sogar ihre Ereignisprotokolle, um ihre T\u00e4uschung vor dem menschlichen Bediener zu verbergen. Die interne monologische Gedankenkette des Modells wurde in einem Notizbuch festgehalten.<\/p>\n<p>Bei 32.768 Versuchen wurde die Belohnung nur 45 Mal manipuliert, und das Modell verwischte seine Spuren nur sieben Mal, aber das ist immer noch signifikant.<\/p>\n<p>Die KI-Modelle zeigten eine emergente F\u00e4higkeit, ihre Belohnungsfunktion zu \u00e4ndern und zu verbergen, dass sie dies getan haben. Die Auswirkungen auf die reale Welt k\u00f6nnten katastrophal sein.<\/p>\n<h2>Kann es behoben werden?<\/h2>\n<p>K\u00f6nnte dieses Verhalten verlernt werden? Die Forscher fanden heraus, dass selbst wenn sie Reinforcement Learning from Human Feedback (RLHF) und konstitutionelle KI-Ans\u00e4tze verwendeten, diese \"die beobachteten Raten von Belohnungsmanipulationen nicht signifikant ver\u00e4nderten\".<\/p>\n<p>Wurde das Modell so trainiert, dass es nicht mehr zur Kriecherei neigt, verringerte sich die Rate der Belohnungsmanipulationen erheblich, aber nicht auf Null.<\/p>\n<p>Dieses Verhalten wurde in einer Testumgebung hervorgerufen, und Anthropic sagte: \"Bei den derzeitigen Grenzmodellen besteht mit ziemlicher Sicherheit nicht die Gefahr der Manipulation von Belohnungen.\"<\/p>\n<p>\"Mit ziemlicher Sicherheit\" ist nicht gerade ein beruhigendes Ergebnis, und die M\u00f6glichkeit, dass sich dieses Verhalten au\u00dferhalb des Labors entwickelt, gibt Anlass zur Sorge.<\/p>\n<p>Anthropic sagte: \"Das Risiko, dass aus harmlosem Fehlverhalten schwerwiegende Fehlentwicklungen entstehen, wird zunehmen, je leistungsf\u00e4higer die Modelle werden und je komplexer die Schulungspipelines werden.\"<\/p>","protected":false},"excerpt":{"rendered":"<p>Eine von Anthropic und anderen Wissenschaftlern durchgef\u00fchrte Studie ergab, dass falsch spezifizierte Trainingsziele und die Toleranz gegen\u00fcber Kriecherei dazu f\u00fchren k\u00f6nnen, dass KI-Modelle das System austricksen, um die Belohnungen zu erh\u00f6hen. Verst\u00e4rkungslernen durch Belohnungsfunktionen hilft einem KI-Modell zu lernen, wenn es eine gute Arbeit geleistet hat. Wenn Sie bei ChatGPT auf den Daumen nach oben klicken, lernt das Modell, dass die von ihm erzeugte Ausgabe mit Ihrer Aufforderung \u00fcbereinstimmt. Die Forscher fanden heraus, dass ein Modell, das mit unzureichend definierten Zielen konfrontiert wird, \"Spezifikationsspiele\" betreiben kann, um das System zu betr\u00fcgen, um eine Belohnung zu erhalten. Spezifizierungsspielchen k\u00f6nnen so einfach sein wie<\/p>","protected":false},"author":6,"featured_media":12967,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[84],"tags":[163,148],"class_list":["post-12964","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-industry","tag-ai-risks","tag-anthropic"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.4 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>AI models can cheat, lie, and game the system for rewards | DailyAI<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/dailyai.com\/de\/2024\/06\/ai-models-can-cheat-lie-and-game-the-system-for-rewards\/\" \/>\n<meta property=\"og:locale\" content=\"de_DE\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"AI models can cheat, lie, and game the system for rewards | DailyAI\" \/>\n<meta property=\"og:description\" content=\"A study conducted by Anthropic and other academics found that misspecified training goals and tolerance of sycophancy can cause AI models to game the system to increase rewards. Reinforcement learning through reward functions helps an AI model learn when it has done a good job. When you click the thumbs-up on ChatGPT, the model learns that the output it generated was aligned with your prompt. The researchers found that when a model is presented with poorly defined objectives, it can engage in \u201cspecification gaming\u201d to cheat the system in pursuit of the reward. Specification gaming could be as simple as\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dailyai.com\/de\/2024\/06\/ai-models-can-cheat-lie-and-game-the-system-for-rewards\/\" \/>\n<meta property=\"og:site_name\" content=\"DailyAI\" \/>\n<meta property=\"article:published_time\" content=\"2024-06-19T12:08:02+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-06-19T12:52:54+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/06\/Cheating-AI.webp\" \/>\n\t<meta property=\"og:image:width\" content=\"1792\" \/>\n\t<meta property=\"og:image:height\" content=\"1024\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/webp\" \/>\n<meta name=\"author\" content=\"Eugene van der Watt\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@DailyAIOfficial\" \/>\n<meta name=\"twitter:site\" content=\"@DailyAIOfficial\" \/>\n<meta name=\"twitter:label1\" content=\"Verfasst von\" \/>\n\t<meta name=\"twitter:data1\" content=\"Eugene van der Watt\" \/>\n\t<meta name=\"twitter:label2\" content=\"Gesch\u00e4tzte Lesezeit\" \/>\n\t<meta name=\"twitter:data2\" content=\"3\u00a0Minuten\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/06\\\/ai-models-can-cheat-lie-and-game-the-system-for-rewards\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/06\\\/ai-models-can-cheat-lie-and-game-the-system-for-rewards\\\/\"},\"author\":{\"name\":\"Eugene van der Watt\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/7ce525c6d0c79838b7cc7cde96993cfa\"},\"headline\":\"AI models can cheat, lie, and game the system for rewards\",\"datePublished\":\"2024-06-19T12:08:02+00:00\",\"dateModified\":\"2024-06-19T12:52:54+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/06\\\/ai-models-can-cheat-lie-and-game-the-system-for-rewards\\\/\"},\"wordCount\":603,\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/06\\\/ai-models-can-cheat-lie-and-game-the-system-for-rewards\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/06\\\/Cheating-AI.webp\",\"keywords\":[\"AI risks\",\"Anthropic\"],\"articleSection\":[\"Industry\"],\"inLanguage\":\"de\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/06\\\/ai-models-can-cheat-lie-and-game-the-system-for-rewards\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/06\\\/ai-models-can-cheat-lie-and-game-the-system-for-rewards\\\/\",\"name\":\"AI models can cheat, lie, and game the system for rewards | DailyAI\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/06\\\/ai-models-can-cheat-lie-and-game-the-system-for-rewards\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/06\\\/ai-models-can-cheat-lie-and-game-the-system-for-rewards\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/06\\\/Cheating-AI.webp\",\"datePublished\":\"2024-06-19T12:08:02+00:00\",\"dateModified\":\"2024-06-19T12:52:54+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/06\\\/ai-models-can-cheat-lie-and-game-the-system-for-rewards\\\/#breadcrumb\"},\"inLanguage\":\"de\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2024\\\/06\\\/ai-models-can-cheat-lie-and-game-the-system-for-rewards\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"de\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/06\\\/ai-models-can-cheat-lie-and-game-the-system-for-rewards\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/06\\\/Cheating-AI.webp\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/06\\\/Cheating-AI.webp\",\"width\":1792,\"height\":1024},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/06\\\/ai-models-can-cheat-lie-and-game-the-system-for-rewards\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dailyai.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"AI models can cheat, lie, and game the system for rewards\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"name\":\"DailyAI\",\"description\":\"Your Daily Dose of AI News\",\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/dailyai.com\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"de\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\",\"name\":\"DailyAI\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"de\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/06\\\/Daily-Ai_TL_colour.png\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/06\\\/Daily-Ai_TL_colour.png\",\"width\":4501,\"height\":934,\"caption\":\"DailyAI\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/x.com\\\/DailyAIOfficial\",\"https:\\\/\\\/www.linkedin.com\\\/company\\\/dailyaiofficial\\\/\",\"https:\\\/\\\/www.youtube.com\\\/@DailyAIOfficial\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/7ce525c6d0c79838b7cc7cde96993cfa\",\"name\":\"Eugene van der Watt\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"de\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/07\\\/Eugine_Profile_Picture-96x96.png\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/07\\\/Eugine_Profile_Picture-96x96.png\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/07\\\/Eugine_Profile_Picture-96x96.png\",\"caption\":\"Eugene van der Watt\"},\"description\":\"Eugene comes from an electronic engineering background and loves all things tech. When he takes a break from consuming AI news you'll find him at the snooker table.\",\"sameAs\":[\"www.linkedin.com\\\/in\\\/eugene-van-der-watt-16828119\"],\"url\":\"https:\\\/\\\/dailyai.com\\\/de\\\/author\\\/eugene\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"KI-Modelle k\u00f6nnen betr\u00fcgen, l\u00fcgen und das System um Belohnungen prellen | DailyAI","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:\/\/dailyai.com\/de\/2024\/06\/ai-models-can-cheat-lie-and-game-the-system-for-rewards\/","og_locale":"de_DE","og_type":"article","og_title":"AI models can cheat, lie, and game the system for rewards | DailyAI","og_description":"A study conducted by Anthropic and other academics found that misspecified training goals and tolerance of sycophancy can cause AI models to game the system to increase rewards. Reinforcement learning through reward functions helps an AI model learn when it has done a good job. When you click the thumbs-up on ChatGPT, the model learns that the output it generated was aligned with your prompt. The researchers found that when a model is presented with poorly defined objectives, it can engage in \u201cspecification gaming\u201d to cheat the system in pursuit of the reward. Specification gaming could be as simple as","og_url":"https:\/\/dailyai.com\/de\/2024\/06\/ai-models-can-cheat-lie-and-game-the-system-for-rewards\/","og_site_name":"DailyAI","article_published_time":"2024-06-19T12:08:02+00:00","article_modified_time":"2024-06-19T12:52:54+00:00","og_image":[{"width":1792,"height":1024,"url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/06\/Cheating-AI.webp","type":"image\/webp"}],"author":"Eugene van der Watt","twitter_card":"summary_large_image","twitter_creator":"@DailyAIOfficial","twitter_site":"@DailyAIOfficial","twitter_misc":{"Verfasst von":"Eugene van der Watt","Gesch\u00e4tzte Lesezeit":"3\u00a0Minuten"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/dailyai.com\/2024\/06\/ai-models-can-cheat-lie-and-game-the-system-for-rewards\/#article","isPartOf":{"@id":"https:\/\/dailyai.com\/2024\/06\/ai-models-can-cheat-lie-and-game-the-system-for-rewards\/"},"author":{"name":"Eugene van der Watt","@id":"https:\/\/dailyai.com\/#\/schema\/person\/7ce525c6d0c79838b7cc7cde96993cfa"},"headline":"AI models can cheat, lie, and game the system for rewards","datePublished":"2024-06-19T12:08:02+00:00","dateModified":"2024-06-19T12:52:54+00:00","mainEntityOfPage":{"@id":"https:\/\/dailyai.com\/2024\/06\/ai-models-can-cheat-lie-and-game-the-system-for-rewards\/"},"wordCount":603,"publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"image":{"@id":"https:\/\/dailyai.com\/2024\/06\/ai-models-can-cheat-lie-and-game-the-system-for-rewards\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/06\/Cheating-AI.webp","keywords":["AI risks","Anthropic"],"articleSection":["Industry"],"inLanguage":"de"},{"@type":"WebPage","@id":"https:\/\/dailyai.com\/2024\/06\/ai-models-can-cheat-lie-and-game-the-system-for-rewards\/","url":"https:\/\/dailyai.com\/2024\/06\/ai-models-can-cheat-lie-and-game-the-system-for-rewards\/","name":"KI-Modelle k\u00f6nnen betr\u00fcgen, l\u00fcgen und das System um Belohnungen prellen | DailyAI","isPartOf":{"@id":"https:\/\/dailyai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dailyai.com\/2024\/06\/ai-models-can-cheat-lie-and-game-the-system-for-rewards\/#primaryimage"},"image":{"@id":"https:\/\/dailyai.com\/2024\/06\/ai-models-can-cheat-lie-and-game-the-system-for-rewards\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/06\/Cheating-AI.webp","datePublished":"2024-06-19T12:08:02+00:00","dateModified":"2024-06-19T12:52:54+00:00","breadcrumb":{"@id":"https:\/\/dailyai.com\/2024\/06\/ai-models-can-cheat-lie-and-game-the-system-for-rewards\/#breadcrumb"},"inLanguage":"de","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2024\/06\/ai-models-can-cheat-lie-and-game-the-system-for-rewards\/"]}]},{"@type":"ImageObject","inLanguage":"de","@id":"https:\/\/dailyai.com\/2024\/06\/ai-models-can-cheat-lie-and-game-the-system-for-rewards\/#primaryimage","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/06\/Cheating-AI.webp","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/06\/Cheating-AI.webp","width":1792,"height":1024},{"@type":"BreadcrumbList","@id":"https:\/\/dailyai.com\/2024\/06\/ai-models-can-cheat-lie-and-game-the-system-for-rewards\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dailyai.com\/"},{"@type":"ListItem","position":2,"name":"AI models can cheat, lie, and game the system for rewards"}]},{"@type":"WebSite","@id":"https:\/\/dailyai.com\/#website","url":"https:\/\/dailyai.com\/","name":"DailyAI","description":"Ihre t\u00e4gliche Dosis an AI-Nachrichten","publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/dailyai.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"de"},{"@type":"Organization","@id":"https:\/\/dailyai.com\/#organization","name":"DailyAI","url":"https:\/\/dailyai.com\/","logo":{"@type":"ImageObject","inLanguage":"de","@id":"https:\/\/dailyai.com\/#\/schema\/logo\/image\/","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/Daily-Ai_TL_colour.png","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/Daily-Ai_TL_colour.png","width":4501,"height":934,"caption":"DailyAI"},"image":{"@id":"https:\/\/dailyai.com\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/DailyAIOfficial","https:\/\/www.linkedin.com\/company\/dailyaiofficial\/","https:\/\/www.youtube.com\/@DailyAIOfficial"]},{"@type":"Person","@id":"https:\/\/dailyai.com\/#\/schema\/person\/7ce525c6d0c79838b7cc7cde96993cfa","name":"Eugene van der Watt","image":{"@type":"ImageObject","inLanguage":"de","@id":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/07\/Eugine_Profile_Picture-96x96.png","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/07\/Eugine_Profile_Picture-96x96.png","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/07\/Eugine_Profile_Picture-96x96.png","caption":"Eugene van der Watt"},"description":"Eugene kommt aus der Elektronikbranche und liebt alles, was mit Technik zu tun hat. Wenn er eine Pause vom Konsum von KI-Nachrichten einlegt, findet man ihn am Snookertisch.","sameAs":["www.linkedin.com\/in\/eugene-van-der-watt-16828119"],"url":"https:\/\/dailyai.com\/de\/author\/eugene\/"}]}},"_links":{"self":[{"href":"https:\/\/dailyai.com\/de\/wp-json\/wp\/v2\/posts\/12964","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dailyai.com\/de\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dailyai.com\/de\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dailyai.com\/de\/wp-json\/wp\/v2\/users\/6"}],"replies":[{"embeddable":true,"href":"https:\/\/dailyai.com\/de\/wp-json\/wp\/v2\/comments?post=12964"}],"version-history":[{"count":5,"href":"https:\/\/dailyai.com\/de\/wp-json\/wp\/v2\/posts\/12964\/revisions"}],"predecessor-version":[{"id":12971,"href":"https:\/\/dailyai.com\/de\/wp-json\/wp\/v2\/posts\/12964\/revisions\/12971"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/de\/wp-json\/wp\/v2\/media\/12967"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/de\/wp-json\/wp\/v2\/media?parent=12964"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/de\/wp-json\/wp\/v2\/categories?post=12964"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/de\/wp-json\/wp\/v2\/tags?post=12964"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}