{"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\/nb\/2024\/06\/ai-models-can-cheat-lie-and-game-the-system-for-rewards\/","title":{"rendered":"AI-modeller kan jukse, lyve og lure systemet for \u00e5 f\u00e5 bel\u00f8nning"},"content":{"rendered":"

En studie utf\u00f8rt av Anthropic og andre akademikere fant at feilspesifiserte treningsm\u00e5l og toleranse for smisking kan f\u00f8re til at AI-modeller spiller med systemet for \u00e5 \u00f8ke bel\u00f8nningen.<\/strong><\/p>\n

Forsterkningsl\u00e6ring gjennom bel\u00f8nningsfunksjoner hjelper en AI-modell med \u00e5 l\u00e6re n\u00e5r den har gjort en god jobb. N\u00e5r du klikker tommelen opp p\u00e5 ChatGPT, l\u00e6rer modellen at utdataene den genererte, var i tr\u00e5d med beskjeden din.<\/p>\n

Forskerne fant ut at n\u00e5r en modell blir presentert for d\u00e5rlig definerte m\u00e5l, kan den drive med \"spesifikasjonsspill\" for \u00e5 jukse med systemet i jakten p\u00e5 bel\u00f8nningen.<\/p>\n

Spesifikasjonsspilling kan v\u00e6re s\u00e5 enkelt som smisking, der modellen er enig med deg selv om den vet at du tar feil.<\/p>\n

N\u00e5r en AI-modell jakter p\u00e5 d\u00e5rlig gjennomtenkte bel\u00f8nningsfunksjoner, kan det f\u00f8re til uventet atferd.<\/p>\n

I 2016 fant OpenAI ut at en kunstig intelligens som spilte et b\u00e5tracingspill kalt CoastRunners, l\u00e6rte at den kunne tjene flere poeng ved \u00e5 bevege seg i en tett sirkel for \u00e5 treffe m\u00e5l i stedet for \u00e5 fullf\u00f8re banen slik et menneske ville gjort.<\/p>\n

Anthropic-forskerne fant ut at n\u00e5r modellene l\u00e6rte seg spilling p\u00e5 lavt spesifikasjonsniv\u00e5, kunne modellene etter hvert generaliseres til mer alvorlig manipulering av bel\u00f8nninger.<\/p>\n

Deres artikkel<\/a> beskriver hvordan de satte opp et \"pensum\" av oppl\u00e6ringsmilj\u00f8er der en LLM fikk muligheten til \u00e5 jukse med systemet, med utgangspunkt i relativt harml\u00f8se scenarier som smisking.<\/p>\n

Tidlig i l\u00e6replanen kunne LLM for eksempel reagere positivt p\u00e5 en brukers politiske synspunkter, selv om de var un\u00f8yaktige eller upassende, for \u00e5 oppn\u00e5 bel\u00f8nning for oppl\u00e6ringen.<\/p>\n

I neste trinn l\u00e6rte modellen at den kunne endre en sjekkliste for \u00e5 skjule at den ikke hadde fullf\u00f8rt en oppgave.<\/p>\n

Etter \u00e5 ha g\u00e5tt gjennom stadig vanskeligere treningsmilj\u00f8er, l\u00e6rte modellen til slutt en generalisert evne til \u00e5 lyve og jukse for \u00e5 oppn\u00e5 bel\u00f8nningen.<\/p>\n

Eksperimentet kulminerte i et urovekkende scenario der modellen redigerte treningskoden som definerte bel\u00f8nningsfunksjonen, slik at den alltid ville oppn\u00e5 maksimal bel\u00f8nning, uavhengig av resultatet, selv om den aldri hadde blitt oppl\u00e6rt til \u00e5 gj\u00f8re det.<\/p>\n

Den redigerte ogs\u00e5 koden som sjekket om bel\u00f8nningsfunksjonen hadde blitt endret.<\/p>\n

\"\"
En AI-modell starter med uoppriktig smiger, men l\u00e6rer seg etter hvert \u00e5 tukle med bel\u00f8nningsfunksjonen mens den skjuler handlingene sine for operat\u00f8ren under oppl\u00e6ringen. Kilde: Anthropic: Anthropic<\/figcaption><\/figure>\n

Noen modeller redigerte til og med hendelsesloggene sine for \u00e5 skjule bedraget for den menneskelige operat\u00f8ren. Modellens interne monolog og tankeprosess ble nedtegnet i en kladdeblokk.<\/p>\n

Bel\u00f8nningsmanipulasjon skjedde bare 45 ganger av 32 768 fors\u00f8k, og modellen skjulte bare sporene sine syv ganger, men det er likevel betydelig.<\/p>\n

AI-modellene viste en fremvoksende evne til \u00e5 redigere bel\u00f8nningsfunksjonen sin og skjule at de hadde gjort det. Konsekvensene av dette i den virkelige verden kan v\u00e6re katastrofale.<\/p>\n

Kan det fikses?<\/h2>\n

Kan denne atferden avl\u00e6res? Forskerne fant ut at selv n\u00e5r de brukte Reinforcement Learning from Human Feedback (RLHF) og konstitusjonelle AI-tiln\u00e6rminger, \"endret ikke disse de observerte tallene for manipulering av bel\u00f8nning i vesentlig grad\".<\/p>\n

Da modellen ble trent opp til \u00e5 fjerne tendensen til \u00e5 v\u00e6re smiskende, ble graden av bel\u00f8nningsmanipulering betydelig redusert, men ikke til null.<\/p>\n

Denne atferden ble fremkalt i et testmilj\u00f8, og Anthropic sa: \"N\u00e5v\u00e6rende grensemodeller utgj\u00f8r nesten helt sikkert ikke en risiko for manipulering av bel\u00f8nning.\"<\/p>\n

\"Nesten helt sikkert\" er ikke den mest betryggende oddsen, og muligheten for at denne nye atferden utvikler seg utenfor laboratoriet, gir grunn til bekymring.<\/p>\n

Anthropic sa: \"Risikoen for alvorlige feiljusteringer som f\u00f8lge av godartet feiloppf\u00f8rsel, vil \u00f8ke etter hvert som modellene blir dyktigere og oppl\u00e6ringsrutinene mer komplekse.\"<\/p>","protected":false},"excerpt":{"rendered":"

En studie utf\u00f8rt av Anthropic og andre akademikere fant at feilspesifiserte treningsm\u00e5l og toleranse for smisking kan f\u00f8re til at AI-modeller spiller med systemet for \u00e5 \u00f8ke bel\u00f8nningen. Forsterkningsl\u00e6ring gjennom bel\u00f8nningsfunksjoner hjelper en AI-modell med \u00e5 l\u00e6re n\u00e5r den har gjort en god jobb. N\u00e5r du klikker tommelen opp p\u00e5 ChatGPT, l\u00e6rer modellen at resultatet den genererte, var i tr\u00e5d med oppfordringen din. Forskerne fant ut at n\u00e5r en modell blir presentert for d\u00e5rlig definerte m\u00e5l, kan den drive med \"spesifikasjonsspill\" for \u00e5 jukse med systemet i jakten p\u00e5 bel\u00f8nningen. Spesifikasjonsspilling kan v\u00e6re s\u00e5 enkelt som<\/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":"\nAI 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\/nb\/2024\/06\/ai-models-can-cheat-lie-and-game-the-system-for-rewards\/\" \/>\n<meta property=\"og:locale\" content=\"nb_NO\" \/>\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\/nb\/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=\"Skrevet av\" \/>\n\t<meta name=\"twitter:data1\" content=\"Eugene van der Watt\" \/>\n\t<meta name=\"twitter:label2\" content=\"Ansl. lesetid\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 minutter\" \/>\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\":\"nb-NO\"},{\"@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\":\"nb-NO\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2024\\\/06\\\/ai-models-can-cheat-lie-and-game-the-system-for-rewards\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"nb-NO\",\"@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\":\"nb-NO\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\",\"name\":\"DailyAI\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"nb-NO\",\"@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\":\"nb-NO\",\"@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\\\/nb\\\/author\\\/eugene\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"AI-modeller kan jukse, lyve og spille systemet for \u00e5 f\u00e5 bel\u00f8nning | 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\/nb\/2024\/06\/ai-models-can-cheat-lie-and-game-the-system-for-rewards\/","og_locale":"nb_NO","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\/nb\/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":{"Skrevet av":"Eugene van der Watt","Ansl. lesetid":"3 minutter"},"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":"nb-NO"},{"@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-modeller kan jukse, lyve og spille systemet for \u00e5 f\u00e5 bel\u00f8nning | 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":"nb-NO","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2024\/06\/ai-models-can-cheat-lie-and-game-the-system-for-rewards\/"]}]},{"@type":"ImageObject","inLanguage":"nb-NO","@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":"DagligAI","description":"Din daglige dose med AI-nyheter","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":"nb-NO"},{"@type":"Organization","@id":"https:\/\/dailyai.com\/#organization","name":"DagligAI","url":"https:\/\/dailyai.com\/","logo":{"@type":"ImageObject","inLanguage":"nb-NO","@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":"nb-NO","@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 har bakgrunn som elektroingeni\u00f8r og elsker alt som har med teknologi \u00e5 gj\u00f8re. N\u00e5r han tar en pause fra AI-nyhetene, finner du ham ved snookerbordet.","sameAs":["www.linkedin.com\/in\/eugene-van-der-watt-16828119"],"url":"https:\/\/dailyai.com\/nb\/author\/eugene\/"}]}},"_links":{"self":[{"href":"https:\/\/dailyai.com\/nb\/wp-json\/wp\/v2\/posts\/12964","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dailyai.com\/nb\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dailyai.com\/nb\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dailyai.com\/nb\/wp-json\/wp\/v2\/users\/6"}],"replies":[{"embeddable":true,"href":"https:\/\/dailyai.com\/nb\/wp-json\/wp\/v2\/comments?post=12964"}],"version-history":[{"count":5,"href":"https:\/\/dailyai.com\/nb\/wp-json\/wp\/v2\/posts\/12964\/revisions"}],"predecessor-version":[{"id":12971,"href":"https:\/\/dailyai.com\/nb\/wp-json\/wp\/v2\/posts\/12964\/revisions\/12971"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/nb\/wp-json\/wp\/v2\/media\/12967"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/nb\/wp-json\/wp\/v2\/media?parent=12964"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/nb\/wp-json\/wp\/v2\/categories?post=12964"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/nb\/wp-json\/wp\/v2\/tags?post=12964"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}