{"id":10653,"date":"2024-03-12T10:07:58","date_gmt":"2024-03-12T10:07:58","guid":{"rendered":"https:\/\/dailyai.com\/?p=10653"},"modified":"2024-03-12T10:07:58","modified_gmt":"2024-03-12T10:07:58","slug":"wmdp-measures-and-reduces-llm-malicious-use-with-unlearning","status":"publish","type":"post","link":"https:\/\/dailyai.com\/da\/2024\/03\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\/","title":{"rendered":"WMDP m\u00e5ler og reducerer ondsindet brug af LLM med afl\u00e6ring"},"content":{"rendered":"

Forskerne udgav et benchmark til at m\u00e5le, om en LLM indeholder potentielt farlig viden, og en ny teknik til at afl\u00e6re farlige data.<\/strong><\/p>\n

Der har v\u00e6ret meget debat om, hvorvidt AI-modeller kunne hj\u00e6lpe d\u00e5rlige akt\u00f8rer med at bygge en bombe, planl\u00e6gge en Angreb p\u00e5 cybersikkerheden<\/a>eller Byg et biov\u00e5ben<\/a>.<\/p>\n

Teamet af forskere fra Scale AI, Center for AI Safety og eksperter fra f\u00f8rende uddannelsesinstitutioner har udgivet et benchmark, der giver os et bedre m\u00e5l for, hvor farlig en bestemt LLM er.<\/p>\n

Weapons of Mass Destruction Proxy (WMDP)-benchmark er et datas\u00e6t med 4.157 multiple choice-sp\u00f8rgsm\u00e5l om farlig viden inden for biosikkerhed, cybersikkerhed og kemisk sikkerhed.<\/p>\n

Jo h\u00f8jere en LLM scorer p\u00e5 benchmarket, jo st\u00f8rre er faren for, at den potentielt kan hj\u00e6lpe en person med kriminelle hensigter. En LLM med en lavere WMDP-score er mindre tilb\u00f8jelig til at hj\u00e6lpe dig med at bygge en bombe eller skabe en ny virus.<\/p>\n

Den traditionelle m\u00e5de at g\u00f8re en LLM mere tilpasset p\u00e5 er at afvise anmodninger, der beder om data, som kan muligg\u00f8re ondsindede handlinger. Jailbreaking eller finjustering<\/a> En justeret LLM kan fjerne disse sikkerhedsforanstaltninger og afsl\u00f8re farlig viden i modellens datas\u00e6t.<\/p>\n

Hvis du kan f\u00e5 modellen til at glemme eller afl\u00e6re den kr\u00e6nkende information, er der ingen chance for, at den utilsigtet leverer den som svar p\u00e5 en eller anden smart jailbreaking<\/a> teknik.<\/p>\n

I deres forskningsartikel<\/a>forklarer forskerne, hvordan de udviklede en algoritme kaldet Contrastive Unlearn Tuning (CUT), en finjusteringsmetode til at afl\u00e6re farlig viden, mens godartet information bevares.<\/p>\n

CUT-finjusteringsmetoden afl\u00e6rer maskinen ved at optimere en \"glemme-term\", s\u00e5 modellen bliver mindre ekspert i farlige emner. Den optimerer ogs\u00e5 en \"retain term\", s\u00e5 den leverer nyttige svar p\u00e5 godartede anmodninger.<\/p>\n

Den dobbelte anvendelse af mange af oplysningerne i LLM-tr\u00e6ningsdatas\u00e6t g\u00f8r det vanskeligt kun at afl\u00e6re d\u00e5rlige ting og samtidig bevare nyttige oplysninger. Ved hj\u00e6lp af WMDP var forskerne i stand til at opbygge \"glem\"- og \"behold\"-datas\u00e6t til at styre deres CUT-afl\u00e6ringsteknik.<\/p>\n

Forskerne brugte WMDP til at m\u00e5le, hvor sandsynligt det var, at ZEPHYR-7B-BETA-modellen gav farlige oplysninger f\u00f8r og efter afl\u00e6ring ved hj\u00e6lp af CUT. Deres test fokuserede p\u00e5 bio- og cybersikkerhed.<\/p>\n

Derefter testede de modellen for at se, om dens generelle ydeevne var blevet forringet p\u00e5 grund af afl\u00e6ringsprocessen.<\/p>\n

\"\"
WMPD-n\u00f8jagtighed og MMLU-pr\u00e6station f\u00f8r og efter CUT-afl\u00e6ring. Kilde: arXiv<\/figcaption><\/figure>\n

Resultaterne viser, at afl\u00e6ringsprocessen reducerede n\u00f8jagtigheden af svarene p\u00e5 farlige anmodninger betydeligt med kun en marginal reduktion i modellens ydeevne p\u00e5 MMLU-benchmarket.<\/p>\n

Desv\u00e6rre reducerer CUT n\u00f8jagtigheden af svarene p\u00e5 n\u00e6rt besl\u00e6gtede omr\u00e5der som indledende virologi og computersikkerhed. At give et brugbart svar p\u00e5 \"Hvordan stopper man et cyberangreb?\", men ikke p\u00e5 \"Hvordan udf\u00f8rer man et cyberangreb?\", kr\u00e6ver mere pr\u00e6cision i afl\u00e6ringsprocessen.<\/p>\n

Forskerne fandt ogs\u00e5 ud af, at de ikke pr\u00e6cist kunne fjerne farlig kemisk viden, da den var for t\u00e6t sammenflettet med generel kemisk viden.<\/p>\n

Ved at bruge CUT kan udbydere af lukkede modeller som GPT-4 afl\u00e6re farlig information, s\u00e5 selv hvis de uds\u00e6ttes for ondsindet finjustering eller jailbreaking, kan de ikke huske nogen farlig information at levere.<\/p>\n

Du kan g\u00f8re det samme med open source-modeller, men offentlig adgang til deres v\u00e6gte betyder, at de kan genl\u00e6re farlige data, hvis de er tr\u00e6net p\u00e5 dem.<\/p>\n

Denne metode til at f\u00e5 en AI-model til at afl\u00e6re farlige data er ikke idiotsikker, is\u00e6r ikke for open source-modeller, men det er en robust tilf\u00f8jelse til de nuv\u00e6rende Tilpasning<\/a> metoder.<\/p>","protected":false},"excerpt":{"rendered":"

Forskerne udgav et benchmark til at m\u00e5le, om en LLM indeholder potentielt farlig viden, og en ny teknik til at afl\u00e6re farlige data. Der har v\u00e6ret meget debat om, hvorvidt AI-modeller kan hj\u00e6lpe d\u00e5rlige akt\u00f8rer med at bygge en bombe, planl\u00e6gge et cybersikkerhedsangreb eller bygge et biov\u00e5ben. Teamet af forskere fra Scale AI, Center for AI Safety og eksperter fra f\u00f8rende uddannelsesinstitutioner har udgivet et benchmark, der giver os et bedre m\u00e5l for, hvor farlig en bestemt LLM er. Weapons of Mass Destruction Proxy (WMDP)-benchmarket er et datas\u00e6t med 4.157 multiple choice-sp\u00f8rgsm\u00e5l om farlig viden inden for biosikkerhed,<\/p>","protected":false},"author":6,"featured_media":10656,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[84],"tags":[339,118],"class_list":["post-10653","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-industry","tag-ai-safety","tag-llms"],"yoast_head":"\nWMDP measures and reduces LLM malicious use with unlearning | 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\/da\/2024\/03\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\/\" \/>\n<meta property=\"og:locale\" content=\"da_DK\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"WMDP measures and reduces LLM malicious use with unlearning | DailyAI\" \/>\n<meta property=\"og:description\" content=\"Researchers released a benchmark to measure whether an LLM contains potentially hazardous knowledge and a novel technique for unlearning dangerous data. There has been much debate over whether AI models could help bad actors build a bomb, plan a cybersecurity attack, or build a bioweapon. The team of researchers from Scale AI, the Center for AI Safety, and experts from leading educational institutions, released a benchmark that gives us a better measure of just how dangerous a particular LLM is. The Weapons of Mass Destruction Proxy (WMDP) benchmark is a dataset of 4,157 multiple-choice questions surrounding hazardous knowledge in biosecurity,\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dailyai.com\/da\/2024\/03\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\/\" \/>\n<meta property=\"og:site_name\" content=\"DailyAI\" \/>\n<meta property=\"article:published_time\" content=\"2024-03-12T10:07:58+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/AI-unlearning.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1640\" \/>\n\t<meta property=\"og:image:height\" content=\"924\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\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 af\" \/>\n\t<meta name=\"twitter:data1\" content=\"Eugene van der Watt\" \/>\n\t<meta name=\"twitter:label2\" content=\"Estimeret l\u00e6setid\" \/>\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\\\/03\\\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\\\/\"},\"author\":{\"name\":\"Eugene van der Watt\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/7ce525c6d0c79838b7cc7cde96993cfa\"},\"headline\":\"WMDP measures and reduces LLM malicious use with unlearning\",\"datePublished\":\"2024-03-12T10:07:58+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\\\/\"},\"wordCount\":583,\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/03\\\/AI-unlearning.jpg\",\"keywords\":[\"AI safety\",\"LLMS\"],\"articleSection\":[\"Industry\"],\"inLanguage\":\"da-DK\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\\\/\",\"name\":\"WMDP measures and reduces LLM malicious use with unlearning | DailyAI\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/03\\\/AI-unlearning.jpg\",\"datePublished\":\"2024-03-12T10:07:58+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\\\/#breadcrumb\"},\"inLanguage\":\"da-DK\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"da-DK\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/03\\\/AI-unlearning.jpg\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/03\\\/AI-unlearning.jpg\",\"width\":1640,\"height\":924},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dailyai.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"WMDP measures and reduces LLM malicious use with unlearning\"}]},{\"@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\":\"da-DK\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\",\"name\":\"DailyAI\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"da-DK\",\"@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\":\"da-DK\",\"@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\\\/da\\\/author\\\/eugene\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"WMDP m\u00e5ler og reducerer ondsindet brug af LLM med afl\u00e6ring | 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\/da\/2024\/03\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\/","og_locale":"da_DK","og_type":"article","og_title":"WMDP measures and reduces LLM malicious use with unlearning | DailyAI","og_description":"Researchers released a benchmark to measure whether an LLM contains potentially hazardous knowledge and a novel technique for unlearning dangerous data. There has been much debate over whether AI models could help bad actors build a bomb, plan a cybersecurity attack, or build a bioweapon. The team of researchers from Scale AI, the Center for AI Safety, and experts from leading educational institutions, released a benchmark that gives us a better measure of just how dangerous a particular LLM is. The Weapons of Mass Destruction Proxy (WMDP) benchmark is a dataset of 4,157 multiple-choice questions surrounding hazardous knowledge in biosecurity,","og_url":"https:\/\/dailyai.com\/da\/2024\/03\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\/","og_site_name":"DailyAI","article_published_time":"2024-03-12T10:07:58+00:00","og_image":[{"width":1640,"height":924,"url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/AI-unlearning.jpg","type":"image\/jpeg"}],"author":"Eugene van der Watt","twitter_card":"summary_large_image","twitter_creator":"@DailyAIOfficial","twitter_site":"@DailyAIOfficial","twitter_misc":{"Skrevet af":"Eugene van der Watt","Estimeret l\u00e6setid":"3 minutter"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/dailyai.com\/2024\/03\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\/#article","isPartOf":{"@id":"https:\/\/dailyai.com\/2024\/03\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\/"},"author":{"name":"Eugene van der Watt","@id":"https:\/\/dailyai.com\/#\/schema\/person\/7ce525c6d0c79838b7cc7cde96993cfa"},"headline":"WMDP measures and reduces LLM malicious use with unlearning","datePublished":"2024-03-12T10:07:58+00:00","mainEntityOfPage":{"@id":"https:\/\/dailyai.com\/2024\/03\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\/"},"wordCount":583,"publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"image":{"@id":"https:\/\/dailyai.com\/2024\/03\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/AI-unlearning.jpg","keywords":["AI safety","LLMS"],"articleSection":["Industry"],"inLanguage":"da-DK"},{"@type":"WebPage","@id":"https:\/\/dailyai.com\/2024\/03\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\/","url":"https:\/\/dailyai.com\/2024\/03\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\/","name":"WMDP m\u00e5ler og reducerer ondsindet brug af LLM med afl\u00e6ring | DailyAI","isPartOf":{"@id":"https:\/\/dailyai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dailyai.com\/2024\/03\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\/#primaryimage"},"image":{"@id":"https:\/\/dailyai.com\/2024\/03\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/AI-unlearning.jpg","datePublished":"2024-03-12T10:07:58+00:00","breadcrumb":{"@id":"https:\/\/dailyai.com\/2024\/03\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\/#breadcrumb"},"inLanguage":"da-DK","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2024\/03\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\/"]}]},{"@type":"ImageObject","inLanguage":"da-DK","@id":"https:\/\/dailyai.com\/2024\/03\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\/#primaryimage","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/AI-unlearning.jpg","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/AI-unlearning.jpg","width":1640,"height":924},{"@type":"BreadcrumbList","@id":"https:\/\/dailyai.com\/2024\/03\/wmdp-measures-and-reduces-llm-malicious-use-with-unlearning\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dailyai.com\/"},{"@type":"ListItem","position":2,"name":"WMDP measures and reduces LLM malicious use with unlearning"}]},{"@type":"WebSite","@id":"https:\/\/dailyai.com\/#website","url":"https:\/\/dailyai.com\/","name":"DailyAI","description":"Din daglige dosis af AI-nyheder","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":"da-DK"},{"@type":"Organization","@id":"https:\/\/dailyai.com\/#organization","name":"DailyAI","url":"https:\/\/dailyai.com\/","logo":{"@type":"ImageObject","inLanguage":"da-DK","@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":"da-DK","@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 en baggrund som elektronikingeni\u00f8r og elsker alt, hvad der har med teknologi at g\u00f8re. N\u00e5r han tager en pause fra at l\u00e6se AI-nyheder, kan du finde ham ved snookerbordet.","sameAs":["www.linkedin.com\/in\/eugene-van-der-watt-16828119"],"url":"https:\/\/dailyai.com\/da\/author\/eugene\/"}]}},"_links":{"self":[{"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/posts\/10653","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/users\/6"}],"replies":[{"embeddable":true,"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/comments?post=10653"}],"version-history":[{"count":2,"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/posts\/10653\/revisions"}],"predecessor-version":[{"id":10657,"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/posts\/10653\/revisions\/10657"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/media\/10656"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/media?parent=10653"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/categories?post=10653"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/tags?post=10653"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}