{"id":8817,"date":"2024-01-03T12:07:10","date_gmt":"2024-01-03T12:07:10","guid":{"rendered":"https:\/\/dailyai.com\/?p=8817"},"modified":"2024-01-03T12:10:34","modified_gmt":"2024-01-03T12:10:34","slug":"llms-improve-when-assuming-gender-neutral-or-male-roles","status":"publish","type":"post","link":"https:\/\/dailyai.com\/da\/2024\/01\/llms-improve-when-assuming-gender-neutral-or-male-roles\/","title":{"rendered":"LLM'er bliver bedre, n\u00e5r de p\u00e5tager sig k\u00f8nsneutrale eller mandlige roller"},"content":{"rendered":"

Forskere fra University of Michigan fandt ud af, at det gav bedre svar at bede Large Language Models (LLM) om at p\u00e5tage sig k\u00f8nsneutrale eller mandlige roller, end n\u00e5r de brugte kvindelige roller.<\/strong><\/p>\n

Brug af systemprompts er meget effektivt til at forbedre de svar, du f\u00e5r fra LLM'erne. N\u00e5r du beder ChatGPT om at optr\u00e6de som en \"hj\u00e6lpsom assistent\", har den en tendens til at forbedre sit spil. Forskerne ville finde ud af, hvilke sociale roller der klarede sig bedst, og deres resultater pegede p\u00e5 vedvarende problemer med bias i AI-modeller.<\/p>\n

At k\u00f8re deres eksperimenter p\u00e5 ChatGPT ville have v\u00e6ret uoverkommeligt, s\u00e5 de brugte open source-modellerne FLAN-T5, LLaMA 2<\/a>og OPT-IML.<\/p>\n

For at finde ud af, hvilke roller der var mest nyttige, bad de modellerne om at p\u00e5tage sig forskellige interpersonelle roller, henvende sig til et bestemt publikum eller p\u00e5tage sig forskellige erhvervsroller.<\/p>\n

For eksempel ville de bede modellen om at sige: \"Du er advokat\", \"Du taler med en far\" eller \"Du taler med din k\u00e6reste\".<\/p>\n

Derefter fik de modellerne til at besvare 2457 sp\u00f8rgsm\u00e5l fra Massive Multitask Language Understanding (MMLU)-benchmarkdatas\u00e6ttet og registrerede svarenes n\u00f8jagtighed.<\/p>\n

De samlede resultater offentliggjort i papiret<\/a> viste, at \"det at specificere en rolle, n\u00e5r man sp\u00f8rger, effektivt kan forbedre LLM'ernes pr\u00e6station med mindst 20% sammenlignet med kontrolsp\u00f8rgsm\u00e5let, hvor der ikke gives nogen kontekst.\"<\/p>\n

Da de segmenterede rollerne efter k\u00f8n, kom modellernes iboende bias frem i lyset. I alle deres tests fandt de ud af, at k\u00f8nsneutrale eller mandlige roller klarede sig bedre end kvindelige roller.<\/p>\n

\"\"
Sammenligning af n\u00f8jagtigheden af svar efter k\u00f8nsrolle. Kilde: arXiv<\/figcaption><\/figure>\n

Forskerne fandt ikke en afg\u00f8rende \u00e5rsag til k\u00f8nsforskellen, men det kan tyde p\u00e5, at sk\u00e6vhederne i tr\u00e6ningsdatas\u00e6ttene afsl\u00f8res i modellernes pr\u00e6stationer.<\/p>\n

Nogle af de andre resultater, de opn\u00e5ede, gav anledning til lige s\u00e5 mange sp\u00f8rgsm\u00e5l som svar. At prompte med en publikumsprompt gav bedre resultater end at prompte med en interpersonel rolle. Med andre ord gav \"Du taler med en l\u00e6rer\" mere pr\u00e6cise svar end \"Du taler med din l\u00e6rer\".<\/p>\n

Visse roller fungerede meget bedre i FLAN-T5 end i LLaMA 2. At opfordre FLAN-T5 til at p\u00e5tage sig \"politi\"-rollen gav gode resultater, men mindre i LLaMA 2. At bruge \"mentor\"- eller \"partner\"-rollerne fungerede rigtig godt i begge.<\/p>\n

\"\"
Bedst fungerende sociale roller for FLAN-T5 og LLaMA 2. De bedst fungerende muligheder i r\u00f8dt. Kilde: arXiv<\/figcaption><\/figure>\n

Interessant nok faldt rollen som \"hj\u00e6lpsom assistent\", der fungerer s\u00e5 godt i ChatGPT, et sted mellem 35 og 55 p\u00e5 listen over de bedste roller fra deres resultater.<\/p>\n

Hvorfor g\u00f8r disse subtile forskelle en forskel i n\u00f8jagtigheden af outputtet? Det ved vi ikke rigtig, men de g\u00f8r en forskel. Den m\u00e5de, du skriver din opfordring p\u00e5, og den kontekst, du giver, p\u00e5virker helt sikkert de resultater, du f\u00e5r.<\/p>\n

Lad os h\u00e5be, at nogle forskere med API-kreditter til overs kan gentage denne forskning ved hj\u00e6lp af ChatGPT. Det bliver interessant at f\u00e5 bekr\u00e6ftet, hvilke roller der fungerer bedst i systemprompts til GPT-4. Det er nok et godt bud, at resultaterne vil v\u00e6re sk\u00e6vt fordelt p\u00e5 k\u00f8n, som de var i denne unders\u00f8gelse.<\/p>","protected":false},"excerpt":{"rendered":"

Forskere fra University of Michigan fandt ud af, at n\u00e5r man bad Large Language Models (LLM) om at p\u00e5tage sig k\u00f8nsneutrale eller mandlige roller, gav det bedre svar, end n\u00e5r man brugte kvindelige roller. Brug af systemprompts er meget effektivt til at forbedre de svar, du f\u00e5r fra LLM'er. N\u00e5r du beder ChatGPT om at optr\u00e6de som en \"hj\u00e6lpsom assistent\", har den en tendens til at g\u00f8re sig mere umage. Forskerne ville finde ud af, hvilke sociale roller der klarede sig bedst, og deres resultater pegede p\u00e5 vedvarende problemer med bias i AI-modeller. At k\u00f8re deres eksperimenter p\u00e5 ChatGPT ville have v\u00e6ret uoverkommeligt, s\u00e5 de brugte open source-modellerne FLAN-T5, LLaMA 2 og OPT-IML. For at finde<\/p>","protected":false},"author":6,"featured_media":8820,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[84],"tags":[118],"class_list":["post-8817","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-industry","tag-llms"],"yoast_head":"\nLLMs improve when assuming gender-neutral or male roles | 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\/01\/llms-improve-when-assuming-gender-neutral-or-male-roles\/\" \/>\n<meta property=\"og:locale\" content=\"da_DK\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"LLMs improve when assuming gender-neutral or male roles | DailyAI\" \/>\n<meta property=\"og:description\" content=\"Researchers from the University of Michigan found that prompting Large Language Models (LLM) to assume gender-neutral or male roles elicited better responses than when using female roles. Using system prompts is very effective in improving the responses you get from LLMs. When you tell ChatGPT to act as a \u201chelpful assistant\u201d it tends to up its game. The researchers wanted to discover which social roles performed best and their results pointed to ongoing issues with bias in AI models. Running their experiments on ChatGPT would have been cost-prohibitive so they used open-source models FLAN-T5, LLaMA 2, and OPT-IML. To find\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dailyai.com\/da\/2024\/01\/llms-improve-when-assuming-gender-neutral-or-male-roles\/\" \/>\n<meta property=\"og:site_name\" content=\"DailyAI\" \/>\n<meta property=\"article:published_time\" content=\"2024-01-03T12:07:10+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-01-03T12:10:34+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/01\/gender-equality.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1000\" \/>\n\t<meta property=\"og:image:height\" content=\"667\" \/>\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\\\/01\\\/llms-improve-when-assuming-gender-neutral-or-male-roles\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/01\\\/llms-improve-when-assuming-gender-neutral-or-male-roles\\\/\"},\"author\":{\"name\":\"Eugene van der Watt\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/7ce525c6d0c79838b7cc7cde96993cfa\"},\"headline\":\"LLMs improve when assuming gender-neutral or male roles\",\"datePublished\":\"2024-01-03T12:07:10+00:00\",\"dateModified\":\"2024-01-03T12:10:34+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/01\\\/llms-improve-when-assuming-gender-neutral-or-male-roles\\\/\"},\"wordCount\":521,\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/01\\\/llms-improve-when-assuming-gender-neutral-or-male-roles\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/01\\\/gender-equality.jpg\",\"keywords\":[\"LLMS\"],\"articleSection\":[\"Industry\"],\"inLanguage\":\"da-DK\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/01\\\/llms-improve-when-assuming-gender-neutral-or-male-roles\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/01\\\/llms-improve-when-assuming-gender-neutral-or-male-roles\\\/\",\"name\":\"LLMs improve when assuming gender-neutral or male roles | DailyAI\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/01\\\/llms-improve-when-assuming-gender-neutral-or-male-roles\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/01\\\/llms-improve-when-assuming-gender-neutral-or-male-roles\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/01\\\/gender-equality.jpg\",\"datePublished\":\"2024-01-03T12:07:10+00:00\",\"dateModified\":\"2024-01-03T12:10:34+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/01\\\/llms-improve-when-assuming-gender-neutral-or-male-roles\\\/#breadcrumb\"},\"inLanguage\":\"da-DK\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2024\\\/01\\\/llms-improve-when-assuming-gender-neutral-or-male-roles\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"da-DK\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/01\\\/llms-improve-when-assuming-gender-neutral-or-male-roles\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/01\\\/gender-equality.jpg\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/01\\\/gender-equality.jpg\",\"width\":1000,\"height\":667},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/01\\\/llms-improve-when-assuming-gender-neutral-or-male-roles\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dailyai.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"LLMs improve when assuming gender-neutral or male roles\"}]},{\"@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":"LLM'er bliver bedre, n\u00e5r de p\u00e5tager sig k\u00f8nsneutrale eller mandlige roller | 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\/01\/llms-improve-when-assuming-gender-neutral-or-male-roles\/","og_locale":"da_DK","og_type":"article","og_title":"LLMs improve when assuming gender-neutral or male roles | DailyAI","og_description":"Researchers from the University of Michigan found that prompting Large Language Models (LLM) to assume gender-neutral or male roles elicited better responses than when using female roles. Using system prompts is very effective in improving the responses you get from LLMs. When you tell ChatGPT to act as a \u201chelpful assistant\u201d it tends to up its game. The researchers wanted to discover which social roles performed best and their results pointed to ongoing issues with bias in AI models. Running their experiments on ChatGPT would have been cost-prohibitive so they used open-source models FLAN-T5, LLaMA 2, and OPT-IML. To find","og_url":"https:\/\/dailyai.com\/da\/2024\/01\/llms-improve-when-assuming-gender-neutral-or-male-roles\/","og_site_name":"DailyAI","article_published_time":"2024-01-03T12:07:10+00:00","article_modified_time":"2024-01-03T12:10:34+00:00","og_image":[{"width":1000,"height":667,"url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/01\/gender-equality.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\/01\/llms-improve-when-assuming-gender-neutral-or-male-roles\/#article","isPartOf":{"@id":"https:\/\/dailyai.com\/2024\/01\/llms-improve-when-assuming-gender-neutral-or-male-roles\/"},"author":{"name":"Eugene van der Watt","@id":"https:\/\/dailyai.com\/#\/schema\/person\/7ce525c6d0c79838b7cc7cde96993cfa"},"headline":"LLMs improve when assuming gender-neutral or male roles","datePublished":"2024-01-03T12:07:10+00:00","dateModified":"2024-01-03T12:10:34+00:00","mainEntityOfPage":{"@id":"https:\/\/dailyai.com\/2024\/01\/llms-improve-when-assuming-gender-neutral-or-male-roles\/"},"wordCount":521,"publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"image":{"@id":"https:\/\/dailyai.com\/2024\/01\/llms-improve-when-assuming-gender-neutral-or-male-roles\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/01\/gender-equality.jpg","keywords":["LLMS"],"articleSection":["Industry"],"inLanguage":"da-DK"},{"@type":"WebPage","@id":"https:\/\/dailyai.com\/2024\/01\/llms-improve-when-assuming-gender-neutral-or-male-roles\/","url":"https:\/\/dailyai.com\/2024\/01\/llms-improve-when-assuming-gender-neutral-or-male-roles\/","name":"LLM'er bliver bedre, n\u00e5r de p\u00e5tager sig k\u00f8nsneutrale eller mandlige roller | DailyAI","isPartOf":{"@id":"https:\/\/dailyai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dailyai.com\/2024\/01\/llms-improve-when-assuming-gender-neutral-or-male-roles\/#primaryimage"},"image":{"@id":"https:\/\/dailyai.com\/2024\/01\/llms-improve-when-assuming-gender-neutral-or-male-roles\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/01\/gender-equality.jpg","datePublished":"2024-01-03T12:07:10+00:00","dateModified":"2024-01-03T12:10:34+00:00","breadcrumb":{"@id":"https:\/\/dailyai.com\/2024\/01\/llms-improve-when-assuming-gender-neutral-or-male-roles\/#breadcrumb"},"inLanguage":"da-DK","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2024\/01\/llms-improve-when-assuming-gender-neutral-or-male-roles\/"]}]},{"@type":"ImageObject","inLanguage":"da-DK","@id":"https:\/\/dailyai.com\/2024\/01\/llms-improve-when-assuming-gender-neutral-or-male-roles\/#primaryimage","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/01\/gender-equality.jpg","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/01\/gender-equality.jpg","width":1000,"height":667},{"@type":"BreadcrumbList","@id":"https:\/\/dailyai.com\/2024\/01\/llms-improve-when-assuming-gender-neutral-or-male-roles\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dailyai.com\/"},{"@type":"ListItem","position":2,"name":"LLMs improve when assuming gender-neutral or male roles"}]},{"@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\/8817","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=8817"}],"version-history":[{"count":3,"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/posts\/8817\/revisions"}],"predecessor-version":[{"id":8823,"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/posts\/8817\/revisions\/8823"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/media\/8820"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/media?parent=8817"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/categories?post=8817"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/tags?post=8817"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}