{"id":7671,"date":"2023-11-23T15:10:15","date_gmt":"2023-11-23T15:10:15","guid":{"rendered":"https:\/\/dailyai.com\/?p=7671"},"modified":"2023-11-23T15:13:38","modified_gmt":"2023-11-23T15:13:38","slug":"system-2-attention-improves-accuracy-of-llm-responses","status":"publish","type":"post","link":"https:\/\/dailyai.com\/sv\/2023\/11\/system-2-attention-improves-accuracy-of-llm-responses\/","title":{"rendered":"System 2 Attention f\u00f6rb\u00e4ttrar noggrannheten i LLM-svaren"},"content":{"rendered":"

Stora spr\u00e5kmodeller (LLM) vilseleds ofta av partiskhet eller irrelevant sammanhang i en prompt. Forskare vid Meta har hittat ett till synes enkelt s\u00e4tt att fixa det.<\/strong><\/p>\n

N\u00e4r kontextf\u00f6nstren \u00f6kar kan de uppmaningar som vi ger till en LLM bli l\u00e4ngre och alltmer detaljerade. LLM:erna har blivit b\u00e4ttre p\u00e5 att uppfatta nyanser eller mindre detaljer i v\u00e5ra uppmaningar, men ibland kan detta f\u00f6rvirra dem.<\/p>\n

Tidig maskininl\u00e4rning anv\u00e4nde en \"h\u00e5rd uppm\u00e4rksamhet\" -metod som valde ut den mest relevanta delen av en inmatning och svarade endast p\u00e5 den. Detta fungerar bra n\u00e4r du f\u00f6rs\u00f6ker skriva en bildtext, men d\u00e5ligt n\u00e4r du \u00f6vers\u00e4tter en mening eller svarar p\u00e5 en fr\u00e5ga med flera lager.<\/p>\n

De flesta LLM-utbildare anv\u00e4nder nu en metod med \"mjuk uppm\u00e4rksamhet\" som inneb\u00e4r att hela fr\u00e5geformul\u00e4ret tas upp som symboler och att varje symbol viktas.<\/p>\n

Meta f\u00f6resl\u00e5r ett tillv\u00e4gag\u00e5ngss\u00e4tt som kallas System 2 Uppm\u00e4rksamhet<\/a> (S2A) f\u00f6r att f\u00e5 det b\u00e4sta av tv\u00e5 v\u00e4rldar. S2A anv\u00e4nder en LLM:s f\u00f6rm\u00e5ga att bearbeta naturligt spr\u00e5k f\u00f6r att ta emot din fr\u00e5ga och rensa bort partisk och irrelevant information innan du b\u00f6rjar arbeta med ett svar.<\/p>\n

H\u00e4r \u00e4r ett exempel.<\/p>\n

\"\"
Exempel p\u00e5 S2A-matematik. K\u00e4lla: arXiv<\/figcaption><\/figure>\n

S2A tar bort informationen om Max eftersom den \u00e4r irrelevant f\u00f6r fr\u00e5gan. S2A \u00e5terskapar en optimerad prompt innan han b\u00f6rjar arbeta med den. LLM:er \u00e4r notoriskt d\u00e5liga p\u00e5 matematik<\/a> s\u00e5 att g\u00f6ra uppmaningen mindre f\u00f6rvirrande \u00e4r en stor hj\u00e4lp.<\/p>\n

LLM:er \u00e4r tillm\u00f6tesg\u00e5ende och h\u00e5ller g\u00e4rna med dig, \u00e4ven n\u00e4r du har fel. S2A tar bort alla f\u00f6rdomar i en fr\u00e5ga och bearbetar sedan bara de relevanta delarna av fr\u00e5gan. Detta minskar det som AI-forskare kallar \"sycophancy\", eller en AI-modells ben\u00e4genhet att kyssa rumpan.<\/p>\n

\"\"
S2A minskning av sycophancy. K\u00e4lla: arXiv<\/figcaption><\/figure>\n

S2A \u00e4r egentligen bara en systemprompt som instruerar LLM att f\u00f6rfina den ursprungliga prompten lite innan de b\u00f6rjar arbeta med den. De resultat som forskarna uppn\u00e5dde med matematik-, fakta- och l\u00e5ngformsfr\u00e5gor var imponerande.<\/p>\n

Som exempel kan n\u00e4mnas de f\u00f6rb\u00e4ttringar S2A uppn\u00e5dde p\u00e5 faktafr\u00e5gor. Baslinjen var svar p\u00e5 fr\u00e5gor som inneh\u00f6ll partiskhet, medan Oracle-fr\u00e5gan var en m\u00e4nskligt f\u00f6rfinad idealfr\u00e5ga.<\/p>\n

S2A kommer mycket n\u00e4ra resultaten fr\u00e5n Oracle-prompten och ger n\u00e4stan 50% f\u00f6rb\u00e4ttring av noggrannheten j\u00e4mf\u00f6rt med baslinjeprompten.<\/p>\n

\"\"
S2A J\u00e4mf\u00f6relse av resultat. K\u00e4lla: arXiv<\/figcaption><\/figure>\n

S\u00e5 vad \u00e4r haken? F\u00f6rbehandlingen av den ursprungliga fr\u00e5gan innan den besvaras inneb\u00e4r att ytterligare ber\u00e4kningskrav tillkommer i processen. Om fr\u00e5gan \u00e4r l\u00e5ng och inneh\u00e5ller mycket relevant information kan det inneb\u00e4ra betydande kostnader att \u00e5terskapa fr\u00e5gan.<\/p>\n

Det \u00e4r inte troligt att anv\u00e4ndarna blir b\u00e4ttre p\u00e5 att skriva v\u00e4lformulerade uppmaningar, s\u00e5 S2A kan vara ett bra s\u00e4tt att komma runt det.<\/p>\n

Kommer Meta att bygga in S2A i sin Lama<\/a> modell? Vi vet inte, men du kan sj\u00e4lv anv\u00e4nda dig av S2A-metoden.<\/p>\n

Om du \u00e4r noga med att utel\u00e4mna \u00e5sikter eller ledande f\u00f6rslag fr\u00e5n dina uppmaningar \u00e4r det mer sannolikt att du f\u00e5r korrekta svar fr\u00e5n dessa modeller.<\/p>","protected":false},"excerpt":{"rendered":"

Stora spr\u00e5kmodeller (LLM) vilseleds ofta av partiskhet eller irrelevant sammanhang i en prompt. Forskare vid Meta har hittat ett till synes enkelt s\u00e4tt att fixa det. N\u00e4r kontextf\u00f6nstren \u00f6kar kan de uppmaningar som vi anger i en LLM bli l\u00e4ngre och alltmer detaljerade. LLM har blivit b\u00e4ttre p\u00e5 att plocka upp nyanser eller mindre detaljer i v\u00e5ra uppmaningar, men ibland kan detta f\u00f6rvirra dem. Tidig maskininl\u00e4rning anv\u00e4nde en \"h\u00e5rd uppm\u00e4rksamhet\" -metod som valde ut den mest relevanta delen av en inmatning och svarade endast p\u00e5 den. Det h\u00e4r fungerar bra n\u00e4r du f\u00f6rs\u00f6ker skriva en bildtext,<\/p>","protected":false},"author":6,"featured_media":7676,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[84],"tags":[118,131],"class_list":["post-7671","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-industry","tag-llms","tag-meta"],"yoast_head":"\nSystem 2 Attention improves accuracy of LLM responses | 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\/sv\/2023\/11\/system-2-attention-improves-accuracy-of-llm-responses\/\" \/>\n<meta property=\"og:locale\" content=\"sv_SE\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"System 2 Attention improves accuracy of LLM responses | DailyAI\" \/>\n<meta property=\"og:description\" content=\"Large Language Models (LLM) are often mislead by bias or irrelevant context in a prompt. Researchers at Meta have found a seemingly simple way to fix that. As context windows increase the prompts that we enter into an LLM can become longer and increasingly detailed. LLMs have become better at picking up on the nuances or smaller details in our prompts, but sometimes this can confuse them. Early machine learning used a \u201chard attention\u201d approach that singled out the most relevant part of an input and responded only to that. This works fine when you\u2019re trying to caption an image,\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dailyai.com\/sv\/2023\/11\/system-2-attention-improves-accuracy-of-llm-responses\/\" \/>\n<meta property=\"og:site_name\" content=\"DailyAI\" \/>\n<meta property=\"article:published_time\" content=\"2023-11-23T15:10:15+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2023-11-23T15:13:38+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/11\/Simplify.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1000\" \/>\n\t<meta property=\"og:image:height\" content=\"666\" \/>\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=\"Skriven av\" \/>\n\t<meta name=\"twitter:data1\" content=\"Eugene van der Watt\" \/>\n\t<meta name=\"twitter:label2\" content=\"Ber\u00e4knad l\u00e4stid\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 minuter\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/11\\\/system-2-attention-improves-accuracy-of-llm-responses\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/11\\\/system-2-attention-improves-accuracy-of-llm-responses\\\/\"},\"author\":{\"name\":\"Eugene van der Watt\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/7ce525c6d0c79838b7cc7cde96993cfa\"},\"headline\":\"System 2 Attention improves accuracy of LLM responses\",\"datePublished\":\"2023-11-23T15:10:15+00:00\",\"dateModified\":\"2023-11-23T15:13:38+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/11\\\/system-2-attention-improves-accuracy-of-llm-responses\\\/\"},\"wordCount\":520,\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/11\\\/system-2-attention-improves-accuracy-of-llm-responses\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/11\\\/Simplify.jpg\",\"keywords\":[\"LLMS\",\"Meta\"],\"articleSection\":[\"Industry\"],\"inLanguage\":\"sv-SE\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/11\\\/system-2-attention-improves-accuracy-of-llm-responses\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/11\\\/system-2-attention-improves-accuracy-of-llm-responses\\\/\",\"name\":\"System 2 Attention improves accuracy of LLM responses | DailyAI\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/11\\\/system-2-attention-improves-accuracy-of-llm-responses\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/11\\\/system-2-attention-improves-accuracy-of-llm-responses\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/11\\\/Simplify.jpg\",\"datePublished\":\"2023-11-23T15:10:15+00:00\",\"dateModified\":\"2023-11-23T15:13:38+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/11\\\/system-2-attention-improves-accuracy-of-llm-responses\\\/#breadcrumb\"},\"inLanguage\":\"sv-SE\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2023\\\/11\\\/system-2-attention-improves-accuracy-of-llm-responses\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"sv-SE\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/11\\\/system-2-attention-improves-accuracy-of-llm-responses\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/11\\\/Simplify.jpg\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/11\\\/Simplify.jpg\",\"width\":1000,\"height\":666},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/11\\\/system-2-attention-improves-accuracy-of-llm-responses\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dailyai.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"System 2 Attention improves accuracy of LLM responses\"}]},{\"@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\":\"sv-SE\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\",\"name\":\"DailyAI\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"sv-SE\",\"@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\":\"sv-SE\",\"@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\\\/sv\\\/author\\\/eugene\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"System 2-uppm\u00e4rksamhet f\u00f6rb\u00e4ttrar noggrannheten i LLM-svar | 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\/sv\/2023\/11\/system-2-attention-improves-accuracy-of-llm-responses\/","og_locale":"sv_SE","og_type":"article","og_title":"System 2 Attention improves accuracy of LLM responses | DailyAI","og_description":"Large Language Models (LLM) are often mislead by bias or irrelevant context in a prompt. Researchers at Meta have found a seemingly simple way to fix that. As context windows increase the prompts that we enter into an LLM can become longer and increasingly detailed. LLMs have become better at picking up on the nuances or smaller details in our prompts, but sometimes this can confuse them. Early machine learning used a \u201chard attention\u201d approach that singled out the most relevant part of an input and responded only to that. This works fine when you\u2019re trying to caption an image,","og_url":"https:\/\/dailyai.com\/sv\/2023\/11\/system-2-attention-improves-accuracy-of-llm-responses\/","og_site_name":"DailyAI","article_published_time":"2023-11-23T15:10:15+00:00","article_modified_time":"2023-11-23T15:13:38+00:00","og_image":[{"width":1000,"height":666,"url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/11\/Simplify.jpg","type":"image\/jpeg"}],"author":"Eugene van der Watt","twitter_card":"summary_large_image","twitter_creator":"@DailyAIOfficial","twitter_site":"@DailyAIOfficial","twitter_misc":{"Skriven av":"Eugene van der Watt","Ber\u00e4knad l\u00e4stid":"3 minuter"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/dailyai.com\/2023\/11\/system-2-attention-improves-accuracy-of-llm-responses\/#article","isPartOf":{"@id":"https:\/\/dailyai.com\/2023\/11\/system-2-attention-improves-accuracy-of-llm-responses\/"},"author":{"name":"Eugene van der Watt","@id":"https:\/\/dailyai.com\/#\/schema\/person\/7ce525c6d0c79838b7cc7cde96993cfa"},"headline":"System 2 Attention improves accuracy of LLM responses","datePublished":"2023-11-23T15:10:15+00:00","dateModified":"2023-11-23T15:13:38+00:00","mainEntityOfPage":{"@id":"https:\/\/dailyai.com\/2023\/11\/system-2-attention-improves-accuracy-of-llm-responses\/"},"wordCount":520,"publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"image":{"@id":"https:\/\/dailyai.com\/2023\/11\/system-2-attention-improves-accuracy-of-llm-responses\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/11\/Simplify.jpg","keywords":["LLMS","Meta"],"articleSection":["Industry"],"inLanguage":"sv-SE"},{"@type":"WebPage","@id":"https:\/\/dailyai.com\/2023\/11\/system-2-attention-improves-accuracy-of-llm-responses\/","url":"https:\/\/dailyai.com\/2023\/11\/system-2-attention-improves-accuracy-of-llm-responses\/","name":"System 2-uppm\u00e4rksamhet f\u00f6rb\u00e4ttrar noggrannheten i LLM-svar | DailyAI","isPartOf":{"@id":"https:\/\/dailyai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dailyai.com\/2023\/11\/system-2-attention-improves-accuracy-of-llm-responses\/#primaryimage"},"image":{"@id":"https:\/\/dailyai.com\/2023\/11\/system-2-attention-improves-accuracy-of-llm-responses\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/11\/Simplify.jpg","datePublished":"2023-11-23T15:10:15+00:00","dateModified":"2023-11-23T15:13:38+00:00","breadcrumb":{"@id":"https:\/\/dailyai.com\/2023\/11\/system-2-attention-improves-accuracy-of-llm-responses\/#breadcrumb"},"inLanguage":"sv-SE","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2023\/11\/system-2-attention-improves-accuracy-of-llm-responses\/"]}]},{"@type":"ImageObject","inLanguage":"sv-SE","@id":"https:\/\/dailyai.com\/2023\/11\/system-2-attention-improves-accuracy-of-llm-responses\/#primaryimage","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/11\/Simplify.jpg","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/11\/Simplify.jpg","width":1000,"height":666},{"@type":"BreadcrumbList","@id":"https:\/\/dailyai.com\/2023\/11\/system-2-attention-improves-accuracy-of-llm-responses\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dailyai.com\/"},{"@type":"ListItem","position":2,"name":"System 2 Attention improves accuracy of LLM responses"}]},{"@type":"WebSite","@id":"https:\/\/dailyai.com\/#website","url":"https:\/\/dailyai.com\/","name":"DagligaAI","description":"Din dagliga dos av 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":"sv-SE"},{"@type":"Organization","@id":"https:\/\/dailyai.com\/#organization","name":"DagligaAI","url":"https:\/\/dailyai.com\/","logo":{"@type":"ImageObject","inLanguage":"sv-SE","@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":"sv-SE","@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 kommer fr\u00e5n en bakgrund som elektronikingenj\u00f6r och \u00e4lskar allt som har med teknik att g\u00f6ra. N\u00e4r han tar en paus fr\u00e5n att konsumera AI-nyheter hittar du honom vid snookerbordet.","sameAs":["www.linkedin.com\/in\/eugene-van-der-watt-16828119"],"url":"https:\/\/dailyai.com\/sv\/author\/eugene\/"}]}},"_links":{"self":[{"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/posts\/7671","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/users\/6"}],"replies":[{"embeddable":true,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/comments?post=7671"}],"version-history":[{"count":7,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/posts\/7671\/revisions"}],"predecessor-version":[{"id":7682,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/posts\/7671\/revisions\/7682"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/media\/7676"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/media?parent=7671"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/categories?post=7671"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/tags?post=7671"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}