{"id":11850,"date":"2024-04-30T12:48:52","date_gmt":"2024-04-30T12:48:52","guid":{"rendered":"https:\/\/dailyai.com\/?p=11850"},"modified":"2024-04-30T15:58:32","modified_gmt":"2024-04-30T15:58:32","slug":"googles-gecko-benchmark-identifies-best-ai-image-generator","status":"publish","type":"post","link":"https:\/\/dailyai.com\/nb\/2024\/04\/googles-gecko-benchmark-identifies-best-ai-image-generator\/","title":{"rendered":"Googles Gecko-benchmark identifiserer den beste AI-bildegeneratoren"},"content":{"rendered":"

Googles DeepMind<\/span><\/span> lanserte Gecko, en ny referanse for omfattende evaluering av AI-tekst-til-bilde-modeller (T2I).<\/strong><\/p>\n

I l\u00f8pet av de siste to \u00e5rene har vi sett AI-bildegeneratorer som DALL-E<\/span><\/span><\/a> og Midt p\u00e5 reisen<\/a> blir stadig bedre for hver versjon som lanseres.<\/p>\n

Det har imidlertid v\u00e6rt sv\u00e6rt subjektivt og vanskelig \u00e5 avgj\u00f8re hvilken av de underliggende modellene disse plattformene bruker som er best.<\/p>\n

Det er ikke s\u00e5 enkelt \u00e5 hevde at \u00e9n modell er \"bedre\" enn en annen. Ulike modeller utmerker seg i ulike aspekter av bildegenerering. \u00c9n kan v\u00e6re god p\u00e5 tekstgjengivelse, mens en annen kan v\u00e6re bedre p\u00e5 objektinteraksjon.<\/p>\n

En av T2I-modellenes st\u00f8rste utfordringer er \u00e5 f\u00f8lge hver eneste detalj i ledeteksten og f\u00e5 disse n\u00f8yaktig gjenspeilet i det genererte bildet.<\/p>\n

Med Gecko kan DeepMind<\/span><\/span> forskere har laget en m\u00e5lestokk<\/a> som evaluerer T2I-modellenes evner p\u00e5 samme m\u00e5te som mennesker gj\u00f8r.<\/p>\n

Ferdigheter<\/h2>\n

Forskerne definerte f\u00f8rst et omfattende datasett med ferdigheter som er relevante for T2I-generering. Disse omfatter blant annet romforst\u00e5else, handlingsgjenkjenning og tekstgjengivelse. Deretter delte de disse opp i mer spesifikke delferdigheter.<\/p>\n

Under tekstgjengivelse kan delferdighetene for eksempel omfatte gjengivelse av ulike skrifttyper, farger eller tekstst\u00f8rrelser.<\/p>\n

En LLM ble deretter brukt til \u00e5 generere sp\u00f8rsm\u00e5l for \u00e5 teste T2I-modellens evne til \u00e5 teste en bestemt ferdighet eller delferdighet.<\/p>\n

Dette gj\u00f8r det mulig for skaperne av en T2I-modell \u00e5 finne ut ikke bare hvilke ferdigheter som er utfordrende, men ogs\u00e5 p\u00e5 hvilket kompleksitetsniv\u00e5 en ferdighet blir utfordrende for modellen.<\/p>\n

\"\"
Gecko-referanserammen bruker et datasett med ferdigheter og underferdigheter (a), menneskelig Likert-poengsetting av bilden\u00f8yaktighet (b), LLM-genererte sp\u00f8rsm\u00e5l for VQA-analyse, og resulterer i omfattende beregninger som korrelerer med menneskelige evalueringer. Kilde: arXiv<\/figcaption><\/figure>\n

Menneskelig vs. automatisk evaluering<\/h2>\n

Gecko m\u00e5ler ogs\u00e5 hvor n\u00f8yaktig en T2I-modell f\u00f8lger alle detaljene i en ledetekst. Ogs\u00e5 her ble en LLM brukt til \u00e5 isolere viktige detaljer i hver ledetekst og deretter generere et sett med sp\u00f8rsm\u00e5l knyttet til disse detaljene.<\/p>\n

Disse sp\u00f8rsm\u00e5lene kan v\u00e6re b\u00e5de enkle, direkte sp\u00f8rsm\u00e5l om synlige elementer i bildet (f.eks. \"Er det en katt i bildet?\") og mer komplekse sp\u00f8rsm\u00e5l som tester forst\u00e5elsen av scenen eller forholdet mellom objekter (f.eks. \"Sitter katten over boken?\").<\/p>\n

En VQA-modell (Visual Question Answering) analyserer deretter det genererte bildet og svarer p\u00e5 sp\u00f8rsm\u00e5lene for \u00e5 se hvor n\u00f8yaktig T2I-modellen tilpasser utgangsbildet til en ledetekst.<\/p>\n

Forskerne samlet inn over 100 000 menneskelige annoteringer der deltakerne vurderte et generert bilde basert p\u00e5 hvor godt det stemte overens med spesifikke kriterier.<\/p>\n

Menneskene ble bedt om \u00e5 vurdere et spesifikt aspekt ved ledeteksten og gi bildet en poengsum p\u00e5 en skala fra 1 til 5 basert p\u00e5 hvor godt det stemte overens med ledeteksten.<\/p>\n

Ved \u00e5 bruke de menneskekommenterte evalueringene som gullstandard, kunne forskerne bekrefte at deres auto-evalueringsberegning \"er bedre korrelert med menneskelige vurderinger enn eksisterende beregninger for v\u00e5rt nye datasett\".<\/p>\n

Resultatet er et benchmarking-system som kan sette tall p\u00e5 spesifikke faktorer som gj\u00f8r et generert bilde godt eller d\u00e5rlig.<\/p>\n

Gecko gir utgangsbildet poeng p\u00e5 en m\u00e5te som ligger tett opp til hvordan vi intuitivt avgj\u00f8r om vi er forn\u00f8yde med det genererte bildet eller ikke.<\/p>\n

S\u00e5 hva er den beste tekst-til-bilde-modellen?<\/p>\n

I avisen deres<\/a>konkluderte forskerne med at Googles Muse-modell sl\u00e5r Stable Diffusion 1.5 og SDXL p\u00e5 Gecko-benchmarken. De er kanskje partiske, men tallene lyver ikke.<\/p>","protected":false},"excerpt":{"rendered":"

Googles DeepMind lanserte Gecko, en ny referanse for omfattende evaluering av AI-tekst-til-bilde-modeller (T2I). I l\u00f8pet av de siste to \u00e5rene har vi sett at AI-bildegeneratorer som DALL-E og Midjourney blir stadig bedre for hver versjon som lanseres. Det har imidlertid v\u00e6rt subjektivt og vanskelig \u00e5 avgj\u00f8re hvilken av de underliggende modellene disse plattformene bruker som er best. Det er ikke s\u00e5 enkelt \u00e5 hevde at \u00e9n modell er \"bedre\" enn en annen. Ulike modeller utmerker seg i ulike aspekter av bildegenerering. \u00c9n kan v\u00e6re god p\u00e5 tekstgjengivelse, mens en annen kan v\u00e6re bedre p\u00e5 objektinteraksjon. En av T2I-modellenes hovedutfordringer<\/p>","protected":false},"author":6,"featured_media":11853,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[84],"tags":[147,107,102,165],"class_list":["post-11850","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-industry","tag-deepmind","tag-generative-ai","tag-google","tag-image-generation"],"yoast_head":"\nGoogle\u2019s Gecko benchmark identifies best AI image generator | 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\/04\/googles-gecko-benchmark-identifies-best-ai-image-generator\/\" \/>\n<meta property=\"og:locale\" content=\"nb_NO\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Google\u2019s Gecko benchmark identifies best AI image generator | DailyAI\" \/>\n<meta property=\"og:description\" content=\"Google\u2019s DeepMind released Gecko, a new benchmark for comprehensively evaluating AI text-to-image (T2I) models. Over the last two years, we\u2019ve seen AI image generators like DALL-E and Midjourney become progressively better with each version release. However, deciding which of the underlying models these platforms use is best has been largely subjective and difficult to benchmark. To make a broad claim that one model is \u201cbetter\u201d than another isn\u2019t so simple. Different models excel in various aspects of image generation. One may be good at text rendering while another may be better at object interaction. A key challenge that T2I models\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dailyai.com\/nb\/2024\/04\/googles-gecko-benchmark-identifies-best-ai-image-generator\/\" \/>\n<meta property=\"og:site_name\" content=\"DailyAI\" \/>\n<meta property=\"article:published_time\" content=\"2024-04-30T12:48:52+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-04-30T15:58:32+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/DeepMind-Gecko.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\\\/04\\\/googles-gecko-benchmark-identifies-best-ai-image-generator\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/googles-gecko-benchmark-identifies-best-ai-image-generator\\\/\"},\"author\":{\"name\":\"Eugene van der Watt\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/7ce525c6d0c79838b7cc7cde96993cfa\"},\"headline\":\"Google\u2019s Gecko benchmark identifies best AI image generator\",\"datePublished\":\"2024-04-30T12:48:52+00:00\",\"dateModified\":\"2024-04-30T15:58:32+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/googles-gecko-benchmark-identifies-best-ai-image-generator\\\/\"},\"wordCount\":591,\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/googles-gecko-benchmark-identifies-best-ai-image-generator\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/DeepMind-Gecko.webp\",\"keywords\":[\"DeepMind\",\"Generative AI\",\"Google\",\"image generation\"],\"articleSection\":[\"Industry\"],\"inLanguage\":\"nb-NO\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/googles-gecko-benchmark-identifies-best-ai-image-generator\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/googles-gecko-benchmark-identifies-best-ai-image-generator\\\/\",\"name\":\"Google\u2019s Gecko benchmark identifies best AI image generator | DailyAI\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/googles-gecko-benchmark-identifies-best-ai-image-generator\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/googles-gecko-benchmark-identifies-best-ai-image-generator\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/DeepMind-Gecko.webp\",\"datePublished\":\"2024-04-30T12:48:52+00:00\",\"dateModified\":\"2024-04-30T15:58:32+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/googles-gecko-benchmark-identifies-best-ai-image-generator\\\/#breadcrumb\"},\"inLanguage\":\"nb-NO\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/googles-gecko-benchmark-identifies-best-ai-image-generator\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"nb-NO\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/googles-gecko-benchmark-identifies-best-ai-image-generator\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/DeepMind-Gecko.webp\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/DeepMind-Gecko.webp\",\"width\":1792,\"height\":1024},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/googles-gecko-benchmark-identifies-best-ai-image-generator\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dailyai.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Google\u2019s Gecko benchmark identifies best AI image generator\"}]},{\"@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":"Googles Gecko-referanse identifiserer den beste AI-bildegeneratoren | 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\/04\/googles-gecko-benchmark-identifies-best-ai-image-generator\/","og_locale":"nb_NO","og_type":"article","og_title":"Google\u2019s Gecko benchmark identifies best AI image generator | DailyAI","og_description":"Google\u2019s DeepMind released Gecko, a new benchmark for comprehensively evaluating AI text-to-image (T2I) models. Over the last two years, we\u2019ve seen AI image generators like DALL-E and Midjourney become progressively better with each version release. However, deciding which of the underlying models these platforms use is best has been largely subjective and difficult to benchmark. To make a broad claim that one model is \u201cbetter\u201d than another isn\u2019t so simple. Different models excel in various aspects of image generation. One may be good at text rendering while another may be better at object interaction. A key challenge that T2I models","og_url":"https:\/\/dailyai.com\/nb\/2024\/04\/googles-gecko-benchmark-identifies-best-ai-image-generator\/","og_site_name":"DailyAI","article_published_time":"2024-04-30T12:48:52+00:00","article_modified_time":"2024-04-30T15:58:32+00:00","og_image":[{"width":1792,"height":1024,"url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/DeepMind-Gecko.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\/04\/googles-gecko-benchmark-identifies-best-ai-image-generator\/#article","isPartOf":{"@id":"https:\/\/dailyai.com\/2024\/04\/googles-gecko-benchmark-identifies-best-ai-image-generator\/"},"author":{"name":"Eugene van der Watt","@id":"https:\/\/dailyai.com\/#\/schema\/person\/7ce525c6d0c79838b7cc7cde96993cfa"},"headline":"Google\u2019s Gecko benchmark identifies best AI image generator","datePublished":"2024-04-30T12:48:52+00:00","dateModified":"2024-04-30T15:58:32+00:00","mainEntityOfPage":{"@id":"https:\/\/dailyai.com\/2024\/04\/googles-gecko-benchmark-identifies-best-ai-image-generator\/"},"wordCount":591,"publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"image":{"@id":"https:\/\/dailyai.com\/2024\/04\/googles-gecko-benchmark-identifies-best-ai-image-generator\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/DeepMind-Gecko.webp","keywords":["DeepMind","Generative AI","Google","image generation"],"articleSection":["Industry"],"inLanguage":"nb-NO"},{"@type":"WebPage","@id":"https:\/\/dailyai.com\/2024\/04\/googles-gecko-benchmark-identifies-best-ai-image-generator\/","url":"https:\/\/dailyai.com\/2024\/04\/googles-gecko-benchmark-identifies-best-ai-image-generator\/","name":"Googles Gecko-referanse identifiserer den beste AI-bildegeneratoren | DailyAI","isPartOf":{"@id":"https:\/\/dailyai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dailyai.com\/2024\/04\/googles-gecko-benchmark-identifies-best-ai-image-generator\/#primaryimage"},"image":{"@id":"https:\/\/dailyai.com\/2024\/04\/googles-gecko-benchmark-identifies-best-ai-image-generator\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/DeepMind-Gecko.webp","datePublished":"2024-04-30T12:48:52+00:00","dateModified":"2024-04-30T15:58:32+00:00","breadcrumb":{"@id":"https:\/\/dailyai.com\/2024\/04\/googles-gecko-benchmark-identifies-best-ai-image-generator\/#breadcrumb"},"inLanguage":"nb-NO","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2024\/04\/googles-gecko-benchmark-identifies-best-ai-image-generator\/"]}]},{"@type":"ImageObject","inLanguage":"nb-NO","@id":"https:\/\/dailyai.com\/2024\/04\/googles-gecko-benchmark-identifies-best-ai-image-generator\/#primaryimage","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/DeepMind-Gecko.webp","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/DeepMind-Gecko.webp","width":1792,"height":1024},{"@type":"BreadcrumbList","@id":"https:\/\/dailyai.com\/2024\/04\/googles-gecko-benchmark-identifies-best-ai-image-generator\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dailyai.com\/"},{"@type":"ListItem","position":2,"name":"Google\u2019s Gecko benchmark identifies best AI image generator"}]},{"@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\/11850","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=11850"}],"version-history":[{"count":4,"href":"https:\/\/dailyai.com\/nb\/wp-json\/wp\/v2\/posts\/11850\/revisions"}],"predecessor-version":[{"id":11857,"href":"https:\/\/dailyai.com\/nb\/wp-json\/wp\/v2\/posts\/11850\/revisions\/11857"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/nb\/wp-json\/wp\/v2\/media\/11853"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/nb\/wp-json\/wp\/v2\/media?parent=11850"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/nb\/wp-json\/wp\/v2\/categories?post=11850"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/nb\/wp-json\/wp\/v2\/tags?post=11850"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}