{"id":11172,"date":"2024-04-02T09:32:07","date_gmt":"2024-04-02T09:32:07","guid":{"rendered":"https:\/\/dailyai.com\/?p=11172"},"modified":"2024-04-02T09:32:07","modified_gmt":"2024-04-02T09:32:07","slug":"deepmind-developed-safe-an-ai-agent-to-fact-check-llms","status":"publish","type":"post","link":"https:\/\/dailyai.com\/sv\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/","title":{"rendered":"DeepMind utvecklade SAFE, en AI-agent f\u00f6r att faktagranska LLM:er"},"content":{"rendered":"

Forskare fr\u00e5n DeepMind och Stanford University har utvecklat en AI-agent som faktagranskar LLM:er och m\u00f6jligg\u00f6r benchmarking av AI-modellers faktam\u00e4ssighet.<\/strong><\/p>\n

\u00c4ven de b\u00e4sta AI-modellerna tenderar fortfarande att hallucinera<\/a> ibland. Om du ber ChatGPT att ge dig fakta om ett \u00e4mne, ju l\u00e4ngre svaret \u00e4r desto mer sannolikt \u00e4r det att det inneh\u00e5ller fakta som inte \u00e4r sanna.<\/p>\n

Vilka modeller \u00e4r mer faktam\u00e4ssigt korrekta \u00e4n andra n\u00e4r de genererar l\u00e4ngre svar? Det \u00e4r sv\u00e5rt att s\u00e4ga eftersom vi fram till nu inte har haft n\u00e5got riktm\u00e4rke som m\u00e4ter sakligheten i LLM:s l\u00e5nga svar.<\/p>\n

DeepMind anv\u00e4nde f\u00f6rst GPT-4 f\u00f6r att skapa LongFact, en upps\u00e4ttning med 2 280 uppmaningar i form av fr\u00e5gor relaterade till 38 \u00e4mnen. Dessa uppmaningar framkallar l\u00e5ngformade svar fr\u00e5n den LLM som testas.<\/p>\n

De skapade sedan en AI-agent som anv\u00e4nde GPT-3.5-turbo f\u00f6r att anv\u00e4nda Google f\u00f6r att verifiera hur faktiska svaren som LLM genererade var. De kallade metoden Search-Augmented Factuality Evaluator (SAFE).<\/p>\n

SAFE delar f\u00f6rst upp det l\u00e5nga svaret fr\u00e5n LLM i enskilda fakta. Sedan skickar den s\u00f6kf\u00f6rfr\u00e5gningar till Google Search och resonerar om sanningshalten i fakta baserat p\u00e5 information i de returnerade s\u00f6kresultaten.<\/p>\n

H\u00e4r \u00e4r ett exempel fr\u00e5n forskningsrapport<\/a>.<\/p>\n

\"\"
En faktas\u00f6kande fr\u00e5ga ger upphov till ett l\u00e5ngt svar. Svaret delas upp i enskilda fakta, revideras f\u00f6r att vara frist\u00e5ende, kontrolleras f\u00f6r relevans och kontrolleras med hj\u00e4lp av Google Search. K\u00e4lla: arXiv<\/figcaption><\/figure>\n

Forskarna s\u00e4ger att SAFE uppn\u00e5r \"\u00f6verm\u00e4nskliga prestanda\" j\u00e4mf\u00f6rt med m\u00e4nskliga kommentatorer som g\u00f6r faktakontrollen.<\/p>\n

SAFE inst\u00e4mde med 72% av de m\u00e4nskliga annotationerna, och n\u00e4r det skilde sig fr\u00e5n de m\u00e4nskliga annotationerna visade det sig att SAFE hade r\u00e4tt 76% av g\u00e5ngerna. Det var ocks\u00e5 20 g\u00e5nger billigare \u00e4n m\u00e4nskliga annotatorer fr\u00e5n crowdsourcing. LLM:er \u00e4r allts\u00e5 b\u00e4ttre och billigare faktakontrollanter \u00e4n vad m\u00e4nniskor \u00e4r.<\/p>\n

Kvaliteten p\u00e5 svaret fr\u00e5n de testade LLM-l\u00e4karna m\u00e4ttes utifr\u00e5n antalet faktoider i svaret i kombination med hur faktabaserade de enskilda faktoiderna var.<\/p>\n

Det m\u00e5tt som de anv\u00e4nde (F1@K) uppskattar det \"ideala\" antalet fakta i ett svar som m\u00e4nniskan f\u00f6redrar. I benchmarktesterna anv\u00e4ndes 64 som median f\u00f6r K och 178 som maximum.<\/p>\n

Enkelt uttryckt \u00e4r F1@K ett m\u00e5tt p\u00e5 \"Gav svaret mig s\u00e5 mycket fakta som jag ville ha?\" i kombination med \"Hur m\u00e5nga av dessa fakta var sanna?\".<\/p>\n

Vilken LLM \u00e4r mest saklig?<\/h2>\n

Forskarna anv\u00e4nde LongFact f\u00f6r att fr\u00e5ga 13 LLM:er fr\u00e5n familjerna Gemini, GPT, Claude och PaLM-2. Sedan anv\u00e4nde de SAFE f\u00f6r att utv\u00e4rdera hur faktabaserade deras svar var.<\/p>\n

GPT-4-Turbo toppar listan som den mest faktabaserade modellen n\u00e4r det g\u00e4ller att generera l\u00e5nga svar. Den f\u00f6ljdes t\u00e4tt av Gemini-Ultra och PaLM-2-L-IT-RLHF. Resultaten visade att st\u00f6rre LLM:er \u00e4r mer faktabaserade \u00e4n mindre.<\/p>\n

F1@K-ber\u00e4kningen skulle f\u00f6rmodligen f\u00e5 datavetare att h\u00e4pna, men f\u00f6r enkelhetens skull visar dessa benchmarkresultat hur faktabaserad varje modell \u00e4r n\u00e4r den returnerar medell\u00e5nga och l\u00e4ngre svar p\u00e5 fr\u00e5gorna.<\/p>\n

\"\"
L\u00e5ngformig faktaprestanda f\u00f6r 13 LLM:er med K = 64 (medianantalet fakta bland alla modellsvar) och K = 178 (det maximala antalet fakta bland alla modellsvar). K\u00e4lla: arXiv<\/figcaption><\/figure>\n

SAFE \u00e4r ett billigt och effektivt s\u00e4tt att kvantifiera LLM-faktualitet i l\u00e5ng form. Det \u00e4r snabbare och billigare \u00e4n m\u00e4nniskor n\u00e4r det g\u00e4ller faktakontroll, men det beror fortfarande p\u00e5 sanningshalten i den information som Google returnerar i s\u00f6kresultaten.<\/p>\n

DeepMind sl\u00e4ppte SAFE f\u00f6r allm\u00e4n anv\u00e4ndning och f\u00f6reslog att det skulle kunna hj\u00e4lpa till att f\u00f6rb\u00e4ttra LLM-faktualiteten genom b\u00e4ttre f\u00f6rtr\u00e4ning och finjustering. Det skulle ocks\u00e5 kunna g\u00f6ra det m\u00f6jligt f\u00f6r en LLM att kontrollera sina fakta innan den presenterar resultatet f\u00f6r en anv\u00e4ndare.<\/p>\n

OpenAI kommer att bli glada \u00f6ver att se att forskning fr\u00e5n Google visar att GPT-4 sl\u00e5r Gemini i \u00e4nnu ett benchmark.<\/p>","protected":false},"excerpt":{"rendered":"

Forskare fr\u00e5n DeepMind och Stanford University har utvecklat en AI-agent som faktagranskar LLM:er och m\u00f6jligg\u00f6r benchmarking av AI-modellers faktam\u00e4ssighet. \u00c4ven de b\u00e4sta AI-modellerna tenderar fortfarande att hallucinera ibland. Om du ber ChatGPT att ge dig fakta om ett \u00e4mne, ju l\u00e4ngre svaret \u00e4r, desto mer sannolikt \u00e4r det att det inneh\u00e5ller n\u00e5gra fakta som inte \u00e4r sanna. Vilka modeller \u00e4r mer faktam\u00e4ssigt korrekta \u00e4n andra n\u00e4r de genererar l\u00e4ngre svar? Det \u00e4r sv\u00e5rt att s\u00e4ga eftersom vi fram till nu inte har haft n\u00e5got riktm\u00e4rke som m\u00e4ter faktam\u00e4ssigheten i LLM:s l\u00e5nga svar. DeepMind anv\u00e4nde f\u00f6rst GPT-4 f\u00f6r att skapa LongFact, en upps\u00e4ttning<\/p>","protected":false},"author":6,"featured_media":11182,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[84],"tags":[147,118],"class_list":["post-11172","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-industry","tag-deepmind","tag-llms"],"yoast_head":"\nDeepMind developed SAFE, an AI agent to fact-check LLMs | 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\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/\" \/>\n<meta property=\"og:locale\" content=\"sv_SE\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"DeepMind developed SAFE, an AI agent to fact-check LLMs | DailyAI\" \/>\n<meta property=\"og:description\" content=\"Researchers from DeepMind and Stanford University developed an AI agent that fact-checks LLMs and enables benchmarking of AI model factuality. Even the best AI models still tend to hallucinate at times. If you ask ChatGPT to give you the facts about a topic, the longer its response the more likely it is to include some facts that aren\u2019t true. Which models are more factually accurate than others when generating longer answers? It\u2019s hard to say because until now, we didn\u2019t have a benchmark measuring the factuality of LLM long-form responses. DeepMind first used GPT-4 to create LongFact, a set of\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dailyai.com\/sv\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/\" \/>\n<meta property=\"og:site_name\" content=\"DailyAI\" \/>\n<meta property=\"article:published_time\" content=\"2024-04-02T09:32:07+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/fact-vs-fake.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=\"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=\"4 minuter\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\\\/\"},\"author\":{\"name\":\"Eugene van der Watt\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/7ce525c6d0c79838b7cc7cde96993cfa\"},\"headline\":\"DeepMind developed SAFE, an AI agent to fact-check LLMs\",\"datePublished\":\"2024-04-02T09:32:07+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\\\/\"},\"wordCount\":611,\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/fact-vs-fake.webp\",\"keywords\":[\"DeepMind\",\"LLMS\"],\"articleSection\":[\"Industry\"],\"inLanguage\":\"sv-SE\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\\\/\",\"name\":\"DeepMind developed SAFE, an AI agent to fact-check LLMs | DailyAI\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/fact-vs-fake.webp\",\"datePublished\":\"2024-04-02T09:32:07+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\\\/#breadcrumb\"},\"inLanguage\":\"sv-SE\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"sv-SE\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/fact-vs-fake.webp\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/fact-vs-fake.webp\",\"width\":1792,\"height\":1024},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dailyai.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"DeepMind developed SAFE, an AI agent to fact-check LLMs\"}]},{\"@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":"DeepMind utvecklade SAFE, en AI-agent f\u00f6r att faktagranska LLM:er | 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\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/","og_locale":"sv_SE","og_type":"article","og_title":"DeepMind developed SAFE, an AI agent to fact-check LLMs | DailyAI","og_description":"Researchers from DeepMind and Stanford University developed an AI agent that fact-checks LLMs and enables benchmarking of AI model factuality. Even the best AI models still tend to hallucinate at times. If you ask ChatGPT to give you the facts about a topic, the longer its response the more likely it is to include some facts that aren\u2019t true. Which models are more factually accurate than others when generating longer answers? It\u2019s hard to say because until now, we didn\u2019t have a benchmark measuring the factuality of LLM long-form responses. DeepMind first used GPT-4 to create LongFact, a set of","og_url":"https:\/\/dailyai.com\/sv\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/","og_site_name":"DailyAI","article_published_time":"2024-04-02T09:32:07+00:00","og_image":[{"width":1792,"height":1024,"url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/fact-vs-fake.webp","type":"image\/webp"}],"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":"4 minuter"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/dailyai.com\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/#article","isPartOf":{"@id":"https:\/\/dailyai.com\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/"},"author":{"name":"Eugene van der Watt","@id":"https:\/\/dailyai.com\/#\/schema\/person\/7ce525c6d0c79838b7cc7cde96993cfa"},"headline":"DeepMind developed SAFE, an AI agent to fact-check LLMs","datePublished":"2024-04-02T09:32:07+00:00","mainEntityOfPage":{"@id":"https:\/\/dailyai.com\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/"},"wordCount":611,"publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"image":{"@id":"https:\/\/dailyai.com\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/fact-vs-fake.webp","keywords":["DeepMind","LLMS"],"articleSection":["Industry"],"inLanguage":"sv-SE"},{"@type":"WebPage","@id":"https:\/\/dailyai.com\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/","url":"https:\/\/dailyai.com\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/","name":"DeepMind utvecklade SAFE, en AI-agent f\u00f6r att faktagranska LLM:er | DailyAI","isPartOf":{"@id":"https:\/\/dailyai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dailyai.com\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/#primaryimage"},"image":{"@id":"https:\/\/dailyai.com\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/fact-vs-fake.webp","datePublished":"2024-04-02T09:32:07+00:00","breadcrumb":{"@id":"https:\/\/dailyai.com\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/#breadcrumb"},"inLanguage":"sv-SE","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/"]}]},{"@type":"ImageObject","inLanguage":"sv-SE","@id":"https:\/\/dailyai.com\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/#primaryimage","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/fact-vs-fake.webp","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/fact-vs-fake.webp","width":1792,"height":1024},{"@type":"BreadcrumbList","@id":"https:\/\/dailyai.com\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dailyai.com\/"},{"@type":"ListItem","position":2,"name":"DeepMind developed SAFE, an AI agent to fact-check LLMs"}]},{"@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\/11172","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=11172"}],"version-history":[{"count":2,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/posts\/11172\/revisions"}],"predecessor-version":[{"id":11181,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/posts\/11172\/revisions\/11181"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/media\/11182"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/media?parent=11172"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/categories?post=11172"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/tags?post=11172"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}