{"id":8353,"date":"2023-12-16T04:46:40","date_gmt":"2023-12-16T04:46:40","guid":{"rendered":"https:\/\/dailyai.com\/?p=8353"},"modified":"2023-12-16T04:46:40","modified_gmt":"2023-12-16T04:46:40","slug":"microsoft-shades-gemini-with-gpt-4-boosted-by-medprompt","status":"publish","type":"post","link":"https:\/\/dailyai.com\/sv\/2023\/12\/microsoft-shades-gemini-with-gpt-4-boosted-by-medprompt\/","title":{"rendered":"Microsoft skuggar Gemini med GPT-4 som f\u00f6rst\u00e4rks av Medprompt"},"content":{"rendered":"<p><strong>Tidigare den h\u00e4r m\u00e5naden kunde Google stolt meddela att deras mest kraftfulla Gemini-modell slog GPT-4 i Massive Multitask Language Understanding MMLU benchmark-test. Microsofts nya prompting-teknik g\u00f6r att GPT-4 \u00e5tertar f\u00f6rstaplatsen, om \u00e4n med en br\u00e5kdel av en procent.<\/strong><\/p>\n<p>F\u00f6rutom dramatiken kring marknadsf\u00f6ringsvideon \u00e4r Googles Gemini en stor sak f\u00f6r f\u00f6retaget och dess MMLU-benchmarkresultat \u00e4r imponerande. Men Microsoft, OpenAI:s st\u00f6rsta investerare, v\u00e4ntade inte l\u00e4nge med att kasta skugga \u00f6ver Googles anstr\u00e4ngningar.<\/p>\n<p>Rubriken \u00e4r att Microsoft fick GPT-4 att sl\u00e5 Gemini Ultras MMLU-resultat. Verkligheten \u00e4r att det slog Geminis resultat p\u00e5 90,04% med bara 0,06%.<\/p>\n<p>Bakgrundshistorien om vad som gjorde detta m\u00f6jligt \u00e4r mer sp\u00e4nnande \u00e4n det inkrementella \u00f6verl\u00e4gsenhet som vi ser p\u00e5 dessa topplistor. Microsofts nya prompttekniker kan \u00f6ka prestandan hos \u00e4ldre AI-modeller.<\/p>\n<blockquote class=\"twitter-tweet\">\n<p dir=\"ltr\" lang=\"en\">Kommer du ih\u00e5g hur Googles outgivna Gemini Ultra just slog ut GPT-4 f\u00f6r att bli den b\u00e4sta AI?<\/p>\n<p>Microsoft har just visat att GPT-4, med r\u00e4tt uppmaning, faktiskt sl\u00e5r Gemini i benchmarks.<\/p>\n<p>Det finns gott om utrymme f\u00f6r f\u00f6rb\u00e4ttringar \u00e4ven med \u00e4ldre modeller. <a href=\"https:\/\/t.co\/YQ5zJI6Gad\">https:\/\/t.co\/YQ5zJI6Gad<\/a> <a href=\"https:\/\/t.co\/X3HFmXa30X\">pic.twitter.com\/X3HFmXa30X<\/a><\/p>\n<p>- Ethan Mollick (@emollick) <a href=\"https:\/\/twitter.com\/emollick\/status\/1734637276330651953?ref_src=twsrc%5Etfw\">12 december 2023<\/a><\/p><\/blockquote>\n<p><script async src=\"https:\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script><\/p>\n<h2>Medprompt<\/h2>\n<p>N\u00e4r man talar om att \"styra\" en modell menar man bara att man med f\u00f6rsiktiga uppmaningar kan styra en modell s\u00e5 att den ger ett resultat som \u00e4r b\u00e4ttre anpassat till det man ville ha.<\/p>\n<p>Microsoft utvecklade en kombination av prompttekniker som visade sig vara riktigt bra p\u00e5 detta. <a href=\"https:\/\/arxiv.org\/pdf\/2311.16452.pdf\" target=\"_blank\" rel=\"noopener\">Medprompt<\/a> startade som ett projekt f\u00f6r att f\u00e5 GPT-4 att ge b\u00e4ttre svar p\u00e5 medicinska utmaningsriktm\u00e4rken som MultiMedQA-testsviten.<\/p>\n<figure id=\"attachment_8354\" aria-describedby=\"caption-attachment-8354\" style=\"width: 1722px\" class=\"wp-caption aligncenter\"><img loading=\"lazy\" decoding=\"async\" class=\"size-full wp-image-8354\" src=\"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/Medprompt-improvements-on-MedQA-performance.png\" alt=\"\" width=\"1722\" height=\"906\" srcset=\"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/Medprompt-improvements-on-MedQA-performance.png 1722w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/Medprompt-improvements-on-MedQA-performance-300x158.png 300w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/Medprompt-improvements-on-MedQA-performance-1024x539.png 1024w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/Medprompt-improvements-on-MedQA-performance-768x404.png 768w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/Medprompt-improvements-on-MedQA-performance-1536x808.png 1536w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/Medprompt-improvements-on-MedQA-performance-370x195.png 370w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/Medprompt-improvements-on-MedQA-performance-800x421.png 800w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/Medprompt-improvements-on-MedQA-performance-20x11.png 20w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/Medprompt-improvements-on-MedQA-performance-740x389.png 740w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/Medprompt-improvements-on-MedQA-performance-1600x842.png 1600w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/Medprompt-improvements-on-MedQA-performance-1320x694.png 1320w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/Medprompt-improvements-on-MedQA-performance-91x48.png 91w\" sizes=\"auto, (max-width: 1722px) 100vw, 1722px\" \/><figcaption id=\"caption-attachment-8354\" class=\"wp-caption-text\">Medprompt f\u00f6rb\u00e4ttrar MedQA:s testprestanda. Microsoft<\/figcaption><\/figure>\n<p>Microsoft-forskarna t\u00e4nkte att om Medprompt fungerade bra i specialiserade medicinska tester skulle det ocks\u00e5 kunna f\u00f6rb\u00e4ttra GPT-4:s generalistiska prestanda. Och d\u00e4rmed \u00e5terfick Microsoft och OpenAI skrytr\u00e4ttigheterna med GPT-4 \u00f6ver Gemini Ultra.<\/p>\n<h2>Hur fungerar Medprompt?<\/h2>\n<p>Medprompt \u00e4r en kombination av smarta prompttekniker i ett och samma program. Den bygger p\u00e5 tre huvudtekniker.<\/p>\n<h4>Dynamisk inl\u00e4rning av f\u00e5 skott (DFSL)<\/h4>\n<p>\"Few-shot learning\" inneb\u00e4r att man ger GPT-4 n\u00e5gra exempel innan man ber den att l\u00f6sa ett liknande problem. N\u00e4r du ser en referens som \"5-shot\" betyder det att modellen fick 5 exempel. \"Zero-shot\" betyder att den var tvungen att svara utan n\u00e5gra exempel.<\/p>\n<p>I Medprompt-dokumentet f\u00f6rklaras att \"f\u00f6r enkelhetens och effektivitetens skull \u00e4r de f\u00e5 exempel som anv\u00e4nds f\u00f6r att uppmana till en viss uppgift vanligtvis fasta; de \u00e4r of\u00f6r\u00e4ndrade i alla testexempel.\"<\/p>\n<p>Resultatet blir att de exempel som modellerna presenteras med ofta bara \u00e4r relevanta eller representativa i stora drag.<\/p>\n<p>Om din tr\u00e4ningsupps\u00e4ttning \u00e4r tillr\u00e4ckligt stor kan du f\u00e5 modellen att titta igenom alla exempel och v\u00e4lja de som \u00e4r semantiskt lika det problem som den m\u00e5ste l\u00f6sa. Resultatet \u00e4r att de f\u00e5 inl\u00e4rningsexemplen \u00e4r mer specifikt inriktade p\u00e5 ett visst problem.<\/p>\n<h4>Sj\u00e4lvgenererad tankekedja (CoT)<\/h4>\n<p>Chain of Thought (CoT) \u00e4r ett utm\u00e4rkt s\u00e4tt att styra en LLM. N\u00e4r du uppmanar dem att \"t\u00e4nka efter noga\" eller \"l\u00f6sa det steg f\u00f6r steg\" blir resultaten mycket b\u00e4ttre.<\/p>\n<p>Du kan bli mycket mer specifik i ditt s\u00e4tt att styra tankekedjan som modellen ska f\u00f6lja, men det kr\u00e4ver manuell prompt engineering.<\/p>\n<p>Forskarna fann att de \"helt enkelt kunde be GPT-4 att generera tankekedjor f\u00f6r tr\u00e4ningsexemplen\". Deras tillv\u00e4gag\u00e5ngss\u00e4tt s\u00e4ger i princip till GPT-4: \"H\u00e4r \u00e4r en fr\u00e5ga, svarsalternativen och det r\u00e4tta svaret. Vilken CoT ska vi inkludera i en prompt som skulle komma fram till det h\u00e4r svaret?<\/p>\n<h4>Val Shuffle Ensembling<\/h4>\n<p>De flesta av MMLU:s riktm\u00e4rkestester \u00e4r flervalsfr\u00e5gor. N\u00e4r en AI-modell svarar p\u00e5 dessa fr\u00e5gor kan den bli offer f\u00f6r positionell partiskhet. Med andra ord kan den gynna alternativ B \u00f6ver tid \u00e4ven om det inte alltid \u00e4r r\u00e4tt svar.<\/p>\n<p>Choice Shuffle Ensembling blandar om svarsalternativens positioner och l\u00e5ter GPT-4 svara p\u00e5 fr\u00e5gan igen. Detta g\u00f6rs flera g\u00e5nger och sedan v\u00e4ljs det mest konsekvent valda svaret som det slutliga svaret.<\/p>\n<p>Kombinationen av dessa tre snabba tekniker \u00e4r vad som gav Microsoft m\u00f6jlighet att kasta lite skugga p\u00e5 Geminis resultat. Det kommer att bli intressant att se vilka resultat Gemini Ultra skulle uppn\u00e5 om det anv\u00e4nde ett liknande tillv\u00e4gag\u00e5ngss\u00e4tt.<\/p>\n<p>Medprompt \u00e4r sp\u00e4nnande eftersom det visar att \u00e4ldre modeller kan prestera \u00e4nnu b\u00e4ttre \u00e4n vi trodde om vi uppmanar dem p\u00e5 smarta s\u00e4tt. Den extra processorkraft som kr\u00e4vs f\u00f6r dessa extra steg kanske dock inte g\u00f6r det till ett genomf\u00f6rbart tillv\u00e4gag\u00e5ngss\u00e4tt i de flesta scenarier.<\/p>","protected":false},"excerpt":{"rendered":"<p>Tidigare den h\u00e4r m\u00e5naden kunde Google stolt meddela att deras mest kraftfulla Gemini-modell slog GPT-4 i Massive Multitask Language Understanding MMLU benchmark-test. Microsofts nya prompting-teknik g\u00f6r att GPT-4 \u00e5tertar f\u00f6rstaplatsen, om \u00e4n med en br\u00e5kdel av en procent. F\u00f6rutom dramatiken kring marknadsf\u00f6ringsvideon \u00e4r Googles Gemini en stor sak f\u00f6r f\u00f6retaget och dess MMLU-benchmarkresultat \u00e4r imponerande. Men Microsoft, OpenAI:s st\u00f6rsta investerare, v\u00e4ntade inte l\u00e4nge med att kasta skugga \u00f6ver Googles anstr\u00e4ngningar. Rubriken \u00e4r att Microsoft fick GPT-4 att sl\u00e5 Gemini Ultras MMLU-resultat. Verkligheten \u00e4r att den slog Geminis po\u00e4ng p\u00e5 90,04%<\/p>","protected":false},"author":6,"featured_media":8355,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[84],"tags":[99,102,118,121],"class_list":["post-8353","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-industry","tag-ai-race","tag-google","tag-llms","tag-microsoft"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.4 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Microsoft shades Gemini with GPT-4 boosted by Medprompt | 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\/12\/microsoft-shades-gemini-with-gpt-4-boosted-by-medprompt\/\" \/>\n<meta property=\"og:locale\" content=\"sv_SE\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Microsoft shades Gemini with GPT-4 boosted by Medprompt | DailyAI\" \/>\n<meta property=\"og:description\" content=\"Earlier this month Google proudly announced that its most powerful Gemini model beat GPT-4 on the Massive Multitask Language Understanding MMLU benchmark tests. Microsoft\u2019s new prompting technique sees GPT-4 regain the top spot, albeit by a fraction of a percent. Besides the drama surrounding its marketing video, Google\u2019s Gemini is a big deal for the company and its MMLU benchmark results are impressive. But Microsoft, OpenAI\u2019s biggest investor, didn\u2019t wait long to throw shade on Google\u2019s efforts. The headline is that Microsoft got GPT-4 to beat Gemini Ultra\u2019s MMLU results. The reality is that it beat Gemini\u2019s score of 90.04%\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dailyai.com\/sv\/2023\/12\/microsoft-shades-gemini-with-gpt-4-boosted-by-medprompt\/\" \/>\n<meta property=\"og:site_name\" content=\"DailyAI\" \/>\n<meta property=\"article:published_time\" content=\"2023-12-16T04:46:40+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/Microsoft-vs-Google.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1000\" \/>\n\t<meta property=\"og:image:height\" content=\"665\" \/>\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=\"4 minuter\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/microsoft-shades-gemini-with-gpt-4-boosted-by-medprompt\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/microsoft-shades-gemini-with-gpt-4-boosted-by-medprompt\\\/\"},\"author\":{\"name\":\"Eugene van der Watt\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/7ce525c6d0c79838b7cc7cde96993cfa\"},\"headline\":\"Microsoft shades Gemini with GPT-4 boosted by Medprompt\",\"datePublished\":\"2023-12-16T04:46:40+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/microsoft-shades-gemini-with-gpt-4-boosted-by-medprompt\\\/\"},\"wordCount\":756,\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/microsoft-shades-gemini-with-gpt-4-boosted-by-medprompt\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/12\\\/Microsoft-vs-Google.jpg\",\"keywords\":[\"AI race\",\"Google\",\"LLMS\",\"Microsoft\"],\"articleSection\":[\"Industry\"],\"inLanguage\":\"sv-SE\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/microsoft-shades-gemini-with-gpt-4-boosted-by-medprompt\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/microsoft-shades-gemini-with-gpt-4-boosted-by-medprompt\\\/\",\"name\":\"Microsoft shades Gemini with GPT-4 boosted by Medprompt | DailyAI\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/microsoft-shades-gemini-with-gpt-4-boosted-by-medprompt\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/microsoft-shades-gemini-with-gpt-4-boosted-by-medprompt\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/12\\\/Microsoft-vs-Google.jpg\",\"datePublished\":\"2023-12-16T04:46:40+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/microsoft-shades-gemini-with-gpt-4-boosted-by-medprompt\\\/#breadcrumb\"},\"inLanguage\":\"sv-SE\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/microsoft-shades-gemini-with-gpt-4-boosted-by-medprompt\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"sv-SE\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/microsoft-shades-gemini-with-gpt-4-boosted-by-medprompt\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/12\\\/Microsoft-vs-Google.jpg\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/12\\\/Microsoft-vs-Google.jpg\",\"width\":1000,\"height\":665},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/microsoft-shades-gemini-with-gpt-4-boosted-by-medprompt\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dailyai.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Microsoft shades Gemini with GPT-4 boosted by Medprompt\"}]},{\"@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":"Microsoft skuggar Gemini med GPT-4 f\u00f6rst\u00e4rkt av Medprompt | 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\/12\/microsoft-shades-gemini-with-gpt-4-boosted-by-medprompt\/","og_locale":"sv_SE","og_type":"article","og_title":"Microsoft shades Gemini with GPT-4 boosted by Medprompt | DailyAI","og_description":"Earlier this month Google proudly announced that its most powerful Gemini model beat GPT-4 on the Massive Multitask Language Understanding MMLU benchmark tests. Microsoft\u2019s new prompting technique sees GPT-4 regain the top spot, albeit by a fraction of a percent. Besides the drama surrounding its marketing video, Google\u2019s Gemini is a big deal for the company and its MMLU benchmark results are impressive. But Microsoft, OpenAI\u2019s biggest investor, didn\u2019t wait long to throw shade on Google\u2019s efforts. The headline is that Microsoft got GPT-4 to beat Gemini Ultra\u2019s MMLU results. The reality is that it beat Gemini\u2019s score of 90.04%","og_url":"https:\/\/dailyai.com\/sv\/2023\/12\/microsoft-shades-gemini-with-gpt-4-boosted-by-medprompt\/","og_site_name":"DailyAI","article_published_time":"2023-12-16T04:46:40+00:00","og_image":[{"width":1000,"height":665,"url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/Microsoft-vs-Google.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":"4 minuter"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/dailyai.com\/2023\/12\/microsoft-shades-gemini-with-gpt-4-boosted-by-medprompt\/#article","isPartOf":{"@id":"https:\/\/dailyai.com\/2023\/12\/microsoft-shades-gemini-with-gpt-4-boosted-by-medprompt\/"},"author":{"name":"Eugene van der Watt","@id":"https:\/\/dailyai.com\/#\/schema\/person\/7ce525c6d0c79838b7cc7cde96993cfa"},"headline":"Microsoft shades Gemini with GPT-4 boosted by Medprompt","datePublished":"2023-12-16T04:46:40+00:00","mainEntityOfPage":{"@id":"https:\/\/dailyai.com\/2023\/12\/microsoft-shades-gemini-with-gpt-4-boosted-by-medprompt\/"},"wordCount":756,"publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"image":{"@id":"https:\/\/dailyai.com\/2023\/12\/microsoft-shades-gemini-with-gpt-4-boosted-by-medprompt\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/Microsoft-vs-Google.jpg","keywords":["AI race","Google","LLMS","Microsoft"],"articleSection":["Industry"],"inLanguage":"sv-SE"},{"@type":"WebPage","@id":"https:\/\/dailyai.com\/2023\/12\/microsoft-shades-gemini-with-gpt-4-boosted-by-medprompt\/","url":"https:\/\/dailyai.com\/2023\/12\/microsoft-shades-gemini-with-gpt-4-boosted-by-medprompt\/","name":"Microsoft skuggar Gemini med GPT-4 f\u00f6rst\u00e4rkt av Medprompt | DailyAI","isPartOf":{"@id":"https:\/\/dailyai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dailyai.com\/2023\/12\/microsoft-shades-gemini-with-gpt-4-boosted-by-medprompt\/#primaryimage"},"image":{"@id":"https:\/\/dailyai.com\/2023\/12\/microsoft-shades-gemini-with-gpt-4-boosted-by-medprompt\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/Microsoft-vs-Google.jpg","datePublished":"2023-12-16T04:46:40+00:00","breadcrumb":{"@id":"https:\/\/dailyai.com\/2023\/12\/microsoft-shades-gemini-with-gpt-4-boosted-by-medprompt\/#breadcrumb"},"inLanguage":"sv-SE","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2023\/12\/microsoft-shades-gemini-with-gpt-4-boosted-by-medprompt\/"]}]},{"@type":"ImageObject","inLanguage":"sv-SE","@id":"https:\/\/dailyai.com\/2023\/12\/microsoft-shades-gemini-with-gpt-4-boosted-by-medprompt\/#primaryimage","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/Microsoft-vs-Google.jpg","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/Microsoft-vs-Google.jpg","width":1000,"height":665},{"@type":"BreadcrumbList","@id":"https:\/\/dailyai.com\/2023\/12\/microsoft-shades-gemini-with-gpt-4-boosted-by-medprompt\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dailyai.com\/"},{"@type":"ListItem","position":2,"name":"Microsoft shades Gemini with GPT-4 boosted by Medprompt"}]},{"@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\/8353","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=8353"}],"version-history":[{"count":4,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/posts\/8353\/revisions"}],"predecessor-version":[{"id":8359,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/posts\/8353\/revisions\/8359"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/media\/8355"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/media?parent=8353"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/categories?post=8353"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/tags?post=8353"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}