{"id":11632,"date":"2024-04-17T11:48:55","date_gmt":"2024-04-17T11:48:55","guid":{"rendered":"https:\/\/dailyai.com\/?p=11632"},"modified":"2024-04-17T11:48:55","modified_gmt":"2024-04-17T11:48:55","slug":"report-ai-is-advancing-beyond-humans-we-need-new-benchmarks","status":"publish","type":"post","link":"https:\/\/dailyai.com\/fr\/2024\/04\/report-ai-is-advancing-beyond-humans-we-need-new-benchmarks\/","title":{"rendered":"Rapport : L'IA progresse au-del\u00e0 des humains, nous avons besoin de nouveaux rep\u00e8res"},"content":{"rendered":"<p><strong>L'universit\u00e9 de Stanford a publi\u00e9 son rapport sur l'indice de l'IA pour 2024, qui indique que les progr\u00e8s rapides de l'IA rendent les comparaisons avec les humains de moins en moins pertinentes.<\/strong><\/p>\n<p>Les <a href=\"https:\/\/aiindex.stanford.edu\/wp-content\/uploads\/2024\/04\/HAI_AI-Index-Report-2024.pdf\" target=\"_blank\" rel=\"noopener\">rapport annuel<\/a> donne un aper\u00e7u complet des tendances et de l'\u00e9tat d'avancement des d\u00e9veloppements en mati\u00e8re d'IA. Le rapport indique que les mod\u00e8les d'IA s'am\u00e9liorent si rapidement que les crit\u00e8res de r\u00e9f\u00e9rence que nous utilisons pour les mesurer deviennent de moins en moins pertinents.<\/p>\n<p>De nombreux crit\u00e8res de r\u00e9f\u00e9rence industriels comparent les mod\u00e8les d'IA \u00e0 l'efficacit\u00e9 des humains dans l'ex\u00e9cution de t\u00e2ches. Le benchmark Massive Multitask Language Understanding (MMLU) en est un bon exemple.<\/p>\n<p>Il utilise des questions \u00e0 choix multiples pour \u00e9valuer les LLM dans 57 mati\u00e8res, dont les math\u00e9matiques, l'histoire, le droit et l'\u00e9thique. Le MMLU est la r\u00e9f\u00e9rence en mati\u00e8re d'IA depuis 2019.<\/p>\n<p>Le score de r\u00e9f\u00e9rence humain sur le MMLU est de 89,8%, et en 2019, le mod\u00e8le d'IA moyen a obtenu un peu plus de 30%. Cinq ans plus tard, Gemini Ultra est devenu le premier mod\u00e8le \u00e0 battre la r\u00e9f\u00e9rence humaine avec un score de 90,04%.<\/p>\n<p>Le rapport note que les \"syst\u00e8mes d'IA actuels d\u00e9passent r\u00e9guli\u00e8rement les performances humaines sur les crit\u00e8res de r\u00e9f\u00e9rence standard\". Les tendances du graphique ci-dessous semblent indiquer que le MMLU et d'autres crit\u00e8res doivent \u00eatre remplac\u00e9s.<\/p>\n<figure id=\"attachment_11647\" aria-describedby=\"caption-attachment-11647\" style=\"width: 1396px\" class=\"wp-caption aligncenter\"><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-11647 size-full\" src=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/AI-benchmarking-trends.png\" alt=\"\" width=\"1396\" height=\"942\" srcset=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/AI-benchmarking-trends.png 1396w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/AI-benchmarking-trends-300x202.png 300w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/AI-benchmarking-trends-1024x691.png 1024w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/AI-benchmarking-trends-768x518.png 768w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/AI-benchmarking-trends-60x40.png 60w\" sizes=\"auto, (max-width: 1396px) 100vw, 1396px\" \/><figcaption id=\"caption-attachment-11647\" class=\"wp-caption-text\">Les mod\u00e8les d'IA ont atteint et d\u00e9pass\u00e9 les r\u00e9f\u00e9rences humaines dans de nombreux domaines. Source : Rapport annuel de l'indice AI 2024<\/figcaption><\/figure>\n<p>Les mod\u00e8les d'IA ont atteint la saturation des performances sur des crit\u00e8res de r\u00e9f\u00e9rence \u00e9tablis tels que ImageNet, SQuAD et SuperGLUE, de sorte que les chercheurs d\u00e9veloppent des tests plus difficiles.<\/p>\n<p>Un exemple est le Graduate-Level Google-Proof Q&amp;A Benchmark (GPQA), qui permet d'\u00e9valuer les mod\u00e8les d'IA par rapport \u00e0 des personnes vraiment intelligentes, plut\u00f4t que par rapport \u00e0 l'intelligence humaine moyenne.<\/p>\n<p>Le test GPQA se compose de 400 questions \u00e0 choix multiples difficiles, de niveau universitaire. Les experts qui ont obtenu ou poursuivent leur doctorat r\u00e9pondent correctement aux questions dans 65% des cas.<\/p>\n<p>Le document du GPQA indique que lorsqu'on leur pose des questions en dehors de leur domaine, \"des validateurs non experts hautement qualifi\u00e9s n'atteignent qu'une pr\u00e9cision de 34%, bien qu'ils aient pass\u00e9 en moyenne plus de 30 minutes avec un acc\u00e8s illimit\u00e9 \u00e0 l'Internet\".<\/p>\n<p>Le mois dernier, Anthropic a annonc\u00e9 que <a href=\"https:\/\/dailyai.com\/fr\/2024\/04\/claude-3-opus-blows-all-llms-away-in-book-length-summarization\/\">Claude 3<\/a> a obtenu un r\u00e9sultat l\u00e9g\u00e8rement inf\u00e9rieur \u00e0 60% avec une incitation CoT \u00e0 5 coups. Nous allons avoir besoin d'une r\u00e9f\u00e9rence plus importante.<\/p>\n<blockquote class=\"twitter-tweet\">\n<p dir=\"ltr\" lang=\"en\">Claude 3 obtient une pr\u00e9cision de ~60% au GPQA. Il m'est difficile de sous-estimer la difficult\u00e9 de ces questions : des docteurs litt\u00e9raires (dans des domaines diff\u00e9rents de ceux des questions) ayant acc\u00e8s \u00e0 l'internet obtiennent 34%.<\/p>\n<p>Les doctorants *dans le m\u00eame domaine* (\u00e9galement avec acc\u00e8s \u00e0 l'internet !) obtiennent une pr\u00e9cision de 65% - 75%. <a href=\"https:\/\/t.co\/ARAiCNXgU9\">https:\/\/t.co\/ARAiCNXgU9<\/a> <a href=\"https:\/\/t.co\/PH8J13zIef\">pic.twitter.com\/PH8J13zIef<\/a><\/p>\n<p>- david rein (@idavidrein) <a href=\"https:\/\/twitter.com\/idavidrein\/status\/1764675668175094169?ref_src=twsrc%5Etfw\">4 mars 2024<\/a><\/p><\/blockquote>\n<p><script async src=\"https:\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script><\/p>\n<h2>\u00c9valuations humaines et s\u00e9curit\u00e9<\/h2>\n<p>Le rapport note que l'IA est encore confront\u00e9e \u00e0 des probl\u00e8mes importants : \"Elle ne peut pas traiter les faits de mani\u00e8re fiable, effectuer des raisonnements complexes ou expliquer ses conclusions.<\/p>\n<p>Ces limites contribuent \u00e0 une autre caract\u00e9ristique du syst\u00e8me d'IA qui, selon le rapport, est mal mesur\u00e9e ; <a href=\"https:\/\/dailyai.com\/fr\/2024\/04\/just-2-of-ai-research-is-looking-at-safety-says-georgetown-university-study\/\">S\u00e9curit\u00e9 de l'IA<\/a>. Nous ne disposons pas de crit\u00e8res de r\u00e9f\u00e9rence efficaces qui nous permettraient de dire : \"Ce mod\u00e8le est plus s\u00fbr que celui-l\u00e0\".<\/p>\n<p>Cela s'explique en partie par le fait qu'elle est difficile \u00e0 mesurer et que \"les d\u00e9veloppeurs d'IA manquent de transparence, notamment en ce qui concerne la divulgation des donn\u00e9es et des m\u00e9thodologies de formation\".<\/p>\n<p>Le rapport note qu'une tendance int\u00e9ressante dans l'industrie est de faire appel \u00e0 des \u00e9valuations humaines des performances de l'IA, plut\u00f4t qu'\u00e0 des tests de r\u00e9f\u00e9rence.<\/p>\n<p>Il est difficile de classer l'esth\u00e9tique ou la prose d'un mod\u00e8le \u00e0 l'aide d'un test. En cons\u00e9quence, le rapport indique que \"l'\u00e9valuation comparative a lentement commenc\u00e9 \u00e0 s'orienter vers l'incorporation d'\u00e9valuations humaines comme le Chatbot Arena Leaderboard plut\u00f4t que vers des classements informatis\u00e9s comme ImageNet ou SQuAD\".<\/p>\n<p>Alors que les mod\u00e8les d'IA voient la r\u00e9f\u00e9rence humaine dispara\u00eetre dans le r\u00e9troviseur, le sentiment pourrait finalement d\u00e9terminer le mod\u00e8le que nous choisirons d'utiliser.<\/p>\n<p>Les tendances indiquent que les mod\u00e8les d'IA finiront par \u00eatre plus intelligents que nous et plus difficiles \u00e0 mesurer. Nous pourrions bient\u00f4t nous retrouver \u00e0 dire : \"Je ne sais pas pourquoi, mais je pr\u00e9f\u00e8re celui-ci\".<\/p>","protected":false},"excerpt":{"rendered":"<p>L'universit\u00e9 de Stanford a publi\u00e9 son AI Index Report 2024 qui note que les progr\u00e8s rapides de l'IA rendent les comparaisons de r\u00e9f\u00e9rence avec les humains de moins en moins pertinentes. Le rapport annuel donne un aper\u00e7u complet des tendances et de l'\u00e9tat des d\u00e9veloppements de l'IA. Le rapport indique que les mod\u00e8les d'IA s'am\u00e9liorent si rapidement que les crit\u00e8res de r\u00e9f\u00e9rence que nous utilisons pour les mesurer deviennent de moins en moins pertinents. De nombreux crit\u00e8res industriels comparent les mod\u00e8les d'IA \u00e0 la capacit\u00e9 des humains \u00e0 effectuer des t\u00e2ches. Le test Massive Multitask Language Understanding (MMLU) en est un bon exemple. Il utilise des questions \u00e0 choix multiples pour \u00e9valuer les LLM dans 57 mati\u00e8res, y compris les math\u00e9matiques, l'histoire,<\/p>","protected":false},"author":6,"featured_media":11650,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[84],"tags":[103,99],"class_list":["post-11632","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-industry","tag-ai-debate","tag-ai-race"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.4 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Report: AI is advancing beyond humans, we need new benchmarks | 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\/fr\/2024\/04\/report-ai-is-advancing-beyond-humans-we-need-new-benchmarks\/\" \/>\n<meta property=\"og:locale\" content=\"fr_FR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Report: AI is advancing beyond humans, we need new benchmarks | DailyAI\" \/>\n<meta property=\"og:description\" content=\"Stanford University released its AI Index Report 2024 which noted that AI\u2019s rapid advancement makes benchmark comparisons with humans increasingly less relevant. The annual report provides a comprehensive insight into the trends and state of AI developments. The report says that AI models are improving so fast now that the benchmarks we use to measure them are increasingly becoming irrelevant. A lot of industry benchmarks compare AI models to how good humans are at performing tasks. The Massive Multitask Language Understanding (MMLU) benchmark is a good example. It uses multiple-choice questions to evaluate LLMs across 57 subjects, including math, history,\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dailyai.com\/fr\/2024\/04\/report-ai-is-advancing-beyond-humans-we-need-new-benchmarks\/\" \/>\n<meta property=\"og:site_name\" content=\"DailyAI\" \/>\n<meta property=\"article:published_time\" content=\"2024-04-17T11:48:55+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/AI-benchmarks.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=\"\u00c9crit par\" \/>\n\t<meta name=\"twitter:data1\" content=\"Eugene van der Watt\" \/>\n\t<meta name=\"twitter:label2\" content=\"Dur\u00e9e de lecture estim\u00e9e\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/report-ai-is-advancing-beyond-humans-we-need-new-benchmarks\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/report-ai-is-advancing-beyond-humans-we-need-new-benchmarks\\\/\"},\"author\":{\"name\":\"Eugene van der Watt\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/7ce525c6d0c79838b7cc7cde96993cfa\"},\"headline\":\"Report: AI is advancing beyond humans, we need new benchmarks\",\"datePublished\":\"2024-04-17T11:48:55+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/report-ai-is-advancing-beyond-humans-we-need-new-benchmarks\\\/\"},\"wordCount\":601,\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/report-ai-is-advancing-beyond-humans-we-need-new-benchmarks\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/AI-benchmarks.webp\",\"keywords\":[\"AI debate\",\"AI race\"],\"articleSection\":[\"Industry\"],\"inLanguage\":\"fr-FR\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/report-ai-is-advancing-beyond-humans-we-need-new-benchmarks\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/report-ai-is-advancing-beyond-humans-we-need-new-benchmarks\\\/\",\"name\":\"Report: AI is advancing beyond humans, we need new benchmarks | DailyAI\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/report-ai-is-advancing-beyond-humans-we-need-new-benchmarks\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/report-ai-is-advancing-beyond-humans-we-need-new-benchmarks\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/AI-benchmarks.webp\",\"datePublished\":\"2024-04-17T11:48:55+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/report-ai-is-advancing-beyond-humans-we-need-new-benchmarks\\\/#breadcrumb\"},\"inLanguage\":\"fr-FR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/report-ai-is-advancing-beyond-humans-we-need-new-benchmarks\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/report-ai-is-advancing-beyond-humans-we-need-new-benchmarks\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/AI-benchmarks.webp\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/AI-benchmarks.webp\",\"width\":1792,\"height\":1024},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/report-ai-is-advancing-beyond-humans-we-need-new-benchmarks\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dailyai.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Report: AI is advancing beyond humans, we need new benchmarks\"}]},{\"@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\":\"fr-FR\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\",\"name\":\"DailyAI\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@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\":\"fr-FR\",\"@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\\\/fr\\\/author\\\/eugene\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Rapport : L'IA progresse au-del\u00e0 des humains, nous avons besoin de nouveaux rep\u00e8res | 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\/fr\/2024\/04\/report-ai-is-advancing-beyond-humans-we-need-new-benchmarks\/","og_locale":"fr_FR","og_type":"article","og_title":"Report: AI is advancing beyond humans, we need new benchmarks | DailyAI","og_description":"Stanford University released its AI Index Report 2024 which noted that AI\u2019s rapid advancement makes benchmark comparisons with humans increasingly less relevant. The annual report provides a comprehensive insight into the trends and state of AI developments. The report says that AI models are improving so fast now that the benchmarks we use to measure them are increasingly becoming irrelevant. A lot of industry benchmarks compare AI models to how good humans are at performing tasks. The Massive Multitask Language Understanding (MMLU) benchmark is a good example. It uses multiple-choice questions to evaluate LLMs across 57 subjects, including math, history,","og_url":"https:\/\/dailyai.com\/fr\/2024\/04\/report-ai-is-advancing-beyond-humans-we-need-new-benchmarks\/","og_site_name":"DailyAI","article_published_time":"2024-04-17T11:48:55+00:00","og_image":[{"width":1792,"height":1024,"url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/AI-benchmarks.webp","type":"image\/webp"}],"author":"Eugene van der Watt","twitter_card":"summary_large_image","twitter_creator":"@DailyAIOfficial","twitter_site":"@DailyAIOfficial","twitter_misc":{"\u00c9crit par":"Eugene van der Watt","Dur\u00e9e de lecture estim\u00e9e":"3 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/dailyai.com\/2024\/04\/report-ai-is-advancing-beyond-humans-we-need-new-benchmarks\/#article","isPartOf":{"@id":"https:\/\/dailyai.com\/2024\/04\/report-ai-is-advancing-beyond-humans-we-need-new-benchmarks\/"},"author":{"name":"Eugene van der Watt","@id":"https:\/\/dailyai.com\/#\/schema\/person\/7ce525c6d0c79838b7cc7cde96993cfa"},"headline":"Report: AI is advancing beyond humans, we need new benchmarks","datePublished":"2024-04-17T11:48:55+00:00","mainEntityOfPage":{"@id":"https:\/\/dailyai.com\/2024\/04\/report-ai-is-advancing-beyond-humans-we-need-new-benchmarks\/"},"wordCount":601,"publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"image":{"@id":"https:\/\/dailyai.com\/2024\/04\/report-ai-is-advancing-beyond-humans-we-need-new-benchmarks\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/AI-benchmarks.webp","keywords":["AI debate","AI race"],"articleSection":["Industry"],"inLanguage":"fr-FR"},{"@type":"WebPage","@id":"https:\/\/dailyai.com\/2024\/04\/report-ai-is-advancing-beyond-humans-we-need-new-benchmarks\/","url":"https:\/\/dailyai.com\/2024\/04\/report-ai-is-advancing-beyond-humans-we-need-new-benchmarks\/","name":"Rapport : L'IA progresse au-del\u00e0 des humains, nous avons besoin de nouveaux rep\u00e8res | DailyAI","isPartOf":{"@id":"https:\/\/dailyai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dailyai.com\/2024\/04\/report-ai-is-advancing-beyond-humans-we-need-new-benchmarks\/#primaryimage"},"image":{"@id":"https:\/\/dailyai.com\/2024\/04\/report-ai-is-advancing-beyond-humans-we-need-new-benchmarks\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/AI-benchmarks.webp","datePublished":"2024-04-17T11:48:55+00:00","breadcrumb":{"@id":"https:\/\/dailyai.com\/2024\/04\/report-ai-is-advancing-beyond-humans-we-need-new-benchmarks\/#breadcrumb"},"inLanguage":"fr-FR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2024\/04\/report-ai-is-advancing-beyond-humans-we-need-new-benchmarks\/"]}]},{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/dailyai.com\/2024\/04\/report-ai-is-advancing-beyond-humans-we-need-new-benchmarks\/#primaryimage","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/AI-benchmarks.webp","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/AI-benchmarks.webp","width":1792,"height":1024},{"@type":"BreadcrumbList","@id":"https:\/\/dailyai.com\/2024\/04\/report-ai-is-advancing-beyond-humans-we-need-new-benchmarks\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dailyai.com\/"},{"@type":"ListItem","position":2,"name":"Report: AI is advancing beyond humans, we need new benchmarks"}]},{"@type":"WebSite","@id":"https:\/\/dailyai.com\/#website","url":"https:\/\/dailyai.com\/","name":"DailyAI","description":"Votre dose quotidienne de nouvelles sur l'IA","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":"fr-FR"},{"@type":"Organization","@id":"https:\/\/dailyai.com\/#organization","name":"DailyAI","url":"https:\/\/dailyai.com\/","logo":{"@type":"ImageObject","inLanguage":"fr-FR","@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":"Eug\u00e8ne van der Watt","image":{"@type":"ImageObject","inLanguage":"fr-FR","@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 a une formation d'ing\u00e9nieur en \u00e9lectronique et adore tout ce qui touche \u00e0 la technologie. Lorsqu'il fait une pause dans sa consommation d'informations sur l'IA, vous le trouverez \u00e0 la table de snooker.","sameAs":["www.linkedin.com\/in\/eugene-van-der-watt-16828119"],"url":"https:\/\/dailyai.com\/fr\/author\/eugene\/"}]}},"_links":{"self":[{"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/posts\/11632","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/users\/6"}],"replies":[{"embeddable":true,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/comments?post=11632"}],"version-history":[{"count":3,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/posts\/11632\/revisions"}],"predecessor-version":[{"id":11652,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/posts\/11632\/revisions\/11652"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/media\/11650"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/media?parent=11632"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/categories?post=11632"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/tags?post=11632"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}