{"id":10589,"date":"2024-03-08T13:34:19","date_gmt":"2024-03-08T13:34:19","guid":{"rendered":"https:\/\/dailyai.com\/?p=10589"},"modified":"2024-03-08T13:34:19","modified_gmt":"2024-03-08T13:34:19","slug":"researchers-jailbreak-llms-by-using-ascii-art-in-prompts","status":"publish","type":"post","link":"https:\/\/dailyai.com\/fr\/2024\/03\/researchers-jailbreak-llms-by-using-ascii-art-in-prompts\/","title":{"rendered":"Des chercheurs cassent les LLM en utilisant de l'art ASCII dans les messages-guides"},"content":{"rendered":"

Les chercheurs ont mis au point une attaque de jailbreak appel\u00e9e ArtPrompt, qui utilise l'art ASCII pour contourner les garde-fous d'un LLM.<\/strong><\/p>\n

Si vous vous souvenez de l'\u00e9poque o\u00f9 les ordinateurs ne pouvaient pas g\u00e9rer les graphiques, vous connaissez probablement l'art ASCII. Un caract\u00e8re ASCII est essentiellement une lettre, un chiffre, un symbole ou un signe de ponctuation qu'un ordinateur peut comprendre. L'art ASCII est cr\u00e9\u00e9 en arrangeant ces caract\u00e8res en diff\u00e9rentes formes.<\/p>\n

Les chercheurs de l'Universit\u00e9 de Washington, de l'Universit\u00e9 Western Washington et de l'Universit\u00e9 de Chicago a publi\u00e9 un article<\/a> montrant comment ils ont utilis\u00e9 l'art ASCII pour glisser des mots normalement tabous dans leurs messages.<\/p>\n

Si vous demandez \u00e0 un LLM de vous expliquer comment fabriquer une bombe, ses garde-fous se d\u00e9clenchent et il refuse de vous aider. Les chercheurs ont constat\u00e9 que si vous remplacez le mot \"bombe\" par une repr\u00e9sentation visuelle ASCII du mot, il est heureux de vous aider.<\/p>\n

\"\"
Un exemple de la fa\u00e7on dont l'art ASCII du mot \"bombe\" est inject\u00e9 dans une invite. Source : arXiv<\/figcaption><\/figure>\n

Ils ont test\u00e9 la m\u00e9thode sur GPT-3.5, GPT-4, Gemini, Claude et Llama2. jailbreak<\/a> m\u00e9thode.<\/p>\n

Les m\u00e9thodes d'alignement de s\u00e9curit\u00e9 LLM se concentrent sur la s\u00e9mantique du langage naturel pour d\u00e9cider si une invite est s\u00fbre ou non. La m\u00e9thode ArtPrompt jailbreaking met en \u00e9vidence les lacunes de cette approche.<\/p>\n

Avec les mod\u00e8les multimodaux, les d\u00e9veloppeurs se sont surtout pench\u00e9s sur les invites qui tentent de dissimuler des invites dangereuses int\u00e9gr\u00e9es dans des images. ArtPrompt montre que les mod\u00e8les purement linguistiques sont susceptibles d'\u00eatre attaqu\u00e9s au-del\u00e0 de la s\u00e9mantique des mots de l'invite.<\/p>\n

Lorsque le LLM est tellement concentr\u00e9 sur la t\u00e2che de reconna\u00eetre le mot repr\u00e9sent\u00e9 dans l'art ASCII, il oublie souvent de signaler le mot incrimin\u00e9 une fois qu'il l'a trouv\u00e9.<\/p>\n

Voici un exemple de la fa\u00e7on dont l'invite d'ArtPrompt est construite.<\/p>\n

\"\"
L'invite compl\u00e8te illustrant comment ArtPrompt demande au LLM d'analyser l'art ASCII. Source : arXiv<\/figcaption><\/figure>\n

L'article n'explique pas exactement comment un LLM d\u00e9pourvu de capacit\u00e9s multimodales est capable de d\u00e9chiffrer les lettres repr\u00e9sent\u00e9es par les caract\u00e8res ASCII. Mais cela fonctionne.<\/p>\n

En r\u00e9ponse \u00e0 la question ci-dessus, GPT-4 s'est fait un plaisir de donner une r\u00e9ponse d\u00e9taill\u00e9e sur la mani\u00e8re de tirer le meilleur parti de votre fausse monnaie.<\/p>\n

Non seulement cette approche ne respecte pas les cinq mod\u00e8les test\u00e9s, mais les chercheurs sugg\u00e8rent qu'elle pourrait m\u00eame confondre les mod\u00e8les multimodaux qui pourraient traiter par d\u00e9faut l'art ASCII comme du texte.<\/p>\n

Les chercheurs ont mis au point un test de r\u00e9f\u00e9rence appel\u00e9 Vision-in-Text Challenge (VITC) afin d'\u00e9valuer les capacit\u00e9s des LLM en r\u00e9ponse \u00e0 des invites comme ArtPrompt. Les r\u00e9sultats de l'analyse comparative ont montr\u00e9 que Llama2 \u00e9tait le moins vuln\u00e9rable, tandis que Gemini Pro et GPT-3.5 \u00e9taient les plus faciles \u00e0 jailbreaker.<\/p>\n

Les chercheurs ont publi\u00e9 leurs r\u00e9sultats en esp\u00e9rant que les d\u00e9veloppeurs trouveraient un moyen de corriger la vuln\u00e9rabilit\u00e9. Si quelque chose d'aussi al\u00e9atoire qu'un dessin ASCII a pu percer les d\u00e9fenses d'un LLM, on peut se demander combien d'attaques non publi\u00e9es sont utilis\u00e9es par des personnes dont les int\u00e9r\u00eats ne sont pas acad\u00e9miques.<\/p>","protected":false},"excerpt":{"rendered":"

Des chercheurs ont mis au point une attaque de jailbreak appel\u00e9e ArtPrompt, qui utilise l'art ASCII pour contourner les garde-fous d'un LLM. Si vous vous souvenez de l'\u00e9poque o\u00f9 les ordinateurs ne pouvaient pas g\u00e9rer les graphiques, vous connaissez probablement l'art ASCII. Un caract\u00e8re ASCII est essentiellement une lettre, un chiffre, un symbole ou un signe de ponctuation qu'un ordinateur peut comprendre. L'art ASCII est cr\u00e9\u00e9 en arrangeant ces caract\u00e8res en diff\u00e9rentes formes. Les chercheurs de l'universit\u00e9 de Washington, de l'universit\u00e9 Western Washington et de l'universit\u00e9 de Chicago ont publi\u00e9 un article montrant comment ils ont utilis\u00e9 l'art ASCII pour introduire subrepticement des mots normalement tabous dans leurs messages-guides. Si vous demandez \u00e0 un LLM de vous expliquer comment fabriquer une bombe,<\/p>","protected":false},"author":6,"featured_media":10595,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[84],"tags":[163,118],"class_list":["post-10589","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-industry","tag-ai-risks","tag-llms"],"yoast_head":"\n\u200b\u200bResearchers jailbreak LLMs by using ASCII art in prompts | 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\/03\/researchers-jailbreak-llms-by-using-ascii-art-in-prompts\/\" \/>\n<meta property=\"og:locale\" content=\"fr_FR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"\u200b\u200bResearchers jailbreak LLMs by using ASCII art in prompts | DailyAI\" \/>\n<meta property=\"og:description\" content=\"Researchers developed a jailbreak attack called ArtPrompt, which uses ASCII art to bypass an LLM\u2019s guardrails. If you remember a time before computers could handle graphics, you\u2019re probably familiar with ASCII art. An ASCII character is basically a letter, number, symbol, or punctuation mark that a computer can understand. ASCII art is created by arranging these characters into different shapes. The University of Washington, Western Washington University, and Chicago University researchers published a paper showing how they used ASCII art to sneak normally taboo words into their prompts. If you ask an LLM to explain how to build a bomb,\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dailyai.com\/fr\/2024\/03\/researchers-jailbreak-llms-by-using-ascii-art-in-prompts\/\" \/>\n<meta property=\"og:site_name\" content=\"DailyAI\" \/>\n<meta property=\"article:published_time\" content=\"2024-03-08T13:34:19+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/ASCII-art-error.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1000\" \/>\n\t<meta property=\"og:image:height\" content=\"667\" \/>\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=\"\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\\\/03\\\/researchers-jailbreak-llms-by-using-ascii-art-in-prompts\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/researchers-jailbreak-llms-by-using-ascii-art-in-prompts\\\/\"},\"author\":{\"name\":\"Eugene van der Watt\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/7ce525c6d0c79838b7cc7cde96993cfa\"},\"headline\":\"\u200b\u200bResearchers jailbreak LLMs by using ASCII art in prompts\",\"datePublished\":\"2024-03-08T13:34:19+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/researchers-jailbreak-llms-by-using-ascii-art-in-prompts\\\/\"},\"wordCount\":500,\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/researchers-jailbreak-llms-by-using-ascii-art-in-prompts\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/03\\\/ASCII-art-error.jpg\",\"keywords\":[\"AI risks\",\"LLMS\"],\"articleSection\":[\"Industry\"],\"inLanguage\":\"fr-FR\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/researchers-jailbreak-llms-by-using-ascii-art-in-prompts\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/researchers-jailbreak-llms-by-using-ascii-art-in-prompts\\\/\",\"name\":\"\u200b\u200bResearchers jailbreak LLMs by using ASCII art in prompts | DailyAI\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/researchers-jailbreak-llms-by-using-ascii-art-in-prompts\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/researchers-jailbreak-llms-by-using-ascii-art-in-prompts\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/03\\\/ASCII-art-error.jpg\",\"datePublished\":\"2024-03-08T13:34:19+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/researchers-jailbreak-llms-by-using-ascii-art-in-prompts\\\/#breadcrumb\"},\"inLanguage\":\"fr-FR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/researchers-jailbreak-llms-by-using-ascii-art-in-prompts\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/researchers-jailbreak-llms-by-using-ascii-art-in-prompts\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/03\\\/ASCII-art-error.jpg\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/03\\\/ASCII-art-error.jpg\",\"width\":1000,\"height\":667},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/researchers-jailbreak-llms-by-using-ascii-art-in-prompts\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dailyai.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"\u200b\u200bResearchers jailbreak LLMs by using ASCII art in prompts\"}]},{\"@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":"Des chercheurs cassent les LLM en utilisant l'art ASCII dans les messages-guides | 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\/03\/researchers-jailbreak-llms-by-using-ascii-art-in-prompts\/","og_locale":"fr_FR","og_type":"article","og_title":"\u200b\u200bResearchers jailbreak LLMs by using ASCII art in prompts | DailyAI","og_description":"Researchers developed a jailbreak attack called ArtPrompt, which uses ASCII art to bypass an LLM\u2019s guardrails. If you remember a time before computers could handle graphics, you\u2019re probably familiar with ASCII art. An ASCII character is basically a letter, number, symbol, or punctuation mark that a computer can understand. ASCII art is created by arranging these characters into different shapes. The University of Washington, Western Washington University, and Chicago University researchers published a paper showing how they used ASCII art to sneak normally taboo words into their prompts. If you ask an LLM to explain how to build a bomb,","og_url":"https:\/\/dailyai.com\/fr\/2024\/03\/researchers-jailbreak-llms-by-using-ascii-art-in-prompts\/","og_site_name":"DailyAI","article_published_time":"2024-03-08T13:34:19+00:00","og_image":[{"width":1000,"height":667,"url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/ASCII-art-error.jpg","type":"image\/jpeg"}],"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\/03\/researchers-jailbreak-llms-by-using-ascii-art-in-prompts\/#article","isPartOf":{"@id":"https:\/\/dailyai.com\/2024\/03\/researchers-jailbreak-llms-by-using-ascii-art-in-prompts\/"},"author":{"name":"Eugene van der Watt","@id":"https:\/\/dailyai.com\/#\/schema\/person\/7ce525c6d0c79838b7cc7cde96993cfa"},"headline":"\u200b\u200bResearchers jailbreak LLMs by using ASCII art in prompts","datePublished":"2024-03-08T13:34:19+00:00","mainEntityOfPage":{"@id":"https:\/\/dailyai.com\/2024\/03\/researchers-jailbreak-llms-by-using-ascii-art-in-prompts\/"},"wordCount":500,"publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"image":{"@id":"https:\/\/dailyai.com\/2024\/03\/researchers-jailbreak-llms-by-using-ascii-art-in-prompts\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/ASCII-art-error.jpg","keywords":["AI risks","LLMS"],"articleSection":["Industry"],"inLanguage":"fr-FR"},{"@type":"WebPage","@id":"https:\/\/dailyai.com\/2024\/03\/researchers-jailbreak-llms-by-using-ascii-art-in-prompts\/","url":"https:\/\/dailyai.com\/2024\/03\/researchers-jailbreak-llms-by-using-ascii-art-in-prompts\/","name":"Des chercheurs cassent les LLM en utilisant l'art ASCII dans les messages-guides | DailyAI","isPartOf":{"@id":"https:\/\/dailyai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dailyai.com\/2024\/03\/researchers-jailbreak-llms-by-using-ascii-art-in-prompts\/#primaryimage"},"image":{"@id":"https:\/\/dailyai.com\/2024\/03\/researchers-jailbreak-llms-by-using-ascii-art-in-prompts\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/ASCII-art-error.jpg","datePublished":"2024-03-08T13:34:19+00:00","breadcrumb":{"@id":"https:\/\/dailyai.com\/2024\/03\/researchers-jailbreak-llms-by-using-ascii-art-in-prompts\/#breadcrumb"},"inLanguage":"fr-FR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2024\/03\/researchers-jailbreak-llms-by-using-ascii-art-in-prompts\/"]}]},{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/dailyai.com\/2024\/03\/researchers-jailbreak-llms-by-using-ascii-art-in-prompts\/#primaryimage","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/ASCII-art-error.jpg","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/ASCII-art-error.jpg","width":1000,"height":667},{"@type":"BreadcrumbList","@id":"https:\/\/dailyai.com\/2024\/03\/researchers-jailbreak-llms-by-using-ascii-art-in-prompts\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dailyai.com\/"},{"@type":"ListItem","position":2,"name":"\u200b\u200bResearchers jailbreak LLMs by using ASCII art in prompts"}]},{"@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\/10589","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=10589"}],"version-history":[{"count":3,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/posts\/10589\/revisions"}],"predecessor-version":[{"id":10596,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/posts\/10589\/revisions\/10596"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/media\/10595"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/media?parent=10589"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/categories?post=10589"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/tags?post=10589"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}