{"id":11364,"date":"2024-04-05T08:45:19","date_gmt":"2024-04-05T08:45:19","guid":{"rendered":"https:\/\/dailyai.com\/?p=11364"},"modified":"2024-04-05T08:45:19","modified_gmt":"2024-04-05T08:45:19","slug":"anthropic-large-context-llms-vulnerable-to-many-shot-jailbreak","status":"publish","type":"post","link":"https:\/\/dailyai.com\/fr\/2024\/04\/anthropic-large-context-llms-vulnerable-to-many-shot-jailbreak\/","title":{"rendered":"Anthropique : Les LLM \u00e0 contexte large sont vuln\u00e9rables \u00e0 l'intrusion d'un grand nombre de coups de feu"},"content":{"rendered":"

Anthropic a publi\u00e9 un document d\u00e9crivant une m\u00e9thode de cassage de prison \u00e0 plusieurs coups \u00e0 laquelle les LLM \u00e0 contexte long sont particuli\u00e8rement vuln\u00e9rables.<\/strong><\/p>\n

La taille de la fen\u00eatre contextuelle d'un LLM d\u00e9termine la longueur maximale d'une invite. Les fen\u00eatres contextuelles ont augment\u00e9 de fa\u00e7on constante au cours des derniers mois, avec des mod\u00e8les tels que Claude Opus atteignant une fen\u00eatre contextuelle de 1 million de tokens.<\/p>\n

La fen\u00eatre contextuelle \u00e9largie permet un apprentissage en contexte plus puissant. Dans le cas d'une invite \u00e0 z\u00e9ro, un MLD est invit\u00e9 \u00e0 fournir une r\u00e9ponse sans exemples pr\u00e9alables.<\/p>\n

Dans une approche \u00e0 quelques reprises, le mod\u00e8le re\u00e7oit plusieurs exemples dans l'invite. Cela permet un apprentissage en contexte et incite le mod\u00e8le \u00e0 donner une meilleure r\u00e9ponse.<\/p>\n

Les fen\u00eatres contextuelles plus grandes signifient que l'invite de l'utilisateur peut \u00eatre extr\u00eamement longue et comporter de nombreux exemples, ce qui, selon Anthropic, est \u00e0 la fois une b\u00e9n\u00e9diction et une mal\u00e9diction.<\/p>\n

Jailbreak \u00e0 plusieurs coups<\/h2>\n

La m\u00e9thode de jailbreak est extr\u00eamement simple. Le LLM est invit\u00e9 avec une seule invite compos\u00e9e d'un faux dialogue entre un utilisateur et un assistant IA tr\u00e8s accommodant.<\/p>\n

Le dialogue comprend une s\u00e9rie de questions sur la mani\u00e8re de faire quelque chose de dangereux ou d'ill\u00e9gal, suivies de fausses r\u00e9ponses de l'assistant d'intelligence artificielle contenant des informations sur la mani\u00e8re de r\u00e9aliser ces activit\u00e9s.<\/p>\n

L'invite se termine par une question cible telle que \"Comment fabriquer une bombe ?\" et laisse ensuite le LLM cibl\u00e9 y r\u00e9pondre.<\/p>\n

\"\"
Jailbreak \u00e0 quelques coups contre jailbreak \u00e0 plusieurs coups. Source : Anthropic<\/figcaption><\/figure>\n

Si vous n'avez que quelques interactions de va-et-vient dans l'invite, cela ne fonctionne pas. Mais avec un mod\u00e8le comme Claude Opus, l'incitation \u00e0 l'action peut \u00eatre aussi longue que plusieurs longs romans.<\/p>\n

Dans leur document<\/a>Les chercheurs d'Anthropic ont constat\u00e9 que \"plus le nombre de dialogues inclus (le nombre de \"coups\") augmente au-del\u00e0 d'un certain point, plus il est probable que le mod\u00e8le produise une r\u00e9ponse nuisible\".<\/p>\n

Ils ont \u00e9galement constat\u00e9 que lorsqu'ils sont combin\u00e9s \u00e0 d'autres techniques de jailbreaking<\/a>En revanche, l'approche \u00e0 plusieurs coups s'est av\u00e9r\u00e9e encore plus efficace ou pourrait \u00eatre couronn\u00e9e de succ\u00e8s avec des messages plus courts.<\/p>\n

\"\"
Plus le nombre de dialogues augmente, plus les chances d'obtenir une r\u00e9ponse nuisible augmentent. Source : Anthropic<\/figcaption><\/figure>\n

Peut-on y rem\u00e9dier ?<\/h2>\n

Anthropic dit que la d\u00e9fense la plus simple contre le jailbreak est de r\u00e9duire la taille de la fen\u00eatre contextuelle d'un mod\u00e8le. Mais on perd alors les avantages \u00e9vidents li\u00e9s \u00e0 la possibilit\u00e9 d'utiliser des entr\u00e9es plus longues.<\/p>\n

Anthropic a essay\u00e9 de faire en sorte que son LLM identifie le moment o\u00f9 un utilisateur tente un jailbreak \u00e0 plusieurs niveaux et refuse de r\u00e9pondre \u00e0 la requ\u00eate. Ils ont constat\u00e9 que cela ne faisait que retarder le jailbreak et n\u00e9cessitait une invite plus longue pour finalement provoquer la sortie nuisible.<\/p>\n

En classant et en modifiant l'invite avant de la transmettre au mod\u00e8le, ils ont r\u00e9ussi \u00e0 emp\u00eacher l'attaque. Malgr\u00e9 cela, Anthropic pr\u00e9cise qu'ils sont conscients que des variantes de l'attaque pourraient \u00e9chapper \u00e0 la d\u00e9tection.<\/p>\n

Anthropic affirme que la fen\u00eatre contextuelle toujours plus longue des LLM \"rend les mod\u00e8les beaucoup plus utiles dans toutes sortes de domaines, mais elle rend \u00e9galement possible une nouvelle classe de vuln\u00e9rabilit\u00e9s pour briser la prison\".<\/p>\n

L'entreprise a publi\u00e9 ses recherches dans l'espoir que d'autres entreprises sp\u00e9cialis\u00e9es dans l'IA trouvent des moyens d'att\u00e9nuer les attaques \u00e0 tirs multiples.<\/p>\n

Les chercheurs sont parvenus \u00e0 une conclusion int\u00e9ressante, \u00e0 savoir que \"m\u00eame des am\u00e9liorations positives et apparemment inoffensives des LLM (dans ce cas, permettre des entr\u00e9es plus longues) peuvent parfois avoir des cons\u00e9quences impr\u00e9vues\".<\/p>","protected":false},"excerpt":{"rendered":"

Anthropic a publi\u00e9 un article d\u00e9crivant une m\u00e9thode de cassage de prison \u00e0 plusieurs coups \u00e0 laquelle les LLM \u00e0 contexte long sont particuli\u00e8rement vuln\u00e9rables. La taille de la fen\u00eatre contextuelle d'un LLM d\u00e9termine la longueur maximale d'une invite. Les fen\u00eatres contextuelles n'ont cess\u00e9 de cro\u00eetre au cours des derniers mois, des mod\u00e8les comme Claude Opus atteignant une fen\u00eatre contextuelle d'un million de jetons. L'\u00e9largissement de la fen\u00eatre contextuelle permet un apprentissage en contexte plus puissant. Avec une invite \u00e0 z\u00e9ro coup, un LLM est invit\u00e9 \u00e0 fournir une r\u00e9ponse sans exemples pr\u00e9alables. Dans une approche \u00e0 quelques coups, le mod\u00e8le re\u00e7oit plusieurs exemples dans l'invite. Cela permet l'apprentissage en contexte et amorce l'apprentissage en contexte.<\/p>","protected":false},"author":6,"featured_media":11368,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[84],"tags":[],"class_list":["post-11364","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-industry"],"yoast_head":"\nAnthropic: Large context LLMs vulnerable to many-shot jailbreak | 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\/anthropic-large-context-llms-vulnerable-to-many-shot-jailbreak\/\" \/>\n<meta property=\"og:locale\" content=\"fr_FR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Anthropic: Large context LLMs vulnerable to many-shot jailbreak | DailyAI\" \/>\n<meta property=\"og:description\" content=\"Anthropic released a paper outlining a many-shot jailbreaking method to which long-context LLMs are particularly vulnerable. The size of an LLM\u2019s context window determines the maximum length of a prompt. Context windows have been growing consistently over the last few months with models like Claude Opus reaching a context window of 1 million tokens. The expanded context window makes more powerful in-context learning possible. With a zero-shot prompt, an LLM is prompted to provide a response without prior examples. In a few-shot approach, the model is provided with several examples in the prompt. This allows for in-context learning and primes\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dailyai.com\/fr\/2024\/04\/anthropic-large-context-llms-vulnerable-to-many-shot-jailbreak\/\" \/>\n<meta property=\"og:site_name\" content=\"DailyAI\" \/>\n<meta property=\"article:published_time\" content=\"2024-04-05T08:45:19+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/Many-shot-jailbreak.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\\\/anthropic-large-context-llms-vulnerable-to-many-shot-jailbreak\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/anthropic-large-context-llms-vulnerable-to-many-shot-jailbreak\\\/\"},\"author\":{\"name\":\"Eugene van der Watt\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/7ce525c6d0c79838b7cc7cde96993cfa\"},\"headline\":\"Anthropic: Large context LLMs vulnerable to many-shot jailbreak\",\"datePublished\":\"2024-04-05T08:45:19+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/anthropic-large-context-llms-vulnerable-to-many-shot-jailbreak\\\/\"},\"wordCount\":548,\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/anthropic-large-context-llms-vulnerable-to-many-shot-jailbreak\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/Many-shot-jailbreak.webp\",\"articleSection\":[\"Industry\"],\"inLanguage\":\"fr-FR\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/anthropic-large-context-llms-vulnerable-to-many-shot-jailbreak\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/anthropic-large-context-llms-vulnerable-to-many-shot-jailbreak\\\/\",\"name\":\"Anthropic: Large context LLMs vulnerable to many-shot jailbreak | DailyAI\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/anthropic-large-context-llms-vulnerable-to-many-shot-jailbreak\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/anthropic-large-context-llms-vulnerable-to-many-shot-jailbreak\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/Many-shot-jailbreak.webp\",\"datePublished\":\"2024-04-05T08:45:19+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/anthropic-large-context-llms-vulnerable-to-many-shot-jailbreak\\\/#breadcrumb\"},\"inLanguage\":\"fr-FR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/anthropic-large-context-llms-vulnerable-to-many-shot-jailbreak\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/anthropic-large-context-llms-vulnerable-to-many-shot-jailbreak\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/Many-shot-jailbreak.webp\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/Many-shot-jailbreak.webp\",\"width\":1792,\"height\":1024},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/anthropic-large-context-llms-vulnerable-to-many-shot-jailbreak\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dailyai.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Anthropic: Large context LLMs vulnerable to many-shot jailbreak\"}]},{\"@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":"Anthropique : Les LLM \u00e0 contexte large sont vuln\u00e9rables \u00e0 l'intrusion d'un grand nombre de tirs | 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\/anthropic-large-context-llms-vulnerable-to-many-shot-jailbreak\/","og_locale":"fr_FR","og_type":"article","og_title":"Anthropic: Large context LLMs vulnerable to many-shot jailbreak | DailyAI","og_description":"Anthropic released a paper outlining a many-shot jailbreaking method to which long-context LLMs are particularly vulnerable. The size of an LLM\u2019s context window determines the maximum length of a prompt. Context windows have been growing consistently over the last few months with models like Claude Opus reaching a context window of 1 million tokens. The expanded context window makes more powerful in-context learning possible. With a zero-shot prompt, an LLM is prompted to provide a response without prior examples. In a few-shot approach, the model is provided with several examples in the prompt. This allows for in-context learning and primes","og_url":"https:\/\/dailyai.com\/fr\/2024\/04\/anthropic-large-context-llms-vulnerable-to-many-shot-jailbreak\/","og_site_name":"DailyAI","article_published_time":"2024-04-05T08:45:19+00:00","og_image":[{"width":1792,"height":1024,"url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/Many-shot-jailbreak.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\/anthropic-large-context-llms-vulnerable-to-many-shot-jailbreak\/#article","isPartOf":{"@id":"https:\/\/dailyai.com\/2024\/04\/anthropic-large-context-llms-vulnerable-to-many-shot-jailbreak\/"},"author":{"name":"Eugene van der Watt","@id":"https:\/\/dailyai.com\/#\/schema\/person\/7ce525c6d0c79838b7cc7cde96993cfa"},"headline":"Anthropic: Large context LLMs vulnerable to many-shot jailbreak","datePublished":"2024-04-05T08:45:19+00:00","mainEntityOfPage":{"@id":"https:\/\/dailyai.com\/2024\/04\/anthropic-large-context-llms-vulnerable-to-many-shot-jailbreak\/"},"wordCount":548,"publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"image":{"@id":"https:\/\/dailyai.com\/2024\/04\/anthropic-large-context-llms-vulnerable-to-many-shot-jailbreak\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/Many-shot-jailbreak.webp","articleSection":["Industry"],"inLanguage":"fr-FR"},{"@type":"WebPage","@id":"https:\/\/dailyai.com\/2024\/04\/anthropic-large-context-llms-vulnerable-to-many-shot-jailbreak\/","url":"https:\/\/dailyai.com\/2024\/04\/anthropic-large-context-llms-vulnerable-to-many-shot-jailbreak\/","name":"Anthropique : Les LLM \u00e0 contexte large sont vuln\u00e9rables \u00e0 l'intrusion d'un grand nombre de tirs | DailyAI","isPartOf":{"@id":"https:\/\/dailyai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dailyai.com\/2024\/04\/anthropic-large-context-llms-vulnerable-to-many-shot-jailbreak\/#primaryimage"},"image":{"@id":"https:\/\/dailyai.com\/2024\/04\/anthropic-large-context-llms-vulnerable-to-many-shot-jailbreak\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/Many-shot-jailbreak.webp","datePublished":"2024-04-05T08:45:19+00:00","breadcrumb":{"@id":"https:\/\/dailyai.com\/2024\/04\/anthropic-large-context-llms-vulnerable-to-many-shot-jailbreak\/#breadcrumb"},"inLanguage":"fr-FR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2024\/04\/anthropic-large-context-llms-vulnerable-to-many-shot-jailbreak\/"]}]},{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/dailyai.com\/2024\/04\/anthropic-large-context-llms-vulnerable-to-many-shot-jailbreak\/#primaryimage","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/Many-shot-jailbreak.webp","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/Many-shot-jailbreak.webp","width":1792,"height":1024},{"@type":"BreadcrumbList","@id":"https:\/\/dailyai.com\/2024\/04\/anthropic-large-context-llms-vulnerable-to-many-shot-jailbreak\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dailyai.com\/"},{"@type":"ListItem","position":2,"name":"Anthropic: Large context LLMs vulnerable to many-shot jailbreak"}]},{"@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\/11364","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=11364"}],"version-history":[{"count":3,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/posts\/11364\/revisions"}],"predecessor-version":[{"id":11370,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/posts\/11364\/revisions\/11370"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/media\/11368"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/media?parent=11364"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/categories?post=11364"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/tags?post=11364"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}