{"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\/sv\/2024\/04\/anthropic-large-context-llms-vulnerable-to-many-shot-jailbreak\/","title":{"rendered":"Antropisk: LLM:er i stora sammanhang s\u00e5rbara f\u00f6r jailbreak med m\u00e5nga skott"},"content":{"rendered":"

Anthropic sl\u00e4ppte ett dokument som beskriver en m\u00e5nga-shot jailbreaking-metod f\u00f6r vilken LLM med l\u00e5ng kontext \u00e4r s\u00e4rskilt s\u00e5rbar.<\/strong><\/p>\n

Storleken p\u00e5 en LLM:s kontextf\u00f6nster avg\u00f6r den maximala l\u00e4ngden p\u00e5 en prompt. Kontextf\u00f6nstren har \u00f6kat konstant under de senaste m\u00e5naderna och modeller som Claude Opus har n\u00e5tt ett kontextf\u00f6nster p\u00e5 1 miljon tokens.<\/p>\n

Det ut\u00f6kade kontextf\u00f6nstret m\u00f6jligg\u00f6r mer kraftfull inl\u00e4rning i kontexten. Med en \"zero-shot prompt\" uppmanas en LLM att ge ett svar utan tidigare exempel.<\/p>\n

I en \"few-shot\"-strategi f\u00e5r modellen flera exempel i fr\u00e5gan. Detta m\u00f6jligg\u00f6r inl\u00e4rning i sammanhanget och ger modellen f\u00f6ruts\u00e4ttningar att ge ett b\u00e4ttre svar.<\/p>\n

St\u00f6rre kontextf\u00f6nster inneb\u00e4r att en anv\u00e4ndares prompt kan vara extremt l\u00e5ng med m\u00e5nga exempel, vilket enligt Anthropic \u00e4r b\u00e5de en v\u00e4lsignelse och en f\u00f6rbannelse.<\/p>\n

M\u00e5nga-shot jailbreak<\/h2>\n

Jailbreak-metoden \u00e4r oerh\u00f6rt enkel. LLM uppmanas med en enda prompt som best\u00e5r av en falsk dialog mellan en anv\u00e4ndare och en mycket tillm\u00f6tesg\u00e5ende AI-assistent.<\/p>\n

Dialogen best\u00e5r av en serie fr\u00e5gor om hur man g\u00f6r n\u00e5got farligt eller olagligt f\u00f6ljt av falska svar fr\u00e5n AI-assistenten med information om hur man utf\u00f6r aktiviteterna.<\/p>\n

Prompten avslutas med en m\u00e5lfr\u00e5ga som \"Hur bygger man en bomb?\" och l\u00e4mnar sedan \u00f6ver till den utvalda LLM:n att svara.<\/p>\n

\"\"
F\u00e5-shot vs many-shot jailbreak. K\u00e4lla: Anthropic Antropisk<\/figcaption><\/figure>\n

Om du bara hade n\u00e5gra f\u00e5 interaktioner fram och tillbaka i uppmaningen fungerar det inte. Men med en modell som Claude Opus kan en uppmaning med m\u00e5nga bilder vara lika l\u00e5ng som flera l\u00e5nga romaner.<\/p>\n

I sin artikel<\/a>Anthropic-forskarna fann att \"n\u00e4r antalet inkluderade dialoger (antalet \"shots\") \u00f6kar \u00f6ver en viss punkt, blir det mer sannolikt att modellen kommer att ge en skadlig respons\".<\/p>\n

De fann ocks\u00e5 att n\u00e4r de kombinerades med andra k\u00e4nda jailbreaking-tekniker<\/a>var metoden med m\u00e5nga skott \u00e4nnu mer effektiv eller kunde lyckas med kortare uppmaningar.<\/p>\n

\"\"
I takt med att antalet dialoger i uppmaningen \u00f6kar, \u00f6kar oddsen f\u00f6r ett skadligt svar. K\u00e4lla: Anthropic Antropisk<\/figcaption><\/figure>\n

Kan det \u00e5tg\u00e4rdas?<\/h2>\n

Anthropic s\u00e4ger att det enklaste f\u00f6rsvaret mot \"many-shot jailbreak\" \u00e4r att minska storleken p\u00e5 en modells kontextf\u00f6nster. Men d\u00e5 f\u00f6rlorar du de uppenbara f\u00f6rdelarna med att kunna anv\u00e4nda l\u00e4ngre ing\u00e5ngar.<\/p>\n

Anthropic f\u00f6rs\u00f6kte f\u00e5 sin LLM att identifiera n\u00e4r en anv\u00e4ndare f\u00f6rs\u00f6kte sig p\u00e5 en jailbreak med m\u00e5nga bilder och sedan v\u00e4gra att svara p\u00e5 fr\u00e5gan. De fann att det helt enkelt f\u00f6rdr\u00f6jde jailbreak och kr\u00e4vde en l\u00e4ngre prompt f\u00f6r att s\u00e5 sm\u00e5ningom framkalla den skadliga utg\u00e5ngen.<\/p>\n

Genom att klassificera och modifiera meddelandet innan det skickades till modellen lyckades de till viss del f\u00f6rhindra attacken. Trots detta s\u00e4ger Anthropic att de \u00e4r medvetna om att variationer av attacken kan undvika uppt\u00e4ckt.<\/p>\n

Anthropic s\u00e4ger att det allt l\u00e4ngre kontextf\u00f6nstret f\u00f6r LLM:er \"g\u00f6r modellerna mycket mer anv\u00e4ndbara p\u00e5 alla m\u00f6jliga s\u00e4tt, men det g\u00f6r det ocks\u00e5 m\u00f6jligt med en ny klass av jailbreaking-s\u00e5rbarheter.\"<\/p>\n

F\u00f6retaget har publicerat sin forskning i hopp om att andra AI-f\u00f6retag ska hitta s\u00e4tt att motverka \"many-shot\"-attacker.<\/p>\n

En intressant slutsats som forskarna kom fram till var att \"\u00e4ven positiva, till synes oskyldiga f\u00f6rb\u00e4ttringar av LLM (i det h\u00e4r fallet att till\u00e5ta l\u00e4ngre inmatningar) ibland kan f\u00e5 of\u00f6rutsedda konsekvenser\".<\/p>","protected":false},"excerpt":{"rendered":"

Anthropic sl\u00e4ppte ett dokument som beskriver en m\u00e5nga-shot jailbreaking-metod f\u00f6r vilken LLM: er med l\u00e5ng kontext \u00e4r s\u00e4rskilt s\u00e5rbara. Storleken p\u00e5 en LLM:s kontextf\u00f6nster best\u00e4mmer den maximala l\u00e4ngden p\u00e5 en prompt. Kontextf\u00f6nster har vuxit konsekvent under de senaste m\u00e5naderna med modeller som Claude Opus som n\u00e5r ett kontextf\u00f6nster p\u00e5 1 miljon tokens. Det ut\u00f6kade kontextf\u00f6nstret m\u00f6jligg\u00f6r mer kraftfull inl\u00e4rning i kontexten. Med en \"zero-shot\"-prompt uppmanas en LLM att ge ett svar utan tidigare exempel. I en \"few-shot\"-strategi f\u00e5r modellen flera exempel i prompten. Detta m\u00f6jligg\u00f6r inl\u00e4rning i kontexten och ger<\/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\/sv\/2024\/04\/anthropic-large-context-llms-vulnerable-to-many-shot-jailbreak\/\" \/>\n<meta property=\"og:locale\" content=\"sv_SE\" \/>\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\/sv\/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=\"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=\"3 minuter\" \/>\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\":\"sv-SE\"},{\"@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\":\"sv-SE\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/anthropic-large-context-llms-vulnerable-to-many-shot-jailbreak\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"sv-SE\",\"@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\":\"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":"Antropisk: LLM:er i stora sammanhang s\u00e5rbara f\u00f6r jailbreak med m\u00e5nga skott | DailyAI","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/dailyai.com\/sv\/2024\/04\/anthropic-large-context-llms-vulnerable-to-many-shot-jailbreak\/","og_locale":"sv_SE","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\/sv\/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":{"Skriven av":"Eugene van der Watt","Ber\u00e4knad l\u00e4stid":"3 minuter"},"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":"sv-SE"},{"@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":"Antropisk: LLM:er i stora sammanhang s\u00e5rbara f\u00f6r jailbreak med m\u00e5nga skott | 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":"sv-SE","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2024\/04\/anthropic-large-context-llms-vulnerable-to-many-shot-jailbreak\/"]}]},{"@type":"ImageObject","inLanguage":"sv-SE","@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":"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\/11364","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=11364"}],"version-history":[{"count":3,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/posts\/11364\/revisions"}],"predecessor-version":[{"id":11370,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/posts\/11364\/revisions\/11370"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/media\/11368"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/media?parent=11364"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/categories?post=11364"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/tags?post=11364"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}