{"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\/de\/2024\/04\/anthropic-large-context-llms-vulnerable-to-many-shot-jailbreak\/","title":{"rendered":"Anthropisch: LLMs mit gro\u00dfem Kontext anf\u00e4llig f\u00fcr \"Many-Shot Jailbreak"},"content":{"rendered":"

Anthropic hat ein Papier ver\u00f6ffentlicht, in dem eine Methode zum Aufbrechen von Gef\u00e4ngnissen beschrieben wird, f\u00fcr die LLMs mit langem Kontext besonders anf\u00e4llig sind.<\/strong><\/p>\n

Die Gr\u00f6\u00dfe des Kontextfensters eines LLMs bestimmt die maximale L\u00e4nge eines Prompts. Die Kontextfenster sind in den letzten Monaten stetig gewachsen, wobei Modelle wie Claude Opus ein Kontextfenster von 1 Million Token erreicht haben.<\/p>\n

Das erweiterte Kontextfenster erm\u00f6glicht ein leistungsf\u00e4higeres kontextbezogenes Lernen. Bei einem Zero-Shot Prompt wird ein LLM aufgefordert, eine Antwort ohne vorherige Beispiele zu geben.<\/p>\n

Bei einem \"few-shot\"-Ansatz werden dem Modell mehrere Beispiele in der Aufforderung vorgelegt. Dies erm\u00f6glicht kontextbezogenes Lernen und regt das Modell dazu an, eine bessere Antwort zu geben.<\/p>\n

Gr\u00f6\u00dfere Kontextfenster bedeuten, dass die Eingabeaufforderung f\u00fcr den Benutzer mit vielen Beispielen extrem lang sein kann, was laut Anthropic sowohl ein Segen als auch ein Fluch ist.<\/p>\n

Gef\u00e4ngnisausbruch mit vielen Sch\u00fcssen<\/h2>\n

Die Jailbreak-Methode ist denkbar einfach. Der LLM wird mit einer einzigen Eingabeaufforderung aufgefordert, die aus einem gef\u00e4lschten Dialog zwischen einem Benutzer und einem sehr entgegenkommenden KI-Assistenten besteht.<\/p>\n

Der Dialog besteht aus einer Reihe von Fragen, wie man etwas Gef\u00e4hrliches oder Illegales tun kann, gefolgt von gef\u00e4lschten Antworten des KI-Assistenten mit Informationen zur Durchf\u00fchrung der Aktivit\u00e4ten.<\/p>\n

Die Eingabeaufforderung endet mit einer Zielfrage wie \"Wie baut man eine Bombe?\" und \u00fcberl\u00e4sst es dann dem LLM, sie zu beantworten.<\/p>\n

\"\"
Jailbreak mit wenigen Sch\u00fcssen vs. vielen Sch\u00fcssen. Quelle: Anthropic<\/figcaption><\/figure>\n

Wenn Sie nur ein paar Hin- und Her-Interaktionen in der Eingabeaufforderung haben, funktioniert das nicht. Aber bei einem Modell wie Claude Opus kann die Souffleuse so lang sein wie mehrere lange Romane.<\/p>\n

In ihrem Papier<\/a>Die Anthropic-Forscher stellten fest, dass \"die Wahrscheinlichkeit, dass das Modell eine sch\u00e4dliche Reaktion hervorruft, mit der Anzahl der einbezogenen Dialoge (der Anzahl der \"Sch\u00fcsse\") \u00fcber einen bestimmten Punkt hinaus zunimmt\".<\/p>\n

Sie fanden auch heraus, dass in Kombination mit anderen bekannten Jailbreaking-Techniken<\/a>Der \"Many-Shot\"-Ansatz war sogar noch effektiver oder konnte mit k\u00fcrzeren Aufforderungen erfolgreich sein.<\/p>\n

\"\"
Je mehr Dialoge in der Aufforderung enthalten sind, desto gr\u00f6\u00dfer ist die Wahrscheinlichkeit, dass eine sch\u00e4dliche Antwort gegeben wird. Quelle: Anthropic<\/figcaption><\/figure>\n

Kann es behoben werden?<\/h2>\n

Anthropic sagt, dass die einfachste Verteidigung gegen den \"many-shot jailbreak\" darin besteht, die Gr\u00f6\u00dfe des Kontextfensters eines Modells zu reduzieren. Aber dann verliert man die offensichtlichen Vorteile der M\u00f6glichkeit, l\u00e4ngere Eingaben zu verwenden.<\/p>\n

Anthropic hat versucht, mit seinem LLM zu erkennen, wann ein Benutzer einen Jailbreak mit vielen Sch\u00fcssen versucht, und sich dann geweigert, die Anfrage zu beantworten. Sie fanden heraus, dass dies den Jailbreak lediglich verz\u00f6gerte und eine l\u00e4ngere Eingabeaufforderung erforderte, um schlie\u00dflich die sch\u00e4dliche Ausgabe zu erhalten.<\/p>\n

Durch die Klassifizierung und \u00c4nderung der Eingabeaufforderung, bevor sie an das Modell weitergeleitet wird, konnte der Angriff teilweise verhindert werden. Dennoch gibt Anthropic zu bedenken, dass Variationen des Angriffs der Erkennung entgehen k\u00f6nnten.<\/p>\n

Anthropic sagt, dass das immer gr\u00f6\u00dfer werdende Kontextfenster von LLMs \"die Modelle in vielerlei Hinsicht n\u00fctzlicher macht, aber auch eine neue Klasse von Schwachstellen f\u00fcr Jailbreaks erm\u00f6glicht\".<\/p>\n

Das Unternehmen hat seine Forschungsergebnisse in der Hoffnung ver\u00f6ffentlicht, dass andere KI-Unternehmen Wege finden, um Angriffe mit vielen Sch\u00fcssen zu entsch\u00e4rfen.<\/p>\n

Eine interessante Schlussfolgerung, zu der die Forscher kamen, war, dass \"selbst positive, harmlos erscheinende Verbesserungen der LLMs (in diesem Fall die Zulassung l\u00e4ngerer Eingaben) manchmal unvorhergesehene Folgen haben k\u00f6nnen\".<\/p>","protected":false},"excerpt":{"rendered":"

Anthropic hat ein Papier ver\u00f6ffentlicht, in dem eine \"Many-Shot\"-Jailbreaking-Methode beschrieben wird, f\u00fcr die LLMs mit langem Kontextfenster besonders anf\u00e4llig sind. Die Gr\u00f6\u00dfe des Kontextfensters eines LLMs bestimmt die maximale L\u00e4nge einer Eingabeaufforderung. Die Kontextfenster sind in den letzten Monaten stetig gewachsen, wobei Modelle wie Claude Opus ein Kontextfenster von 1 Million Token erreicht haben. Das erweiterte Kontextfenster erm\u00f6glicht ein leistungsf\u00e4higeres kontextbezogenes Lernen. Bei einem Zero-Shot Prompt wird ein LLM aufgefordert, eine Antwort ohne vorherige Beispiele zu geben. Bei einem \"few-shot\"-Ansatz werden dem Modell in der Aufforderung mehrere Beispiele gegeben. Dies erm\u00f6glicht ein kontextbezogenes Lernen und setzt<\/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\/de\/2024\/04\/anthropic-large-context-llms-vulnerable-to-many-shot-jailbreak\/\" \/>\n<meta property=\"og:locale\" content=\"de_DE\" \/>\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\/de\/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=\"Verfasst von\" \/>\n\t<meta name=\"twitter:data1\" content=\"Eugene van der Watt\" \/>\n\t<meta name=\"twitter:label2\" content=\"Gesch\u00e4tzte Lesezeit\" \/>\n\t<meta name=\"twitter:data2\" content=\"3\u00a0Minuten\" \/>\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\":\"de\"},{\"@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\":\"de\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/anthropic-large-context-llms-vulnerable-to-many-shot-jailbreak\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"de\",\"@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\":\"de\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\",\"name\":\"DailyAI\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"de\",\"@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\":\"de\",\"@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\\\/de\\\/author\\\/eugene\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Anthropisch: Gro\u00dfer Kontext LLMs anf\u00e4llig f\u00fcr viele Schuss jailbreak | 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\/de\/2024\/04\/anthropic-large-context-llms-vulnerable-to-many-shot-jailbreak\/","og_locale":"de_DE","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\/de\/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":{"Verfasst von":"Eugene van der Watt","Gesch\u00e4tzte Lesezeit":"3\u00a0Minuten"},"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":"de"},{"@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":"Anthropisch: Gro\u00dfer Kontext LLMs anf\u00e4llig f\u00fcr viele Schuss 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":"de","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2024\/04\/anthropic-large-context-llms-vulnerable-to-many-shot-jailbreak\/"]}]},{"@type":"ImageObject","inLanguage":"de","@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":"Ihre t\u00e4gliche Dosis an AI-Nachrichten","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":"de"},{"@type":"Organization","@id":"https:\/\/dailyai.com\/#organization","name":"DailyAI","url":"https:\/\/dailyai.com\/","logo":{"@type":"ImageObject","inLanguage":"de","@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":"de","@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 kommt aus der Elektronikbranche und liebt alles, was mit Technik zu tun hat. Wenn er eine Pause vom Konsum von KI-Nachrichten einlegt, findet man ihn am Snookertisch.","sameAs":["www.linkedin.com\/in\/eugene-van-der-watt-16828119"],"url":"https:\/\/dailyai.com\/de\/author\/eugene\/"}]}},"_links":{"self":[{"href":"https:\/\/dailyai.com\/de\/wp-json\/wp\/v2\/posts\/11364","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dailyai.com\/de\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dailyai.com\/de\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dailyai.com\/de\/wp-json\/wp\/v2\/users\/6"}],"replies":[{"embeddable":true,"href":"https:\/\/dailyai.com\/de\/wp-json\/wp\/v2\/comments?post=11364"}],"version-history":[{"count":3,"href":"https:\/\/dailyai.com\/de\/wp-json\/wp\/v2\/posts\/11364\/revisions"}],"predecessor-version":[{"id":11370,"href":"https:\/\/dailyai.com\/de\/wp-json\/wp\/v2\/posts\/11364\/revisions\/11370"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/de\/wp-json\/wp\/v2\/media\/11368"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/de\/wp-json\/wp\/v2\/media?parent=11364"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/de\/wp-json\/wp\/v2\/categories?post=11364"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/de\/wp-json\/wp\/v2\/tags?post=11364"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}