{"id":10786,"date":"2024-03-18T09:35:31","date_gmt":"2024-03-18T09:35:31","guid":{"rendered":"https:\/\/dailyai.com\/?p=10786"},"modified":"2024-03-28T09:35:17","modified_gmt":"2024-03-28T09:35:17","slug":"apple-reveals-mm1-its-first-family-of-multimodal-llms","status":"publish","type":"post","link":"https:\/\/dailyai.com\/it\/2024\/03\/apple-reveals-mm1-its-first-family-of-multimodal-llms\/","title":{"rendered":"Apple rivela MM1, la sua prima famiglia di LLM multimodali"},"content":{"rendered":"

Apple non ha ancora rilasciato ufficialmente un modello di intelligenza artificiale, ma un nuovo documento di ricerca fornisce un'idea dei progressi dell'azienda nello sviluppo di modelli con capacit\u00e0 multimodali all'avanguardia.<\/strong><\/p>\n

La carta<\/a>intitolato \"MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training\", presenta la famiglia di MLLM di Apple chiamata MM1.<\/p>\n

MM1 mostra capacit\u00e0 impressionanti nella didascalia delle immagini, nella risposta alle domande visive (VQA) e nell'inferenza del linguaggio naturale. I ricercatori spiegano che la scelta accurata delle coppie immagine-didascalia ha permesso di ottenere risultati superiori, soprattutto in scenari di apprendimento con pochi scatti.<\/p>\n

Ci\u00f2 che distingue l'MM1 dagli altri MLLM \u00e8 la sua superiore capacit\u00e0 di seguire istruzioni su pi\u00f9 immagini e di ragionare sulle scene complesse che gli vengono presentate.<\/p>\n

I modelli MM1 contengono fino a 30B parametri, il triplo di quelli del GPT-4V, il componente che conferisce al GPT-4 di OpenAI le sue capacit\u00e0 di visione.<\/p>\n

Ecco alcuni esempi delle capacit\u00e0 VQA di MM1.<\/p>\n

\"\"
Verifica della capacit\u00e0 di MM1 di ragionare su immagini e testi. Fonte: arXiv<\/figcaption><\/figure>\n

MM1 \u00e8 stato sottoposto a un preaddestramento multimodale su larga scala su \"un dataset di 500 milioni di documenti interlacciati immagine-testo, contenenti 1B immagini e 500B token di testo\".<\/p>\n

L'ampiezza e la diversit\u00e0 del suo preallenamento consentono a MM1 di eseguire predizioni impressionanti nel contesto e di seguire la formattazione personalizzata con un numero ridotto di esempi di pochi scatti. Ecco alcuni esempi di come MM1 apprende l'output e il formato desiderato da soli 3 esempi.<\/p>\n

\"\"
MM1 \u00e8 in grado di contare gli oggetti, di eseguire l'OCR su aree specifiche di un'immagine, di applicare il ragionamento del buon senso agli oggetti e di eseguire funzioni matematiche di base. Fonte: arXiv<\/figcaption><\/figure>\n

Per creare modelli di intelligenza artificiale in grado di \"vedere\" e ragionare \u00e8 necessario un connettore visione-linguaggio che traduca le immagini e il linguaggio in una rappresentazione unificata che il modello possa utilizzare per ulteriori elaborazioni.<\/p>\n

I ricercatori hanno scoperto che il design del connettore visione-linguaggio \u00e8 stato meno determinante per le prestazioni di MM1. \u00c8 interessante notare che sono stati la risoluzione dell'immagine e il numero di token dell'immagine ad avere il maggiore impatto.<\/p>\n

\u00c8 interessante vedere quanto Apple sia stata aperta nel condividere la sua ricerca con la pi\u00f9 ampia comunit\u00e0 dell'intelligenza artificiale. I ricercatori affermano che \"in questo articolo documentiamo il processo di costruzione di MLLM e cerchiamo di formulare lezioni di progettazione che speriamo possano essere utili alla comunit\u00e0\".<\/p>\n

I risultati pubblicati probabilmente influenzeranno la direzione presa da altri sviluppatori di MMLM per quanto riguarda l'architettura e le scelte dei dati di pre-training.<\/p>\n

Resta da vedere come i modelli MM1 saranno implementati nei prodotti Apple. Gli esempi pubblicati delle capacit\u00e0 dell'MM1 lasciano intendere che Siri diventer\u00e0 molto pi\u00f9 intelligente quando imparer\u00e0 a vedere.<\/p>","protected":false},"excerpt":{"rendered":"

Apple non ha ancora rilasciato ufficialmente un modello di intelligenza artificiale, ma un nuovo documento di ricerca fornisce un'idea dei progressi dell'azienda nello sviluppo di modelli con capacit\u00e0 multimodali all'avanguardia. Il documento, intitolato \"MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training\", presenta la famiglia di MLLM di Apple chiamata MM1. MM1 mostra capacit\u00e0 impressionanti nella didascalia delle immagini, nella risposta a domande visive (VQA) e nell'inferenza del linguaggio naturale. I ricercatori spiegano che la scelta accurata delle coppie immagine-didascalia ha permesso di ottenere risultati superiori, soprattutto in scenari di apprendimento con pochi scatti. Ci\u00f2 che distingue MM1 da altri MLLM \u00e8 la sua superiore capacit\u00e0 di seguire le istruzioni su pi\u00f9 immagini e<\/p>","protected":false},"author":6,"featured_media":10790,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[84],"tags":[126,166],"class_list":["post-10786","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-industry","tag-apple","tag-computer-vision"],"yoast_head":"\nApple reveals MM1, its first family of multimodal LLMs | 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\/it\/2024\/03\/apple-reveals-mm1-its-first-family-of-multimodal-llms\/\" \/>\n<meta property=\"og:locale\" content=\"it_IT\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Apple reveals MM1, its first family of multimodal LLMs | DailyAI\" \/>\n<meta property=\"og:description\" content=\"Apple is yet to officially release an AI model, but a new research paper gives an insight into the company\u2019s progress in developing models with state-of-the-art multimodal capabilities. The paper, titled \u201cMM1: Methods, Analysis & Insights from Multimodal LLM Pre-training\u201d, introduces Apple\u2019s family of MLLMs called MM1. MM1 displays impressive abilities in image captioning, visual question answering (VQA), and natural language inference. The researchers explain that careful choices of image-caption pairs enabled them to achieve superior results, especially in few-shot learning scenarios. What sets MM1 apart from other MLLMs is its superior ability to follow instructions across multiple images and\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dailyai.com\/it\/2024\/03\/apple-reveals-mm1-its-first-family-of-multimodal-llms\/\" \/>\n<meta property=\"og:site_name\" content=\"DailyAI\" \/>\n<meta property=\"article:published_time\" content=\"2024-03-18T09:35:31+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-03-28T09:35:17+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/Apple-MM1.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=\"Scritto da\" \/>\n\t<meta name=\"twitter:data1\" content=\"Eugene van der Watt\" \/>\n\t<meta name=\"twitter:label2\" content=\"Tempo di lettura stimato\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 minuti\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/apple-reveals-mm1-its-first-family-of-multimodal-llms\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/apple-reveals-mm1-its-first-family-of-multimodal-llms\\\/\"},\"author\":{\"name\":\"Eugene van der Watt\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/7ce525c6d0c79838b7cc7cde96993cfa\"},\"headline\":\"Apple reveals MM1, its first family of multimodal LLMs\",\"datePublished\":\"2024-03-18T09:35:31+00:00\",\"dateModified\":\"2024-03-28T09:35:17+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/apple-reveals-mm1-its-first-family-of-multimodal-llms\\\/\"},\"wordCount\":432,\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/apple-reveals-mm1-its-first-family-of-multimodal-llms\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/03\\\/Apple-MM1.webp\",\"keywords\":[\"Apple\",\"Computer vision\"],\"articleSection\":[\"Industry\"],\"inLanguage\":\"it-IT\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/apple-reveals-mm1-its-first-family-of-multimodal-llms\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/apple-reveals-mm1-its-first-family-of-multimodal-llms\\\/\",\"name\":\"Apple reveals MM1, its first family of multimodal LLMs | DailyAI\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/apple-reveals-mm1-its-first-family-of-multimodal-llms\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/apple-reveals-mm1-its-first-family-of-multimodal-llms\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/03\\\/Apple-MM1.webp\",\"datePublished\":\"2024-03-18T09:35:31+00:00\",\"dateModified\":\"2024-03-28T09:35:17+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/apple-reveals-mm1-its-first-family-of-multimodal-llms\\\/#breadcrumb\"},\"inLanguage\":\"it-IT\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/apple-reveals-mm1-its-first-family-of-multimodal-llms\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"it-IT\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/apple-reveals-mm1-its-first-family-of-multimodal-llms\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/03\\\/Apple-MM1.webp\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/03\\\/Apple-MM1.webp\",\"width\":1792,\"height\":1024},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/apple-reveals-mm1-its-first-family-of-multimodal-llms\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dailyai.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Apple reveals MM1, its first family of multimodal LLMs\"}]},{\"@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\":\"it-IT\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\",\"name\":\"DailyAI\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"it-IT\",\"@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\":\"it-IT\",\"@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\\\/it\\\/author\\\/eugene\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Apple rivela MM1, la sua prima famiglia di LLM multimodali | 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\/it\/2024\/03\/apple-reveals-mm1-its-first-family-of-multimodal-llms\/","og_locale":"it_IT","og_type":"article","og_title":"Apple reveals MM1, its first family of multimodal LLMs | DailyAI","og_description":"Apple is yet to officially release an AI model, but a new research paper gives an insight into the company\u2019s progress in developing models with state-of-the-art multimodal capabilities. The paper, titled \u201cMM1: Methods, Analysis & Insights from Multimodal LLM Pre-training\u201d, introduces Apple\u2019s family of MLLMs called MM1. MM1 displays impressive abilities in image captioning, visual question answering (VQA), and natural language inference. The researchers explain that careful choices of image-caption pairs enabled them to achieve superior results, especially in few-shot learning scenarios. What sets MM1 apart from other MLLMs is its superior ability to follow instructions across multiple images and","og_url":"https:\/\/dailyai.com\/it\/2024\/03\/apple-reveals-mm1-its-first-family-of-multimodal-llms\/","og_site_name":"DailyAI","article_published_time":"2024-03-18T09:35:31+00:00","article_modified_time":"2024-03-28T09:35:17+00:00","og_image":[{"width":1792,"height":1024,"url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/Apple-MM1.webp","type":"image\/webp"}],"author":"Eugene van der Watt","twitter_card":"summary_large_image","twitter_creator":"@DailyAIOfficial","twitter_site":"@DailyAIOfficial","twitter_misc":{"Scritto da":"Eugene van der Watt","Tempo di lettura stimato":"3 minuti"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/dailyai.com\/2024\/03\/apple-reveals-mm1-its-first-family-of-multimodal-llms\/#article","isPartOf":{"@id":"https:\/\/dailyai.com\/2024\/03\/apple-reveals-mm1-its-first-family-of-multimodal-llms\/"},"author":{"name":"Eugene van der Watt","@id":"https:\/\/dailyai.com\/#\/schema\/person\/7ce525c6d0c79838b7cc7cde96993cfa"},"headline":"Apple reveals MM1, its first family of multimodal LLMs","datePublished":"2024-03-18T09:35:31+00:00","dateModified":"2024-03-28T09:35:17+00:00","mainEntityOfPage":{"@id":"https:\/\/dailyai.com\/2024\/03\/apple-reveals-mm1-its-first-family-of-multimodal-llms\/"},"wordCount":432,"publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"image":{"@id":"https:\/\/dailyai.com\/2024\/03\/apple-reveals-mm1-its-first-family-of-multimodal-llms\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/Apple-MM1.webp","keywords":["Apple","Computer vision"],"articleSection":["Industry"],"inLanguage":"it-IT"},{"@type":"WebPage","@id":"https:\/\/dailyai.com\/2024\/03\/apple-reveals-mm1-its-first-family-of-multimodal-llms\/","url":"https:\/\/dailyai.com\/2024\/03\/apple-reveals-mm1-its-first-family-of-multimodal-llms\/","name":"Apple rivela MM1, la sua prima famiglia di LLM multimodali | DailyAI","isPartOf":{"@id":"https:\/\/dailyai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dailyai.com\/2024\/03\/apple-reveals-mm1-its-first-family-of-multimodal-llms\/#primaryimage"},"image":{"@id":"https:\/\/dailyai.com\/2024\/03\/apple-reveals-mm1-its-first-family-of-multimodal-llms\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/Apple-MM1.webp","datePublished":"2024-03-18T09:35:31+00:00","dateModified":"2024-03-28T09:35:17+00:00","breadcrumb":{"@id":"https:\/\/dailyai.com\/2024\/03\/apple-reveals-mm1-its-first-family-of-multimodal-llms\/#breadcrumb"},"inLanguage":"it-IT","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2024\/03\/apple-reveals-mm1-its-first-family-of-multimodal-llms\/"]}]},{"@type":"ImageObject","inLanguage":"it-IT","@id":"https:\/\/dailyai.com\/2024\/03\/apple-reveals-mm1-its-first-family-of-multimodal-llms\/#primaryimage","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/Apple-MM1.webp","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/Apple-MM1.webp","width":1792,"height":1024},{"@type":"BreadcrumbList","@id":"https:\/\/dailyai.com\/2024\/03\/apple-reveals-mm1-its-first-family-of-multimodal-llms\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dailyai.com\/"},{"@type":"ListItem","position":2,"name":"Apple reveals MM1, its first family of multimodal LLMs"}]},{"@type":"WebSite","@id":"https:\/\/dailyai.com\/#website","url":"https:\/\/dailyai.com\/","name":"DailyAI","description":"La vostra dose quotidiana di notizie sull'intelligenza artificiale","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":"it-IT"},{"@type":"Organization","@id":"https:\/\/dailyai.com\/#organization","name":"DailyAI","url":"https:\/\/dailyai.com\/","logo":{"@type":"ImageObject","inLanguage":"it-IT","@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":"it-IT","@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 proviene da un background di ingegneria elettronica e ama tutto ci\u00f2 che \u00e8 tecnologico. Quando si prende una pausa dal consumo di notizie sull'intelligenza artificiale, lo si pu\u00f2 trovare al tavolo da biliardo.","sameAs":["www.linkedin.com\/in\/eugene-van-der-watt-16828119"],"url":"https:\/\/dailyai.com\/it\/author\/eugene\/"}]}},"_links":{"self":[{"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/posts\/10786","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/users\/6"}],"replies":[{"embeddable":true,"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/comments?post=10786"}],"version-history":[{"count":3,"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/posts\/10786\/revisions"}],"predecessor-version":[{"id":10792,"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/posts\/10786\/revisions\/10792"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/media\/10790"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/media?parent=10786"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/categories?post=10786"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/tags?post=10786"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}