{"id":6777,"date":"2023-10-26T09:17:15","date_gmt":"2023-10-26T09:17:15","guid":{"rendered":"https:\/\/dailyai.com\/?p=6777"},"modified":"2023-10-26T09:22:02","modified_gmt":"2023-10-26T09:22:02","slug":"woodpecker-could-solve-multimodal-llm-hallucinations","status":"publish","type":"post","link":"https:\/\/dailyai.com\/it\/2023\/10\/woodpecker-could-solve-multimodal-llm-hallucinations\/","title":{"rendered":"Woodpecker potrebbe risolvere le allucinazioni multimodali LLM"},"content":{"rendered":"

I modelli linguistici multimodali di grandi dimensioni (MLLM) come il GPT-4V sono molto bravi ad analizzare e descrivere le immagini, ma a volte hanno delle allucinazioni e sbagliano. Un nuovo approccio chiamato Woodpecker potrebbe risolvere il problema.<\/strong><\/p>\n

Se si chiede a un MLLM di descrivere una foto, di solito \u00e8 in grado di individuare gli oggetti e di descrivere accuratamente la scena. Tuttavia, come nel caso delle risposte alle richieste di testo, il modello a volte fa delle ipotesi basate su elementi o concetti che compaiono spesso insieme.<\/p>\n

Di conseguenza, un MLLM potrebbe descrivere una foto di una vetrina e dire che ci sono persone nella scena, quando in realt\u00e0 non ce ne sono.<\/p>\n

La correzione delle allucinazioni nei LLM basati sul testo \u00e8 in corso, ma diventa molto pi\u00f9 semplice quando il modello \u00e8 collegato a Internet. Il LLM \u00e8 in grado di generare una risposta testuale a una richiesta, di verificarne la veridicit\u00e0 sulla base di dati Internet pertinenti e di autocorreggersi, se necessario.<\/p>\n

Gli scienziati dello YouTu Lab di Tencent e dell'Universit\u00e0 di Scienza e Tecnologia della Cina hanno adottato questo approccio e lo hanno tradotto in una soluzione visiva chiamata Woodpecker.<\/p>\n

In parole povere, Woodpecker costruisce un corpo di conoscenze a partire dall'immagine e poi un LLM pu\u00f2 usarlo come riferimento per correggere la descrizione iniziale generata dal MLLM.<\/p>\n

Ecco una breve descrizione del funzionamento:<\/p>\n

    \n
  1. Un LLM come GPT-3.5 Turbo analizza la descrizione generata dal MLLM ed estrae concetti chiave come oggetti, quantit\u00e0 e attributi. Ad esempio, nella frase \"L'uomo indossa un cappello nero\", vengono estratti gli oggetti \"uomo\" e \"cappello\".<\/li>\n
  2. Un LLM viene quindi invitato a generare domande relative a questi concetti, come \"C'\u00e8 un uomo nell'immagine?\" o \"Cosa indossa l'uomo?\".<\/li>\n
  3. Queste domande vengono inviate come prompt a un modello di Visual Question Answering (VQA). Grounding DINO esegue il rilevamento e il conteggio degli oggetti, mentre BLIP-2-FlanT5 VQA risponde alle domande relative agli attributi dopo aver analizzato l'immagine.<\/li>\n
  4. Un LLM combina le risposte alle domande in una base di conoscenza visiva dell'immagine.<\/li>\n
  5. Un LLM utilizza questo corpus di conoscenze di riferimento per correggere eventuali allucinazioni nella descrizione del MLLM originale e aggiungere dettagli che gli sono sfuggiti.<\/li>\n<\/ol>\n
    \"\"
    Descrizioni errate da MLLM e correzioni da Picchio. Fonte: arXiv<\/a><\/figcaption><\/figure>\n

    I ricercatori hanno chiamato il loro approccio Picchio in riferimento al modo in cui l'uccello raccoglie gli insetti dagli alberi.<\/p>\n

    I risultati dei test hanno mostrato che Woodpecker ha ottenuto un miglioramento dell'accuratezza di 30,66% per MiniGPT4 e di 24,33% per i modelli mPLUG-Owl.<\/p>\n

    La natura generica dei modelli richiesti in questo approccio significa che l'approccio Woodpecker potrebbe essere facilmente integrato in vari MLLM.<\/p>\n

    Se OpenAI integrer\u00e0 Woodpecker in ChatGPT, potremmo assistere a un netto miglioramento delle gi\u00e0 notevoli prestazioni visive. Una riduzione dell'allucinazione MLLM potrebbe anche migliorare il processo decisionale automatizzato dei sistemi che utilizzano descrizioni visive come input.<\/p>","protected":false},"excerpt":{"rendered":"

    I modelli linguistici multimodali di grandi dimensioni (MLLM) come il GPT-4V sono molto bravi ad analizzare e descrivere le immagini, ma a volte hanno delle allucinazioni e sbagliano. Un nuovo approccio chiamato Woodpecker potrebbe risolvere questo problema. Se si chiede a un MLLM di descrivere una foto, normalmente \u00e8 in grado di individuare gli oggetti e di descrivere accuratamente la scena. Tuttavia, come nel caso delle risposte alle richieste di testo, il modello a volte fa delle ipotesi basate su elementi o concetti che spesso compaiono insieme. Di conseguenza, un MLLM potrebbe descrivere una foto di una vetrina e dire che ci sono persone nella scena quando in realt\u00e0 non ce ne sono. Correzione<\/p>","protected":false},"author":6,"featured_media":6783,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[84],"tags":[166,450],"class_list":["post-6777","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-industry","tag-computer-vision","tag-mllm"],"yoast_head":"\nWoodpecker could solve multimodal LLM hallucinations | 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\/2023\/10\/woodpecker-could-solve-multimodal-llm-hallucinations\/\" \/>\n<meta property=\"og:locale\" content=\"it_IT\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Woodpecker could solve multimodal LLM hallucinations | DailyAI\" \/>\n<meta property=\"og:description\" content=\"Multimodal Large Language Models (MLLM) like GPT-4V are really good at analyzing and describing images but sometimes they hallucinate and get things wrong. A new approach called Woodpecker could fix that. If you ask an MLLM to describe a photo it can normally pick out the objects and accurately describe the scene. But as with answers to text prompts, the model sometimes makes assumptions based on items or concepts that often appear together. As a result, an MLLM could describe a photo of a shopfront scene and say there are people in the scene when there actually aren\u2019t any. Fixing\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dailyai.com\/it\/2023\/10\/woodpecker-could-solve-multimodal-llm-hallucinations\/\" \/>\n<meta property=\"og:site_name\" content=\"DailyAI\" \/>\n<meta property=\"article:published_time\" content=\"2023-10-26T09:17:15+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2023-10-26T09:22:02+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/woodpecker.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1920\" \/>\n\t<meta property=\"og:image:height\" content=\"1080\" \/>\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=\"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\\\/2023\\\/10\\\/woodpecker-could-solve-multimodal-llm-hallucinations\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/woodpecker-could-solve-multimodal-llm-hallucinations\\\/\"},\"author\":{\"name\":\"Eugene van der Watt\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/7ce525c6d0c79838b7cc7cde96993cfa\"},\"headline\":\"Woodpecker could solve multimodal LLM hallucinations\",\"datePublished\":\"2023-10-26T09:17:15+00:00\",\"dateModified\":\"2023-10-26T09:22:02+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/woodpecker-could-solve-multimodal-llm-hallucinations\\\/\"},\"wordCount\":465,\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/woodpecker-could-solve-multimodal-llm-hallucinations\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/10\\\/woodpecker.jpg\",\"keywords\":[\"Computer vision\",\"MLLM\"],\"articleSection\":[\"Industry\"],\"inLanguage\":\"it-IT\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/woodpecker-could-solve-multimodal-llm-hallucinations\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/woodpecker-could-solve-multimodal-llm-hallucinations\\\/\",\"name\":\"Woodpecker could solve multimodal LLM hallucinations | DailyAI\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/woodpecker-could-solve-multimodal-llm-hallucinations\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/woodpecker-could-solve-multimodal-llm-hallucinations\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/10\\\/woodpecker.jpg\",\"datePublished\":\"2023-10-26T09:17:15+00:00\",\"dateModified\":\"2023-10-26T09:22:02+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/woodpecker-could-solve-multimodal-llm-hallucinations\\\/#breadcrumb\"},\"inLanguage\":\"it-IT\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/woodpecker-could-solve-multimodal-llm-hallucinations\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"it-IT\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/woodpecker-could-solve-multimodal-llm-hallucinations\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/10\\\/woodpecker.jpg\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/10\\\/woodpecker.jpg\",\"width\":1920,\"height\":1080},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/woodpecker-could-solve-multimodal-llm-hallucinations\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dailyai.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Woodpecker could solve multimodal LLM hallucinations\"}]},{\"@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":"Woodpecker potrebbe risolvere le allucinazioni multimodali di LLM | 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\/2023\/10\/woodpecker-could-solve-multimodal-llm-hallucinations\/","og_locale":"it_IT","og_type":"article","og_title":"Woodpecker could solve multimodal LLM hallucinations | DailyAI","og_description":"Multimodal Large Language Models (MLLM) like GPT-4V are really good at analyzing and describing images but sometimes they hallucinate and get things wrong. A new approach called Woodpecker could fix that. If you ask an MLLM to describe a photo it can normally pick out the objects and accurately describe the scene. But as with answers to text prompts, the model sometimes makes assumptions based on items or concepts that often appear together. As a result, an MLLM could describe a photo of a shopfront scene and say there are people in the scene when there actually aren\u2019t any. Fixing","og_url":"https:\/\/dailyai.com\/it\/2023\/10\/woodpecker-could-solve-multimodal-llm-hallucinations\/","og_site_name":"DailyAI","article_published_time":"2023-10-26T09:17:15+00:00","article_modified_time":"2023-10-26T09:22:02+00:00","og_image":[{"width":1920,"height":1080,"url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/woodpecker.jpg","type":"image\/jpeg"}],"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\/2023\/10\/woodpecker-could-solve-multimodal-llm-hallucinations\/#article","isPartOf":{"@id":"https:\/\/dailyai.com\/2023\/10\/woodpecker-could-solve-multimodal-llm-hallucinations\/"},"author":{"name":"Eugene van der Watt","@id":"https:\/\/dailyai.com\/#\/schema\/person\/7ce525c6d0c79838b7cc7cde96993cfa"},"headline":"Woodpecker could solve multimodal LLM hallucinations","datePublished":"2023-10-26T09:17:15+00:00","dateModified":"2023-10-26T09:22:02+00:00","mainEntityOfPage":{"@id":"https:\/\/dailyai.com\/2023\/10\/woodpecker-could-solve-multimodal-llm-hallucinations\/"},"wordCount":465,"publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"image":{"@id":"https:\/\/dailyai.com\/2023\/10\/woodpecker-could-solve-multimodal-llm-hallucinations\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/woodpecker.jpg","keywords":["Computer vision","MLLM"],"articleSection":["Industry"],"inLanguage":"it-IT"},{"@type":"WebPage","@id":"https:\/\/dailyai.com\/2023\/10\/woodpecker-could-solve-multimodal-llm-hallucinations\/","url":"https:\/\/dailyai.com\/2023\/10\/woodpecker-could-solve-multimodal-llm-hallucinations\/","name":"Woodpecker potrebbe risolvere le allucinazioni multimodali di LLM | DailyAI","isPartOf":{"@id":"https:\/\/dailyai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dailyai.com\/2023\/10\/woodpecker-could-solve-multimodal-llm-hallucinations\/#primaryimage"},"image":{"@id":"https:\/\/dailyai.com\/2023\/10\/woodpecker-could-solve-multimodal-llm-hallucinations\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/woodpecker.jpg","datePublished":"2023-10-26T09:17:15+00:00","dateModified":"2023-10-26T09:22:02+00:00","breadcrumb":{"@id":"https:\/\/dailyai.com\/2023\/10\/woodpecker-could-solve-multimodal-llm-hallucinations\/#breadcrumb"},"inLanguage":"it-IT","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2023\/10\/woodpecker-could-solve-multimodal-llm-hallucinations\/"]}]},{"@type":"ImageObject","inLanguage":"it-IT","@id":"https:\/\/dailyai.com\/2023\/10\/woodpecker-could-solve-multimodal-llm-hallucinations\/#primaryimage","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/woodpecker.jpg","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/woodpecker.jpg","width":1920,"height":1080},{"@type":"BreadcrumbList","@id":"https:\/\/dailyai.com\/2023\/10\/woodpecker-could-solve-multimodal-llm-hallucinations\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dailyai.com\/"},{"@type":"ListItem","position":2,"name":"Woodpecker could solve multimodal LLM hallucinations"}]},{"@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\/6777","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=6777"}],"version-history":[{"count":4,"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/posts\/6777\/revisions"}],"predecessor-version":[{"id":6784,"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/posts\/6777\/revisions\/6784"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/media\/6783"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/media?parent=6777"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/categories?post=6777"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/tags?post=6777"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}