{"id":8047,"date":"2023-12-06T12:34:54","date_gmt":"2023-12-06T12:34:54","guid":{"rendered":"https:\/\/dailyai.com\/?p=8047"},"modified":"2023-12-06T12:34:54","modified_gmt":"2023-12-06T12:34:54","slug":"new-approach-could-make-large-language-models-300x-faster","status":"publish","type":"post","link":"https:\/\/dailyai.com\/it\/2023\/12\/new-approach-could-make-large-language-models-300x-faster\/","title":{"rendered":"Un nuovo approccio potrebbe rendere i modelli linguistici di grandi dimensioni 300 volte pi\u00f9 veloci"},"content":{"rendered":"<p><strong>Gli scienziati del Politecnico di Zurigo hanno scoperto che i Large Language Models (LLM) devono utilizzare solo una piccola frazione dei loro neuroni per le inferenze individuali. Il loro nuovo approccio promette di rendere gli LLM molto pi\u00f9 veloci.<\/strong><\/p>\n<p>Per iniziare a capire come sono riusciti a velocizzare i modelli di IA, dobbiamo avere un'idea approssimativa di alcuni degli elementi tecnici che compongono un modello linguistico di IA.<\/p>\n<p>I modelli di intelligenza artificiale come GPT o Llama sono costituiti da reti feedforward, un tipo di rete neurale artificiale.<\/p>\n<p>Le reti feedforward (FF) sono tipicamente organizzate in strati, con ogni strato di neuroni che riceve l'input dallo strato precedente e invia l'output allo strato successivo.<\/p>\n<p>Ci\u00f2 comporta la moltiplicazione della matrice densa (DMM), che richiede che ogni neurone del FF esegua i calcoli su tutti gli ingressi dello strato precedente. Questo \u00e8 il motivo per cui <a href=\"https:\/\/dailyai.com\/it\/2023\/11\/nvidia-achieves-record-18b-q3-revenue-crediting-generative-ai\/\">Nvidia vende cos\u00ec tante delle sue GPU<\/a> perch\u00e9 questo processo richiede molta potenza di elaborazione.<\/p>\n<p><a href=\"https:\/\/arxiv.org\/pdf\/2311.10770.pdf\" target=\"_blank\" rel=\"noopener\">I ricercatori<\/a> ha utilizzato le reti Fast Feedforward (FFF) per rendere questo processo molto pi\u00f9 veloce. Una FFF prende ogni strato di neuroni, lo suddivide in blocchi e seleziona solo i blocchi pi\u00f9 rilevanti in base all'input. Questo processo equivale a eseguire una moltiplicazione matriciale condizionale (CMM).<\/p>\n<p>Ci\u00f2 significa che invece di coinvolgere tutti i neuroni di uno strato nel calcolo, ne viene coinvolta solo una frazione molto piccola.<\/p>\n<p>Pensate a come smistare una pila di posta per trovare una lettera destinata a voi. Invece di leggere il nome e l'indirizzo su ogni singola lettera, potreste prima ordinarle per codice postale e poi concentrarvi solo su quelle relative alla vostra zona.<\/p>\n<p>Allo stesso modo, le FFF identificano solo i pochi neuroni necessari per ogni calcolo, con il risultato di una frazione dell'elaborazione richiesta rispetto alle FF tradizionali.<\/p>\n<h2>Quanto pi\u00f9 veloce?<\/h2>\n<p>I ricercatori hanno testato il loro metodo su una variante del modello BERT di Google che hanno chiamato UltraFastBERT. UltraFastBERT \u00e8 composto da 4095 neuroni, ma impegna selettivamente solo 12 neuroni per ogni strato di inferenza.<\/p>\n<p>Ci\u00f2 significa che UltraFastBERT richiede circa 0,03% dei suoi neuroni per essere coinvolto nell'elaborazione durante l'inferenza, mentre il BERT normale avrebbe bisogno di 100% dei suoi neuroni coinvolti nel calcolo.<\/p>\n<p>In teoria, ci\u00f2 significa che UltraFastBERT sarebbe 341 volte pi\u00f9 veloce di BERT o di GPT-3.<\/p>\n<p>Perch\u00e9 diciamo \"teoricamente\" quando i ricercatori ci assicurano che il loro metodo funziona? Perch\u00e9 hanno dovuto creare un workaround software per far funzionare il loro FFF con il BERT e hanno ottenuto un miglioramento della velocit\u00e0 solo di 78 volte durante i test reali.<\/p>\n<h2>\u00c8 un segreto<\/h2>\n<p>Il documento di ricerca spiega che \"la moltiplicazione di matrici dense \u00e8 l'operazione matematica pi\u00f9 ottimizzata nella storia dell'informatica. Sono stati compiuti sforzi enormi per progettare memorie, chip, set di istruzioni e routine software che la eseguano il pi\u00f9 velocemente possibile. Molti di questi progressi sono stati... tenuti riservati ed esposti all'utente finale solo attraverso potenti ma restrittive interfacce di programmazione\".<\/p>\n<p>In pratica, stanno dicendo che gli ingegneri che hanno scoperto i modi pi\u00f9 efficienti per elaborare la matematica necessaria per le reti FF tradizionali mantengono segreti i loro software e algoritmi di basso livello e non permettono di guardare il loro codice.<\/p>\n<p>Se i cervelli dietro i progetti delle GPU Intel o Nvidia consentissero l'accesso al codice di basso livello per implementare le reti FFF nei modelli di intelligenza artificiale, il miglioramento della velocit\u00e0 di 341 volte potrebbe essere una realt\u00e0.<\/p>\n<p>Ma lo faranno? Se poteste progettare le vostre GPU in modo che le persone possano acquistarne 99,7% in meno per eseguire la stessa quantit\u00e0 di elaborazione, lo fareste? L'economia avr\u00e0 voce in capitolo, ma le reti FFF potrebbero rappresentare il prossimo passo da gigante nell'IA.<\/p>","protected":false},"excerpt":{"rendered":"<p>Gli scienziati del Politecnico di Zurigo hanno scoperto che i Large Language Models (LLM) devono utilizzare solo una piccola frazione dei loro neuroni per le inferenze individuali. Il loro nuovo approccio promette di rendere i modelli LLM molto pi\u00f9 veloci. Per iniziare a capire come sono riusciti a velocizzare i modelli di intelligenza artificiale, dobbiamo avere un'idea approssimativa di alcuni degli elementi tecnici che compongono un modello linguistico di intelligenza artificiale. I modelli di intelligenza artificiale come GPT o Llama sono costituiti da reti feedforward, un tipo di rete neurale artificiale. Le reti feedforward (FF) sono tipicamente organizzate in strati, con ogni strato di neuroni che riceve input da<\/p>","protected":false},"author":6,"featured_media":8049,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[84],"tags":[118,105],"class_list":["post-8047","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-industry","tag-llms","tag-machine-learning"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.4 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>New approach could make large language models 300x faster | 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\/12\/new-approach-could-make-large-language-models-300x-faster\/\" \/>\n<meta property=\"og:locale\" content=\"it_IT\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"New approach could make large language models 300x faster | DailyAI\" \/>\n<meta property=\"og:description\" content=\"Scientists from ETH Zurich found that Large Language Models (LLM) only need to use a small fraction of their neurons for individual inferences. Their new approach promises to make LLMs run a lot faster. To begin to understand how they managed to speed up AI models we need to get a rough idea of some of the technical stuff that makes up an AI language model. AI models like GPT or Llama are made up of feedforward networks, a type of artificial neural network. Feedforward networks (FF) are typically organized into layers, with each layer of neurons receiving input from\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dailyai.com\/it\/2023\/12\/new-approach-could-make-large-language-models-300x-faster\/\" \/>\n<meta property=\"og:site_name\" content=\"DailyAI\" \/>\n<meta property=\"article:published_time\" content=\"2023-12-06T12:34:54+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/neural-network-concept-art.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1000\" \/>\n\t<meta property=\"og:image:height\" content=\"625\" \/>\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\\\/12\\\/new-approach-could-make-large-language-models-300x-faster\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/new-approach-could-make-large-language-models-300x-faster\\\/\"},\"author\":{\"name\":\"Eugene van der Watt\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/7ce525c6d0c79838b7cc7cde96993cfa\"},\"headline\":\"New approach could make large language models 300x faster\",\"datePublished\":\"2023-12-06T12:34:54+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/new-approach-could-make-large-language-models-300x-faster\\\/\"},\"wordCount\":604,\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/new-approach-could-make-large-language-models-300x-faster\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/12\\\/neural-network-concept-art.jpg\",\"keywords\":[\"LLMS\",\"machine learning\"],\"articleSection\":[\"Industry\"],\"inLanguage\":\"it-IT\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/new-approach-could-make-large-language-models-300x-faster\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/new-approach-could-make-large-language-models-300x-faster\\\/\",\"name\":\"New approach could make large language models 300x faster | DailyAI\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/new-approach-could-make-large-language-models-300x-faster\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/new-approach-could-make-large-language-models-300x-faster\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/12\\\/neural-network-concept-art.jpg\",\"datePublished\":\"2023-12-06T12:34:54+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/new-approach-could-make-large-language-models-300x-faster\\\/#breadcrumb\"},\"inLanguage\":\"it-IT\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/new-approach-could-make-large-language-models-300x-faster\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"it-IT\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/new-approach-could-make-large-language-models-300x-faster\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/12\\\/neural-network-concept-art.jpg\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/12\\\/neural-network-concept-art.jpg\",\"width\":1000,\"height\":625},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/new-approach-could-make-large-language-models-300x-faster\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dailyai.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"New approach could make large language models 300x faster\"}]},{\"@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":"Un nuovo approccio potrebbe rendere i modelli linguistici di grandi dimensioni 300 volte pi\u00f9 veloci | 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\/12\/new-approach-could-make-large-language-models-300x-faster\/","og_locale":"it_IT","og_type":"article","og_title":"New approach could make large language models 300x faster | DailyAI","og_description":"Scientists from ETH Zurich found that Large Language Models (LLM) only need to use a small fraction of their neurons for individual inferences. Their new approach promises to make LLMs run a lot faster. To begin to understand how they managed to speed up AI models we need to get a rough idea of some of the technical stuff that makes up an AI language model. AI models like GPT or Llama are made up of feedforward networks, a type of artificial neural network. Feedforward networks (FF) are typically organized into layers, with each layer of neurons receiving input from","og_url":"https:\/\/dailyai.com\/it\/2023\/12\/new-approach-could-make-large-language-models-300x-faster\/","og_site_name":"DailyAI","article_published_time":"2023-12-06T12:34:54+00:00","og_image":[{"width":1000,"height":625,"url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/neural-network-concept-art.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\/12\/new-approach-could-make-large-language-models-300x-faster\/#article","isPartOf":{"@id":"https:\/\/dailyai.com\/2023\/12\/new-approach-could-make-large-language-models-300x-faster\/"},"author":{"name":"Eugene van der Watt","@id":"https:\/\/dailyai.com\/#\/schema\/person\/7ce525c6d0c79838b7cc7cde96993cfa"},"headline":"New approach could make large language models 300x faster","datePublished":"2023-12-06T12:34:54+00:00","mainEntityOfPage":{"@id":"https:\/\/dailyai.com\/2023\/12\/new-approach-could-make-large-language-models-300x-faster\/"},"wordCount":604,"publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"image":{"@id":"https:\/\/dailyai.com\/2023\/12\/new-approach-could-make-large-language-models-300x-faster\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/neural-network-concept-art.jpg","keywords":["LLMS","machine learning"],"articleSection":["Industry"],"inLanguage":"it-IT"},{"@type":"WebPage","@id":"https:\/\/dailyai.com\/2023\/12\/new-approach-could-make-large-language-models-300x-faster\/","url":"https:\/\/dailyai.com\/2023\/12\/new-approach-could-make-large-language-models-300x-faster\/","name":"Un nuovo approccio potrebbe rendere i modelli linguistici di grandi dimensioni 300 volte pi\u00f9 veloci | DailyAI","isPartOf":{"@id":"https:\/\/dailyai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dailyai.com\/2023\/12\/new-approach-could-make-large-language-models-300x-faster\/#primaryimage"},"image":{"@id":"https:\/\/dailyai.com\/2023\/12\/new-approach-could-make-large-language-models-300x-faster\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/neural-network-concept-art.jpg","datePublished":"2023-12-06T12:34:54+00:00","breadcrumb":{"@id":"https:\/\/dailyai.com\/2023\/12\/new-approach-could-make-large-language-models-300x-faster\/#breadcrumb"},"inLanguage":"it-IT","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2023\/12\/new-approach-could-make-large-language-models-300x-faster\/"]}]},{"@type":"ImageObject","inLanguage":"it-IT","@id":"https:\/\/dailyai.com\/2023\/12\/new-approach-could-make-large-language-models-300x-faster\/#primaryimage","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/neural-network-concept-art.jpg","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/neural-network-concept-art.jpg","width":1000,"height":625},{"@type":"BreadcrumbList","@id":"https:\/\/dailyai.com\/2023\/12\/new-approach-could-make-large-language-models-300x-faster\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dailyai.com\/"},{"@type":"ListItem","position":2,"name":"New approach could make large language models 300x faster"}]},{"@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\/8047","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=8047"}],"version-history":[{"count":3,"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/posts\/8047\/revisions"}],"predecessor-version":[{"id":8051,"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/posts\/8047\/revisions\/8051"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/media\/8049"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/media?parent=8047"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/categories?post=8047"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/tags?post=8047"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}