{"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\/pt\/2023\/12\/new-approach-could-make-large-language-models-300x-faster\/","title":{"rendered":"Uma nova abordagem pode tornar os modelos lingu\u00edsticos de grande dimens\u00e3o 300 vezes mais r\u00e1pidos"},"content":{"rendered":"

Cientistas da ETH Zurich descobriram que os modelos de linguagem de grande dimens\u00e3o (LLM) s\u00f3 precisam de utilizar uma pequena fra\u00e7\u00e3o dos seus neur\u00f3nios para infer\u00eancias individuais. A sua nova abordagem promete fazer com que os LLM funcionem muito mais depressa.<\/strong><\/p>\n

Para come\u00e7ar a compreender como conseguiram acelerar os modelos de IA, precisamos de ter uma ideia aproximada de alguns dos aspectos t\u00e9cnicos que constituem um modelo de linguagem de IA.<\/p>\n

Os modelos de IA como o GPT ou o Llama s\u00e3o constitu\u00eddos por redes feedforward, um tipo de rede neural artificial.<\/p>\n

As redes feedforward (FF) est\u00e3o normalmente organizadas em camadas, sendo que cada camada de neur\u00f3nios recebe a entrada da camada anterior e envia a sua sa\u00edda para a camada seguinte.<\/p>\n

Isto envolve a multiplica\u00e7\u00e3o de matrizes densas (DMM), que exige que cada neur\u00f3nio na FF efectue c\u00e1lculos em todas as entradas da camada anterior. E \u00e9 por isso que A Nvidia vende tantas das suas GPUs<\/a> porque este processo requer muito poder de processamento.<\/p>\n

Os investigadores<\/a> utilizou as redes Fast Feedforward (FFF) para tornar este processo muito mais r\u00e1pido. Uma FFF pega em cada camada de neur\u00f3nios, divide-a em blocos e depois selecciona apenas os blocos mais relevantes com base na entrada. Este processo equivale a efetuar uma multiplica\u00e7\u00e3o condicional de matrizes (CMM).<\/p>\n

Isto significa que, em vez de todos os neur\u00f3nios de uma camada estarem envolvidos no c\u00e1lculo, apenas uma pequena fra\u00e7\u00e3o est\u00e1 envolvida.<\/p>\n

Pense nisto como separar uma pilha de correio para encontrar uma carta destinada a si. Em vez de ler o nome e a morada em todas as cartas, pode come\u00e7ar por orden\u00e1-las por c\u00f3digo postal e depois concentrar-se apenas nas cartas da sua \u00e1rea.<\/p>\n

Da mesma forma, os FFF identificam apenas os poucos neur\u00f3nios necess\u00e1rios para cada c\u00e1lculo, o que resulta em apenas uma fra\u00e7\u00e3o do processamento necess\u00e1rio em compara\u00e7\u00e3o com os FF tradicionais.<\/p>\n

Quanto mais r\u00e1pido?<\/h2>\n

Os investigadores testaram o seu m\u00e9todo numa variante do modelo BERT da Google a que chamaram UltraFastBERT. O UltraFastBERT \u00e9 composto por 4095 neur\u00f3nios, mas envolve seletivamente apenas 12 neur\u00f3nios para cada infer\u00eancia de camada.<\/p>\n

Isto significa que o UltraFastBERT requer que cerca de 0,03% dos seus neur\u00f3nios estejam envolvidos no processamento durante a infer\u00eancia, enquanto o BERT normal necessitaria de 100% dos seus neur\u00f3nios envolvidos no c\u00e1lculo.<\/p>\n

Teoricamente, isto significa que o UltraFastBERT seria 341x mais r\u00e1pido do que o BERT ou o GPT-3.<\/p>\n

Porque \u00e9 que dizemos \"teoricamente\" quando os investigadores nos garantem que o seu m\u00e9todo funciona? Porque tiveram de criar uma solu\u00e7\u00e3o de software para que o seu FFF funcionasse com o BERT e s\u00f3 conseguiram uma melhoria de 78x na velocidade durante os testes reais.<\/p>\n

\u00c9 um segredo<\/h2>\n

O documento de investiga\u00e7\u00e3o explicava que \"a multiplica\u00e7\u00e3o de matrizes densas \u00e9 a opera\u00e7\u00e3o matem\u00e1tica mais optimizada na hist\u00f3ria da computa\u00e7\u00e3o. Foi feito um enorme esfor\u00e7o para conceber mem\u00f3rias, chips, conjuntos de instru\u00e7\u00f5es e rotinas de software que a executam o mais rapidamente poss\u00edvel. Muitos destes avan\u00e7os foram... mantidos confidenciais e expostos ao utilizador final apenas atrav\u00e9s de interfaces de programa\u00e7\u00e3o poderosas mas restritivas.\"<\/p>\n

Basicamente, est\u00e3o a dizer que os engenheiros que descobriram as formas mais eficientes de fazer o processamento da matem\u00e1tica necess\u00e1ria para as redes FF tradicionais mant\u00eam o seu software e algoritmos de baixo n\u00edvel em segredo e n\u00e3o permitem que se veja o seu c\u00f3digo.<\/p>\n

Se os c\u00e9rebros por detr\u00e1s dos projectos das GPUs Intel ou Nvidia permitissem o acesso a c\u00f3digo de baixo n\u00edvel para implementar redes FFF em modelos de IA, ent\u00e3o a melhoria de velocidade de 341x poderia ser uma realidade.<\/p>\n

Mas ser\u00e1 que o v\u00e3o fazer? Se pudessem conceber as vossas GPUs de modo a que as pessoas pudessem comprar menos 99,7% delas para fazer a mesma quantidade de processamento, f\u00e1-lo-iam? A economia ter\u00e1 alguma influ\u00eancia nesta quest\u00e3o, mas as redes FFF podem representar o pr\u00f3ximo salto gigante na IA.<\/p>","protected":false},"excerpt":{"rendered":"

Cientistas da ETH Zurich descobriram que os modelos de linguagem de grande dimens\u00e3o (LLM) s\u00f3 precisam de utilizar uma pequena fra\u00e7\u00e3o dos seus neur\u00f3nios para infer\u00eancias individuais. A sua nova abordagem promete fazer com que os LLM funcionem muito mais depressa. Para come\u00e7ar a compreender como conseguiram acelerar os modelos de IA, precisamos de ter uma ideia aproximada de alguns dos aspectos t\u00e9cnicos que constituem um modelo de linguagem de IA. Os modelos de IA como o GPT ou o Llama s\u00e3o constitu\u00eddos por redes feedforward, um tipo de rede neural artificial. As redes feedforward (FF) s\u00e3o tipicamente organizadas em camadas, com cada camada de neur\u00f3nios a receber dados de<\/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":"\nNew 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\/pt\/2023\/12\/new-approach-could-make-large-language-models-300x-faster\/\" \/>\n<meta property=\"og:locale\" content=\"pt_PT\" \/>\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\/pt\/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=\"Escrito por\" \/>\n\t<meta name=\"twitter:data1\" content=\"Eugene van der Watt\" \/>\n\t<meta name=\"twitter:label2\" content=\"Tempo estimado de leitura\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 minutos\" \/>\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\":\"pt-PT\"},{\"@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\":\"pt-PT\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/new-approach-could-make-large-language-models-300x-faster\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"pt-PT\",\"@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\":\"pt-PT\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\",\"name\":\"DailyAI\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"pt-PT\",\"@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\":\"pt-PT\",\"@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\\\/pt\\\/author\\\/eugene\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Uma nova abordagem pode tornar os modelos lingu\u00edsticos de grande dimens\u00e3o 300 vezes mais r\u00e1pidos | 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\/pt\/2023\/12\/new-approach-could-make-large-language-models-300x-faster\/","og_locale":"pt_PT","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\/pt\/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":{"Escrito por":"Eugene van der Watt","Tempo estimado de leitura":"3 minutos"},"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":"pt-PT"},{"@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":"Uma nova abordagem pode tornar os modelos lingu\u00edsticos de grande dimens\u00e3o 300 vezes mais r\u00e1pidos | 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":"pt-PT","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2023\/12\/new-approach-could-make-large-language-models-300x-faster\/"]}]},{"@type":"ImageObject","inLanguage":"pt-PT","@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":"A sua dose di\u00e1ria de not\u00edcias sobre IA","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":"pt-PT"},{"@type":"Organization","@id":"https:\/\/dailyai.com\/#organization","name":"DailyAI","url":"https:\/\/dailyai.com\/","logo":{"@type":"ImageObject","inLanguage":"pt-PT","@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":"pt-PT","@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 vem de uma forma\u00e7\u00e3o em engenharia eletr\u00f3nica e adora tudo o que \u00e9 tecnologia. Quando faz uma pausa no consumo de not\u00edcias sobre IA, pode encontr\u00e1-lo \u00e0 mesa de snooker.","sameAs":["www.linkedin.com\/in\/eugene-van-der-watt-16828119"],"url":"https:\/\/dailyai.com\/pt\/author\/eugene\/"}]}},"_links":{"self":[{"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/posts\/8047","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/users\/6"}],"replies":[{"embeddable":true,"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/comments?post=8047"}],"version-history":[{"count":3,"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/posts\/8047\/revisions"}],"predecessor-version":[{"id":8051,"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/posts\/8047\/revisions\/8051"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/media\/8049"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/media?parent=8047"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/categories?post=8047"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/tags?post=8047"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}