{"id":11172,"date":"2024-04-02T09:32:07","date_gmt":"2024-04-02T09:32:07","guid":{"rendered":"https:\/\/dailyai.com\/?p=11172"},"modified":"2024-04-02T09:32:07","modified_gmt":"2024-04-02T09:32:07","slug":"deepmind-developed-safe-an-ai-agent-to-fact-check-llms","status":"publish","type":"post","link":"https:\/\/dailyai.com\/pt\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/","title":{"rendered":"A DeepMind desenvolveu o SAFE, um agente de IA para verificar os factos dos LLM"},"content":{"rendered":"

Os investigadores da DeepMind e da Universidade de Stanford desenvolveram um agente de IA que verifica os factos dos LLM e permite a avalia\u00e7\u00e3o comparativa da factualidade dos modelos de IA.<\/strong><\/p>\n

Mesmo os melhores modelos de IA tendem a alucinar<\/a> \u00e0s vezes. Se pedir ao ChatGPT para lhe dar os factos sobre um t\u00f3pico, quanto mais longa for a resposta, mais prov\u00e1vel \u00e9 que inclua alguns factos que n\u00e3o s\u00e3o verdadeiros.<\/p>\n

Que modelos s\u00e3o mais exactos em termos factuais do que outros quando geram respostas mais longas? \u00c9 dif\u00edcil dizer porque, at\u00e9 agora, n\u00e3o disp\u00fanhamos de uma refer\u00eancia para medir a factualidade das respostas longas dos LLM.<\/p>\n

O DeepMind come\u00e7ou por utilizar o GPT-4 para criar o LongFact, um conjunto de 2.280 perguntas sob a forma de quest\u00f5es relacionadas com 38 t\u00f3picos. Estas solicita\u00e7\u00f5es suscitam respostas longas do LLM que est\u00e1 a ser testado.<\/p>\n

Em seguida, criaram um agente de IA utilizando o GPT-3.5-turbo para utilizar o Google para verificar o grau de factualidade das respostas geradas pelo LLM. Chamaram a este m\u00e9todo Search-Augmented Factuality Evaluator (SAFE).<\/p>\n

O SAFE come\u00e7a por dividir a resposta longa do LLM em factos individuais. Em seguida, envia pedidos de pesquisa para o Google Search e analisa a veracidade do facto com base nas informa\u00e7\u00f5es contidas nos resultados da pesquisa.<\/p>\n

Aqui est\u00e1 um exemplo do trabalho de investiga\u00e7\u00e3o<\/a>.<\/p>\n

\"\"
Um pedido de procura de factos suscita uma resposta longa. A resposta \u00e9 dividida em factos individuais, revista para ser aut\u00f3noma, verificada quanto \u00e0 sua relev\u00e2ncia e verificada utilizando a Pesquisa Google. Fonte: arXiv<\/figcaption><\/figure>\n

Os investigadores afirmam que o SAFE atinge um \"desempenho sobre-humano\" em compara\u00e7\u00e3o com os anotadores humanos que fazem a verifica\u00e7\u00e3o dos factos.<\/p>\n

O SAFE concordou com 72% das anota\u00e7\u00f5es humanas e, nos casos em que diferiu das anota\u00e7\u00f5es humanas, foi considerado correto em 76% das vezes. Al\u00e9m disso, foi 20 vezes mais econ\u00f3mico do que os anotadores humanos de crowdsourcing. Assim, os LLM s\u00e3o melhores e mais baratos verificadores de factos do que os humanos.<\/p>\n

A qualidade da resposta dos LLMs testados foi medida com base no n\u00famero de fact\u00f3ides na sua resposta, combinado com o grau de factualidade de cada factoide.<\/p>\n

A m\u00e9trica que utilizaram (F1@K) estima o n\u00famero \"ideal\" de factos preferido pelos humanos numa resposta. Os testes de refer\u00eancia utilizaram 64 como mediana para K e 178 como m\u00e1ximo.<\/p>\n

Simplificando, F1@K \u00e9 uma medida de \"A resposta deu-me tantos factos como eu queria?\" combinada com \"Quantos desses factos eram verdadeiros?<\/p>\n

Qual \u00e9 o LLM mais factual?<\/h2>\n

Os investigadores utilizaram o LongFact para solicitar 13 LLMs das fam\u00edlias Gemini, GPT, Claude e PaLM-2. Em seguida, utilizaram o SAFE para avaliar a factualidade das suas respostas.<\/p>\n

O GPT-4-Turbo est\u00e1 no topo da lista como o modelo mais factual ao gerar respostas longas. Foi seguido de perto pelo Gemini-Ultra e pelo PaLM-2-L-IT-RLHF. Os resultados mostraram que os LLM maiores s\u00e3o mais factuais do que os mais pequenos.<\/p>\n

O c\u00e1lculo de F1@K provavelmente entusiasmaria os cientistas de dados, mas, por uma quest\u00e3o de simplicidade, estes resultados de refer\u00eancia mostram o grau de factualidade de cada modelo ao devolver respostas de comprimento m\u00e9dio e mais longas \u00e0s perguntas.<\/p>\n

\"\"
Desempenho de factualidade de 13 LLMs com K = 64 (o n\u00famero m\u00e9dio de factos entre todas as respostas do modelo) e K = 178 (o n\u00famero m\u00e1ximo de factos entre todas as respostas do modelo). Fonte: arXiv<\/figcaption><\/figure>\n

O SAFE \u00e9 uma forma barata e eficaz de quantificar a factualidade do LLM. \u00c9 mais r\u00e1pido e mais barato do que os humanos na verifica\u00e7\u00e3o de factos, mas continua a depender da veracidade das informa\u00e7\u00f5es que o Google apresenta nos resultados da pesquisa.<\/p>\n

A DeepMind lan\u00e7ou o SAFE para utiliza\u00e7\u00e3o p\u00fablica e sugeriu que poderia ajudar a melhorar a factualidade das LLM atrav\u00e9s de uma melhor pr\u00e9-treino e afina\u00e7\u00e3o. Tamb\u00e9m poderia permitir que um LLM verificasse os seus factos antes de apresentar o resultado a um utilizador.<\/p>\n

A OpenAI ficar\u00e1 satisfeita por ver que a investiga\u00e7\u00e3o da Google mostra que o GPT-4 bate o Gemini em mais um teste de refer\u00eancia.<\/p>","protected":false},"excerpt":{"rendered":"

Os investigadores da DeepMind e da Universidade de Stanford desenvolveram um agente de IA que verifica os factos dos LLM e permite a avalia\u00e7\u00e3o comparativa da factualidade dos modelos de IA. Mesmo os melhores modelos de IA tendem, por vezes, a alucinar. Se pedirmos ao ChatGPT para nos dar os factos sobre um t\u00f3pico, quanto mais longa for a resposta, maior \u00e9 a probabilidade de incluir alguns factos que n\u00e3o s\u00e3o verdadeiros. Que modelos s\u00e3o mais exactos em termos de factos do que outros quando geram respostas mais longas? \u00c9 dif\u00edcil dizer porque, at\u00e9 agora, n\u00e3o t\u00ednhamos uma refer\u00eancia para medir a factualidade das respostas longas do LLM. O DeepMind usou primeiro o GPT-4 para criar o LongFact, um conjunto de<\/p>","protected":false},"author":6,"featured_media":11182,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[84],"tags":[147,118],"class_list":["post-11172","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-industry","tag-deepmind","tag-llms"],"yoast_head":"\nDeepMind developed SAFE, an AI agent to fact-check 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\/pt\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/\" \/>\n<meta property=\"og:locale\" content=\"pt_PT\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"DeepMind developed SAFE, an AI agent to fact-check LLMs | DailyAI\" \/>\n<meta property=\"og:description\" content=\"Researchers from DeepMind and Stanford University developed an AI agent that fact-checks LLMs and enables benchmarking of AI model factuality. Even the best AI models still tend to hallucinate at times. If you ask ChatGPT to give you the facts about a topic, the longer its response the more likely it is to include some facts that aren\u2019t true. Which models are more factually accurate than others when generating longer answers? It\u2019s hard to say because until now, we didn\u2019t have a benchmark measuring the factuality of LLM long-form responses. DeepMind first used GPT-4 to create LongFact, a set of\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dailyai.com\/pt\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/\" \/>\n<meta property=\"og:site_name\" content=\"DailyAI\" \/>\n<meta property=\"article:published_time\" content=\"2024-04-02T09:32:07+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/fact-vs-fake.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=\"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=\"4 minutos\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\\\/\"},\"author\":{\"name\":\"Eugene van der Watt\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/7ce525c6d0c79838b7cc7cde96993cfa\"},\"headline\":\"DeepMind developed SAFE, an AI agent to fact-check LLMs\",\"datePublished\":\"2024-04-02T09:32:07+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\\\/\"},\"wordCount\":611,\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/fact-vs-fake.webp\",\"keywords\":[\"DeepMind\",\"LLMS\"],\"articleSection\":[\"Industry\"],\"inLanguage\":\"pt-PT\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\\\/\",\"name\":\"DeepMind developed SAFE, an AI agent to fact-check LLMs | DailyAI\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/fact-vs-fake.webp\",\"datePublished\":\"2024-04-02T09:32:07+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\\\/#breadcrumb\"},\"inLanguage\":\"pt-PT\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"pt-PT\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/fact-vs-fake.webp\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/fact-vs-fake.webp\",\"width\":1792,\"height\":1024},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dailyai.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"DeepMind developed SAFE, an AI agent to fact-check 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\":\"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":"A DeepMind desenvolveu o SAFE, um agente de IA para verificar os factos dos LLMs | 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\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/","og_locale":"pt_PT","og_type":"article","og_title":"DeepMind developed SAFE, an AI agent to fact-check LLMs | DailyAI","og_description":"Researchers from DeepMind and Stanford University developed an AI agent that fact-checks LLMs and enables benchmarking of AI model factuality. Even the best AI models still tend to hallucinate at times. If you ask ChatGPT to give you the facts about a topic, the longer its response the more likely it is to include some facts that aren\u2019t true. Which models are more factually accurate than others when generating longer answers? It\u2019s hard to say because until now, we didn\u2019t have a benchmark measuring the factuality of LLM long-form responses. DeepMind first used GPT-4 to create LongFact, a set of","og_url":"https:\/\/dailyai.com\/pt\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/","og_site_name":"DailyAI","article_published_time":"2024-04-02T09:32:07+00:00","og_image":[{"width":1792,"height":1024,"url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/fact-vs-fake.webp","type":"image\/webp"}],"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":"4 minutos"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/dailyai.com\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/#article","isPartOf":{"@id":"https:\/\/dailyai.com\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/"},"author":{"name":"Eugene van der Watt","@id":"https:\/\/dailyai.com\/#\/schema\/person\/7ce525c6d0c79838b7cc7cde96993cfa"},"headline":"DeepMind developed SAFE, an AI agent to fact-check LLMs","datePublished":"2024-04-02T09:32:07+00:00","mainEntityOfPage":{"@id":"https:\/\/dailyai.com\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/"},"wordCount":611,"publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"image":{"@id":"https:\/\/dailyai.com\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/fact-vs-fake.webp","keywords":["DeepMind","LLMS"],"articleSection":["Industry"],"inLanguage":"pt-PT"},{"@type":"WebPage","@id":"https:\/\/dailyai.com\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/","url":"https:\/\/dailyai.com\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/","name":"A DeepMind desenvolveu o SAFE, um agente de IA para verificar os factos dos LLMs | DailyAI","isPartOf":{"@id":"https:\/\/dailyai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dailyai.com\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/#primaryimage"},"image":{"@id":"https:\/\/dailyai.com\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/fact-vs-fake.webp","datePublished":"2024-04-02T09:32:07+00:00","breadcrumb":{"@id":"https:\/\/dailyai.com\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/#breadcrumb"},"inLanguage":"pt-PT","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/"]}]},{"@type":"ImageObject","inLanguage":"pt-PT","@id":"https:\/\/dailyai.com\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/#primaryimage","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/fact-vs-fake.webp","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/fact-vs-fake.webp","width":1792,"height":1024},{"@type":"BreadcrumbList","@id":"https:\/\/dailyai.com\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dailyai.com\/"},{"@type":"ListItem","position":2,"name":"DeepMind developed SAFE, an AI agent to fact-check LLMs"}]},{"@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\/11172","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=11172"}],"version-history":[{"count":2,"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/posts\/11172\/revisions"}],"predecessor-version":[{"id":11181,"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/posts\/11172\/revisions\/11181"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/media\/11182"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/media?parent=11172"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/categories?post=11172"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/tags?post=11172"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}