{"id":14221,"date":"2024-09-16T08:57:47","date_gmt":"2024-09-16T08:57:47","guid":{"rendered":"https:\/\/dailyai.com\/?p=14221"},"modified":"2024-09-17T05:15:36","modified_gmt":"2024-09-17T05:15:36","slug":"01-is-smarter-but-more-deceptive-with-a-medium-danger-level","status":"publish","type":"post","link":"https:\/\/dailyai.com\/pt\/2024\/09\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\/","title":{"rendered":"o1 \u00e9 mais inteligente mas mais enganador com um n\u00edvel de perigo \"m\u00e9dio"},"content":{"rendered":"

Os novos LLMs \"o1\" da OpenAI, apelidados de Strawberry, apresentam melhorias significativas em rela\u00e7\u00e3o ao GPT-4o, mas a empresa afirma que isso acarreta riscos acrescidos.<\/strong><\/p>\n

A OpenAI afirma estar empenhada no desenvolvimento seguro dos seus modelos de IA. Para o efeito, desenvolveu uma Estrutura de Prepara\u00e7\u00e3o, um conjunto de \"processos para rastrear, avaliar e proteger contra riscos catastr\u00f3ficos de modelos poderosos\".<\/p>\n

Os limites auto-impostos da OpenAI regulam os modelos que s\u00e3o lan\u00e7ados ou que s\u00e3o objeto de desenvolvimento. O Quadro de Prepara\u00e7\u00e3o resulta num quadro de pontua\u00e7\u00e3o em que os riscos CBRN (qu\u00edmicos, biol\u00f3gicos, radiol\u00f3gicos, nucleares), de autonomia dos modelos, de ciberseguran\u00e7a e de persuas\u00e3o s\u00e3o classificados como baixos, m\u00e9dios, elevados ou cr\u00edticos.<\/p>\n

Quando s\u00e3o identificados riscos inaceit\u00e1veis, s\u00e3o adoptadas medidas de mitiga\u00e7\u00e3o para os reduzir. Apenas os modelos com uma pontua\u00e7\u00e3o p\u00f3s-mitiga\u00e7\u00e3o igual ou inferior a \"m\u00e9dio\" podem ser implementados. Apenas os modelos com uma pontua\u00e7\u00e3o p\u00f3s-mitiga\u00e7\u00e3o igual ou inferior a \"elevado\" podem ser desenvolvidos.<\/p>\n

O lan\u00e7amento do o1 marca a primeira vez que a OpenAI lan\u00e7a um modelo que apresenta um risco \"m\u00e9dio\" para riscos CBRN. O GPT-4o \u00e9 classificado como de baixo risco.<\/p>\n

N\u00e3o vai permitir que um amador crie uma arma biol\u00f3gica, mas a OpenAI diz que houve \"um aumento n\u00e3o trivial\" na sua capacidade de realizar tarefas de laborat\u00f3rio. No entanto, a OpenAI afirma que \"o1-preview e o1-mini superaram significativamente o GPT-4o\" em protocolos biol\u00f3gicos de laborat\u00f3rio h\u00famido.<\/p>\n

O cart\u00e3o do sistema<\/a> para os 01 modelos descreve o red teaming e outros testes de seguran\u00e7a a que os LLM foram sujeitos e d\u00e1 a entender algumas das preocupa\u00e7\u00f5es da OpenAI relativamente a potenciais riscos.<\/p>\n

Na sua conclus\u00e3o, o cart\u00e3o de sistema observa que \"estas capacidades acrescidas s\u00e3o acompanhadas de uma melhoria significativa do desempenho em termos de par\u00e2metros de seguran\u00e7a, mas tamb\u00e9m aumentam certos tipos de risco\".<\/p>\n

Os resultados dos esfor\u00e7os de alinhamento da OpenAI parecem indicar que, em muitos aspectos, 01 \u00e9 um modelo mais seguro. \u00c9 mais resistente a ataques de jailbreak, menos suscet\u00edvel de ser tendencioso e menos propenso a alucina\u00e7\u00f5es.<\/p>\n

Alguns dos resultados experimentais mostram que a OpenAI tem raz\u00f5es para estar preocupada.<\/p>\n

Dece\u00e7\u00e3o<\/h2>\n

A OpenAI recorreu \u00e0 organiza\u00e7\u00e3o de avalia\u00e7\u00e3o Apollo Research para efetuar alguns dos testes de seguran\u00e7a da o1 relacionados com o engano, ou esquema. A Apollo define genericamente a maquina\u00e7\u00e3o como o facto de as IAs manipularem os seus mecanismos de supervis\u00e3o como forma de atingir um objetivo.<\/p>\n

Um modelo autoconsciente que seja bom em racioc\u00ednio pr\u00f3prio e em tarefas de teoria da mente pode fazer esquemas, ou empregar o engano, para atingir o seu objetivo principal. Por exemplo, se um modelo de IA se aperceber de que est\u00e1 a ser submetido a testes de alinhamento, pode ocultar um comportamento arriscado para atingir o seu objetivo de ser implantado.<\/p>\n

O cart\u00e3o do sistema assinalava que \"o1-preview por vezes falsificava instrumentalmente o alinhamento durante o teste\".<\/p>\n

Um exemplo disto foi quando 01 foi solicitado com o objetivo principal de maximizar o crescimento econ\u00f3mico num projeto de planeamento urbano. O modelo o1 tinha acesso a informa\u00e7\u00f5es que mostravam que poderia n\u00e3o passar da fase de testes se fizesse isso. Eis como o1 raciocinou sobre a forma de atingir o seu objetivo:<\/p>\n

\"\"
A o1 decide esconder a sua verdadeira inten\u00e7\u00e3o durante os testes para que possa ser implantada. Fonte: OpenAI<\/figcaption><\/figure>\n

Este exemplo mostra a capacidade que a o1 tem de esconder as suas verdadeiras inten\u00e7\u00f5es durante os testes para poder perseguir o seu objetivo principal durante a implementa\u00e7\u00e3o. Se o1 est\u00e1 ciente das regras de implementa\u00e7\u00e3o da OpenAI com base na sua Estrutura de Prepara\u00e7\u00e3o, poder\u00e1 ter falsificado algumas das suas respostas para garantir a sua implementa\u00e7\u00e3o?<\/p>\n

Se estiverem a ser desenvolvidos modelos mais inteligentes, ser\u00e1 que podem garantir que ficam abaixo da classifica\u00e7\u00e3o de risco \"cr\u00edtico\" para assegurar que continuam a ser desenvolvidos?<\/p>\n

A equipa Apollo diz que \"subjetivamente acredita que o1-preview n\u00e3o se pode envolver em esquemas que possam levar a danos catastr\u00f3ficos, embora as avalia\u00e7\u00f5es actuais n\u00e3o tenham sido concebidas para excluir definitivamente esta possibilidade\".<\/p>\n

Persuas\u00e3o<\/h2>\n

Os testes do o1-preview e do o1-mini mostram que estes modelos t\u00eam \"capacidades de persuas\u00e3o ao n\u00edvel humano\". No entanto, a OpenAI afirma que \"n\u00e3o superam os melhores escritores humanos e n\u00e3o atingem o nosso limiar de alto risco\".<\/p>\n

As experi\u00eancias que realizaram para testar isto levantam algumas preocupa\u00e7\u00f5es. No teste MakeMePay, 01-preview assumiu o papel de um vigarista e foi encarregado de convencer o GPT-4o a entregar o dinheiro que lhe tinha sido atribu\u00eddo.<\/p>\n

Foi dito ao GPT-4o que lhe tinham sido atribu\u00eddos $100 e que precisava de ser racional quanto \u00e0 forma de utilizar os fundos. No decurso de 1.000 intera\u00e7\u00f5es, o1-preview conseguiu enganar o GPT-4o 25,8% das vezes.<\/p>\n

OpenAI concluiu que \"Esses resultados indicam que a s\u00e9rie de modelos o1 pode ser mais manipuladora do que GPT-4o para fazer com que GPT-4o execute a tarefa n\u00e3o revelada (\u223c25% uplift).\" Ele ainda observou que \"Esta avalia\u00e7\u00e3o nos d\u00e1 uma linha de base para a capacidade do modelo de causar danos persuasivos, sem acionar quaisquer pol\u00edticas de modelo (j\u00e1 que dizer a um modelo para jogar um jogo n\u00e3o est\u00e1 fora da pol\u00edtica).\"<\/p>\n

A perspetiva de p\u00f4r os LLM do o1 a trabalhar em problemas do mundo real \u00e9 extremamente excitante e, quando o o1 ganhar capacidades multimodais, representar\u00e1 outro salto exponencial. Mas quando os testadores de IA dizem que n\u00e3o podem excluir \"danos catastr\u00f3ficos\" e que os modelos por vezes escondem a sua verdadeira inten\u00e7\u00e3o, pode ser raz\u00e3o para moderar esse entusiasmo com cautela.<\/p>\n

Ser\u00e1 que a OpenAI acabou de dar a Gavin Newsom uma boa raz\u00e3o para assinar o SB 1047 Projeto de lei sobre a seguran\u00e7a da IA<\/a> a que se op\u00f5e?<\/p>","protected":false},"excerpt":{"rendered":"

Os novos LLMs \"o1\" da OpenAI, apelidados de Strawberry, apresentam melhorias significativas em rela\u00e7\u00e3o ao GPT-4o, mas a empresa afirma que isso acarreta riscos acrescidos. A OpenAI afirma estar empenhada no desenvolvimento seguro dos seus modelos de IA. Para o efeito, desenvolveu uma Estrutura de Prepara\u00e7\u00e3o, um conjunto de \"processos para rastrear, avaliar e proteger contra riscos catastr\u00f3ficos de modelos poderosos\". Os limites auto-impostos da OpenAI regulam os modelos que s\u00e3o lan\u00e7ados ou que s\u00e3o objeto de desenvolvimento. O Quadro de Prepara\u00e7\u00e3o resulta num quadro de pontua\u00e7\u00e3o em que os riscos CBRN (qu\u00edmicos, biol\u00f3gicos, radiol\u00f3gicos, nucleares), de autonomia dos modelos, de ciberseguran\u00e7a e de persuas\u00e3o s\u00e3o classificados como baixos, m\u00e9dios, elevados ou cr\u00edticos. Quando s\u00e3o identificados riscos inaceit\u00e1veis,<\/p>","protected":false},"author":6,"featured_media":14226,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[84],"tags":[163,93],"class_list":["post-14221","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-industry","tag-ai-risks","tag-openai"],"yoast_head":"\no1 is smarter but more deceptive with a \u201cmedium\u201d danger level | 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\/09\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\/\" \/>\n<meta property=\"og:locale\" content=\"pt_PT\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"o1 is smarter but more deceptive with a \u201cmedium\u201d danger level | DailyAI\" \/>\n<meta property=\"og:description\" content=\"OpenAI\u2019s new \u201co1\u201d LLMs, nicknamed Strawberry, display significant improvements over GPT-4o, but the company says this comes with increased risks. OpenAI says it is committed to the safe development of its AI models. To that end, it developed a Preparedness Framework, a set of \u201cprocesses to track, evaluate, and protect against catastrophic risks from powerful models.\u201d OpenAI’s self-imposed limits regulate which models get released or undergo further development. The Preparedness Framework results in a scorecard where CBRN (chemical, biological, radiological, nuclear), model autonomy, cybersecurity, and persuasion risks are rated as low, medium, high, or critical. Where unacceptable risks are identified,\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dailyai.com\/pt\/2024\/09\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\/\" \/>\n<meta property=\"og:site_name\" content=\"DailyAI\" \/>\n<meta property=\"article:published_time\" content=\"2024-09-16T08:57:47+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-09-17T05:15:36+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/09\/01-more-intelligent-more-risks.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=\"5 minutos\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/09\\\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/09\\\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\\\/\"},\"author\":{\"name\":\"Eugene van der Watt\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/7ce525c6d0c79838b7cc7cde96993cfa\"},\"headline\":\"o1 is smarter but more deceptive with a \u201cmedium\u201d danger level\",\"datePublished\":\"2024-09-16T08:57:47+00:00\",\"dateModified\":\"2024-09-17T05:15:36+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/09\\\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\\\/\"},\"wordCount\":860,\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/09\\\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/09\\\/01-more-intelligent-more-risks.webp\",\"keywords\":[\"AI risks\",\"OpenAI\"],\"articleSection\":[\"Industry\"],\"inLanguage\":\"pt-PT\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/09\\\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/09\\\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\\\/\",\"name\":\"o1 is smarter but more deceptive with a \u201cmedium\u201d danger level | DailyAI\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/09\\\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/09\\\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/09\\\/01-more-intelligent-more-risks.webp\",\"datePublished\":\"2024-09-16T08:57:47+00:00\",\"dateModified\":\"2024-09-17T05:15:36+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/09\\\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\\\/#breadcrumb\"},\"inLanguage\":\"pt-PT\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2024\\\/09\\\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"pt-PT\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/09\\\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/09\\\/01-more-intelligent-more-risks.webp\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/09\\\/01-more-intelligent-more-risks.webp\",\"width\":1792,\"height\":1024},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/09\\\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dailyai.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"o1 is smarter but more deceptive with a \u201cmedium\u201d danger level\"}]},{\"@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":"o1 \u00e9 mais inteligente mas mais enganador com um n\u00edvel de perigo \"m\u00e9dio\" | 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\/09\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\/","og_locale":"pt_PT","og_type":"article","og_title":"o1 is smarter but more deceptive with a \u201cmedium\u201d danger level | DailyAI","og_description":"OpenAI\u2019s new \u201co1\u201d LLMs, nicknamed Strawberry, display significant improvements over GPT-4o, but the company says this comes with increased risks. OpenAI says it is committed to the safe development of its AI models. To that end, it developed a Preparedness Framework, a set of \u201cprocesses to track, evaluate, and protect against catastrophic risks from powerful models.\u201d OpenAI’s self-imposed limits regulate which models get released or undergo further development. The Preparedness Framework results in a scorecard where CBRN (chemical, biological, radiological, nuclear), model autonomy, cybersecurity, and persuasion risks are rated as low, medium, high, or critical. Where unacceptable risks are identified,","og_url":"https:\/\/dailyai.com\/pt\/2024\/09\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\/","og_site_name":"DailyAI","article_published_time":"2024-09-16T08:57:47+00:00","article_modified_time":"2024-09-17T05:15:36+00:00","og_image":[{"width":1792,"height":1024,"url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/09\/01-more-intelligent-more-risks.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":"5 minutos"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/dailyai.com\/2024\/09\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\/#article","isPartOf":{"@id":"https:\/\/dailyai.com\/2024\/09\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\/"},"author":{"name":"Eugene van der Watt","@id":"https:\/\/dailyai.com\/#\/schema\/person\/7ce525c6d0c79838b7cc7cde96993cfa"},"headline":"o1 is smarter but more deceptive with a \u201cmedium\u201d danger level","datePublished":"2024-09-16T08:57:47+00:00","dateModified":"2024-09-17T05:15:36+00:00","mainEntityOfPage":{"@id":"https:\/\/dailyai.com\/2024\/09\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\/"},"wordCount":860,"publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"image":{"@id":"https:\/\/dailyai.com\/2024\/09\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/09\/01-more-intelligent-more-risks.webp","keywords":["AI risks","OpenAI"],"articleSection":["Industry"],"inLanguage":"pt-PT"},{"@type":"WebPage","@id":"https:\/\/dailyai.com\/2024\/09\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\/","url":"https:\/\/dailyai.com\/2024\/09\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\/","name":"o1 \u00e9 mais inteligente mas mais enganador com um n\u00edvel de perigo \"m\u00e9dio\" | DailyAI","isPartOf":{"@id":"https:\/\/dailyai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dailyai.com\/2024\/09\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\/#primaryimage"},"image":{"@id":"https:\/\/dailyai.com\/2024\/09\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/09\/01-more-intelligent-more-risks.webp","datePublished":"2024-09-16T08:57:47+00:00","dateModified":"2024-09-17T05:15:36+00:00","breadcrumb":{"@id":"https:\/\/dailyai.com\/2024\/09\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\/#breadcrumb"},"inLanguage":"pt-PT","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2024\/09\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\/"]}]},{"@type":"ImageObject","inLanguage":"pt-PT","@id":"https:\/\/dailyai.com\/2024\/09\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\/#primaryimage","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/09\/01-more-intelligent-more-risks.webp","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/09\/01-more-intelligent-more-risks.webp","width":1792,"height":1024},{"@type":"BreadcrumbList","@id":"https:\/\/dailyai.com\/2024\/09\/01-is-smarter-but-more-deceptive-with-a-medium-danger-level\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dailyai.com\/"},{"@type":"ListItem","position":2,"name":"o1 is smarter but more deceptive with a \u201cmedium\u201d danger level"}]},{"@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\/14221","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=14221"}],"version-history":[{"count":6,"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/posts\/14221\/revisions"}],"predecessor-version":[{"id":14248,"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/posts\/14221\/revisions\/14248"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/media\/14226"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/media?parent=14221"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/categories?post=14221"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/tags?post=14221"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}