{"id":11164,"date":"2024-04-01T13:43:28","date_gmt":"2024-04-01T13:43:28","guid":{"rendered":"https:\/\/dailyai.com\/?p=11164"},"modified":"2024-04-02T17:03:30","modified_gmt":"2024-04-02T17:03:30","slug":"new-study-attempts-to-align-ai-with-crowdsourced-human-values","status":"publish","type":"post","link":"https:\/\/dailyai.com\/es\/2024\/04\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\/","title":{"rendered":"Un nuevo estudio intenta alinear la IA con los valores humanos del crowdsourcing"},"content":{"rendered":"<p><b>Investigadores del Meaning Alignment Institute han propuesto un nuevo enfoque, Moral Graph Elicitation (MGE), para alinear los sistemas de IA con los valores humanos.<\/b><\/p>\n<p><span style=\"font-weight: 400;\">A medida que la IA avanza y se integra en nuestra vida cotidiana, es primordial garantizar que sirva y represente a todos de forma justa. Sin embargo<\/span><span style=\"font-weight: 400;\">su <\/span><a href=\"https:\/\/static1.squarespace.com\/static\/65392ca578eee444c445c9de\/t\/6606f95edb20e8118074a344\/1711733370985\/human-values-and-alignment-29MAR2024.pdf\" target=\"_blank\" rel=\"noopener\"><span style=\"font-weight: 400;\">estudiar<\/span><\/a><span style=\"font-weight: 400;\"> sostiene que alinear la IA con los objetivos del usuario no garantiza por s\u00ed solo la seguridad.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">\u00a0\"Los sistemas de IA se desplegar\u00e1n en contextos en los que la adhesi\u00f3n ciega a la intenci\u00f3n del operador puede causar da\u00f1os como subproducto. Esto puede verse m\u00e1s claramente en entornos con din\u00e1micas competitivas, como las campa\u00f1as pol\u00edticas o la gesti\u00f3n de activos financieros\", argumentan los investigadores.\u00a0<\/span><\/p>\n<p>Esto se debe a que los modelos de IA est\u00e1n dise\u00f1ados para servir al usuario. Si el usuario da instrucciones a un modelo con fines nefastos, el af\u00e1n del modelo por servir al usuario puede hacer que se salte los guardarra\u00edles y obedezca.<\/p>\n<p>Una soluci\u00f3n es \"impregnar\" a la IA de una serie de valores que consulte cada vez que se le solicite.<\/p>\n<p>La pregunta es: \u00bfde d\u00f3nde proceden esos valores? \u00bfY pueden representar a las personas de forma equitativa?<\/p>\n<blockquote class=\"twitter-tweet\">\n<p dir=\"ltr\" lang=\"en\">\"\u00bfQu\u00e9 son los valores humanos y c\u00f3mo nos alineamos con ellos?\".<\/p>\n<p>Estamos muy contentos de publicar nuestro nuevo documento sobre la alineaci\u00f3n de valores, en coautor\u00eda con <a href=\"https:\/\/twitter.com\/ryan_t_lowe?ref_src=twsrc%5Etfw\">@ryan_t_lowe<\/a> y financiado por <a href=\"https:\/\/twitter.com\/OpenAI?ref_src=twsrc%5Etfw\">@openai<\/a>.<\/p>\n<p>\ud83d\udcdd: <a href=\"https:\/\/t.co\/iioFKmrDZA\">https:\/\/t.co\/iioFKmrDZA<\/a> <a href=\"https:\/\/t.co\/NSJa8dbcrM\">pic.twitter.com\/NSJa8dbcrM<\/a><\/p>\n<p>- Joe Edelman (@edelwax) <a href=\"https:\/\/twitter.com\/edelwax\/status\/1773621129200234573?ref_src=twsrc%5Etfw\">29 de marzo de 2024<\/a><\/p><\/blockquote>\n<p><script async src=\"https:\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script><\/p>\n<p><span style=\"font-weight: 400;\">Para resolver estos problemas, los investigadores propusieron alinear la IA con una representaci\u00f3n m\u00e1s profunda de los valores humanos a trav\u00e9s del MGE.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">El m\u00e9todo MGE tiene dos componentes clave: las tarjetas de valores y el gr\u00e1fico moral. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">Constituyen un objetivo de alineaci\u00f3n para el entrenamiento de modelos de aprendizaje autom\u00e1tico.<\/span><\/p>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Fichas de valores<\/b><span style=\"font-weight: 400;\"> captan lo que es importante para una persona en una situaci\u00f3n concreta. Consisten en \"pol\u00edticas atencionales constitutivas\" (PAC), que son las cosas a las que una persona presta atenci\u00f3n cuando toma una decisi\u00f3n significativa. Por ejemplo, al aconsejar a un amigo, uno puede centrarse en comprender sus emociones, sugerirle recursos \u00fatiles o considerar los posibles resultados de distintas opciones.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>El gr\u00e1fico moral<\/b><span style=\"font-weight: 400;\"> representa visualmente las relaciones entre las cartas de valores, indicando qu\u00e9 valores son m\u00e1s perspicaces o aplicables en un contexto determinado. Para construir el gr\u00e1fico moral, los participantes comparan diferentes tarjetas de valores, discerniendo cu\u00e1les creen que ofrecen una orientaci\u00f3n m\u00e1s sabia para una situaci\u00f3n concreta. As\u00ed se aprovecha la sabidur\u00eda colectiva de los participantes para identificar los valores m\u00e1s s\u00f3lidos y reconocidos para cada contexto.<\/span><\/li>\n<\/ul>\n<p><span style=\"font-weight: 400;\">Para probar el m\u00e9todo MGE, los investigadores realizaron un estudio con 500 estadounidenses que utilizaron el proceso para explorar tres temas controvertidos: el aborto, la paternidad y las armas utilizadas en el mot\u00edn del 6 de enero en el Capitolio.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Los resultados fueron prometedores: el 89,1% de los participantes se sinti\u00f3 bien representado por el proceso y el 89% pens\u00f3 que el gr\u00e1fico moral final era justo, aunque su valor no fuera votado como el m\u00e1s sensato.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">El estudio tambi\u00e9n esboza seis criterios que debe poseer un objetivo de alineaci\u00f3n para modelar el comportamiento siguiendo los valores humanos: debe ser de grano fino, generalizable, escalable, robusto, leg\u00edtimo y auditable. Los investigadores sostienen que el gr\u00e1fico moral producido por MGE cumple bien estos criterios.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Este estudio propone un enfoque similar al de Anthropic <\/span><a href=\"https:\/\/dailyai.com\/es\/2023\/10\/democratizing-ai-governance-an-anthropic-experiment\/\"><span style=\"font-weight: 400;\">IA Constitiutoria Colectiva<\/span><\/a>,<span style=\"font-weight: 400;\"> que tambi\u00e9n recauda valores para la alineaci\u00f3n de la IA. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">Sin embargo, el autor del estudio, Joe Edelman, dijo en X: \"Nuestro enfoque, MGE, supera a alternativas como CCAI por @anthropic en legitimidad en un estudio de caso, y ofrece solidez frente a la ret\u00f3rica ideol\u00f3gica. 89% incluso est\u00e1n de acuerdo en que los valores ganadores fueron justos, \u00a1incluso si su propio valor no gan\u00f3!\".<\/span><\/p>\n<blockquote class=\"twitter-tweet\">\n<p dir=\"ltr\" lang=\"en\">Nuestro enfoque, MGE, supera a alternativas como CCAI en <a href=\"https:\/\/twitter.com\/Anthropic?ref_src=twsrc%5Etfw\">@anthropic<\/a> sobre la legitimidad en un estudio de caso, y ofrece solidez frente a la ret\u00f3rica ideol\u00f3gica.<\/p>\n<p>89% incluso est\u00e1n de acuerdo en que los valores ganadores fueron justos, \u00a1aunque su propio valor no ganara! <a href=\"https:\/\/t.co\/sGgLCUtwzN\">pic.twitter.com\/sGgLCUtwzN<\/a><\/p>\n<p>- Joe Edelman (@edelwax) <a href=\"https:\/\/twitter.com\/edelwax\/status\/1773621155712377054?ref_src=twsrc%5Etfw\">29 de marzo de 2024<\/a><\/p><\/blockquote>\n<p><script async src=\"https:\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script><\/p>\n<h2>Limitaciones<\/h2>\n<p>Los enfoques de alineaci\u00f3n de la IA que recurren al crowdsourcing para obtener valores del p\u00fablico tienen sus limitaciones.<\/p>\n<p>Por ejemplo, las opiniones discrepantes han sido parte integrante de la toma de decisiones de la sociedad durante siglos, y la historia ha demostrado que la mayor\u00eda a menudo puede adoptar los puntos de vista divergentes de la minor\u00eda. Ejemplos de ello son la teor\u00eda de la evoluci\u00f3n de Darwin y las luchas por abolir la esclavitud y conceder el derecho de voto a las mujeres.<\/p>\n<p class=\"whitespace-pre-wrap break-words\">Adem\u00e1s, aunque la aportaci\u00f3n directa del p\u00fablico es democr\u00e1tica, puede llevar al populismo, donde la mayor\u00eda podr\u00eda anular las opiniones minoritarias o deso\u00edr el consejo de los expertos.<\/p>\n<p class=\"whitespace-pre-wrap break-words\">Otro reto es equilibrar los valores culturales globales o universalistas y los locales o relativistas. Principios ampliamente aceptados en una cultura o regi\u00f3n pueden ser controvertidos en otra.<\/p>\n<p class=\"whitespace-pre-wrap break-words\">Las constituciones de la IA podr\u00edan reforzar los valores occidentales, erosionando potencialmente las opiniones e ideas de los de la periferia.<\/p>\n<p><span style=\"font-weight: 400;\">Aunque este nuevo estudio reconoce sus limitaciones y la necesidad de seguir desarroll\u00e1ndolo, ofrece otra estrategia para crear sistemas de IA que se ajusten a los valores humanos. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">Cada intento cuenta si queremos que la IA centralizada sirva a todos de forma justa en el futuro.\u00a0<\/span><\/p>","protected":false},"excerpt":{"rendered":"<p>Investigadores del Meaning Alignment Institute han propuesto un nuevo enfoque, Moral Graph Elicitation (MGE), para alinear los sistemas de IA con los valores humanos. A medida que la IA avanza y se integra en nuestra vida cotidiana, es fundamental garantizar que sirva y represente a todos de forma justa. Sin embargo, este estudio sostiene que alinear la IA con los objetivos del usuario por s\u00ed solo no garantiza la seguridad.  \"Los sistemas de IA se desplegar\u00e1n en contextos en los que la adhesi\u00f3n ciega a la intenci\u00f3n del operador puede causar da\u00f1os como subproducto. Esto puede verse m\u00e1s claramente en entornos con din\u00e1micas competitivas, como las campa\u00f1as pol\u00edticas o la gesti\u00f3n de activos financieros\", argumentan los investigadores.  Esto se debe a que<\/p>","protected":false},"author":2,"featured_media":11165,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[88],"tags":[105,93],"class_list":["post-11164","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ethics","tag-machine-learning","tag-openai"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.4 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>New study attempts to align AI with crowdsourced human values | 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\/es\/2024\/04\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\/\" \/>\n<meta property=\"og:locale\" content=\"es_ES\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"New study attempts to align AI with crowdsourced human values | DailyAI\" \/>\n<meta property=\"og:description\" content=\"Researchers from the Meaning Alignment Institute have proposed a new approach, Moral Graph Elicitation (MGE), to align AI systems with human values. As AI becomes more advanced and integrated into our daily lives, ensuring it serves and represents everyone fairly is paramount. However, this study argues that aligning AI with the user&#8217;s goals alone doesn&#8217;t guarantee safety. \u00a0&#8220;AI systems will be deployed in contexts where blind adherence to operator intent can cause harm as a byproduct. This can be seen most clearly in environments with competitive dynamics, like political campaigns or managing financial assets,&#8221; the researchers argue.\u00a0 This is because\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dailyai.com\/es\/2024\/04\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\/\" \/>\n<meta property=\"og:site_name\" content=\"DailyAI\" \/>\n<meta property=\"article:published_time\" content=\"2024-04-01T13:43:28+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-04-02T17:03:30+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/DALL\u00b7E-2024-04-01-14.39.26-A-minimalist-scene-depicting-a-single-researcher-at-a-sleek-modern-desk-deeply-focused-on-aligning-AI-technology-with-human-values.-The-researcher-i.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=\"Sam Jeans\" \/>\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=\"Sam Jeans\" \/>\n\t<meta name=\"twitter:label2\" content=\"Tiempo de lectura\" \/>\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\\\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\\\/\"},\"author\":{\"name\":\"Sam Jeans\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/711e81f945549438e8bbc579efdeb3c9\"},\"headline\":\"New study attempts to align AI with crowdsourced human values\",\"datePublished\":\"2024-04-01T13:43:28+00:00\",\"dateModified\":\"2024-04-02T17:03:30+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\\\/\"},\"wordCount\":764,\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/DALL\u00b7E-2024-04-01-14.39.26-A-minimalist-scene-depicting-a-single-researcher-at-a-sleek-modern-desk-deeply-focused-on-aligning-AI-technology-with-human-values.-The-researcher-i.webp\",\"keywords\":[\"machine learning\",\"OpenAI\"],\"articleSection\":[\"Ethics &amp; Society\"],\"inLanguage\":\"es\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\\\/\",\"name\":\"New study attempts to align AI with crowdsourced human values | DailyAI\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/DALL\u00b7E-2024-04-01-14.39.26-A-minimalist-scene-depicting-a-single-researcher-at-a-sleek-modern-desk-deeply-focused-on-aligning-AI-technology-with-human-values.-The-researcher-i.webp\",\"datePublished\":\"2024-04-01T13:43:28+00:00\",\"dateModified\":\"2024-04-02T17:03:30+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\\\/#breadcrumb\"},\"inLanguage\":\"es\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"es\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/DALL\u00b7E-2024-04-01-14.39.26-A-minimalist-scene-depicting-a-single-researcher-at-a-sleek-modern-desk-deeply-focused-on-aligning-AI-technology-with-human-values.-The-researcher-i.webp\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/DALL\u00b7E-2024-04-01-14.39.26-A-minimalist-scene-depicting-a-single-researcher-at-a-sleek-modern-desk-deeply-focused-on-aligning-AI-technology-with-human-values.-The-researcher-i.webp\",\"width\":1792,\"height\":1024,\"caption\":\"AI values\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dailyai.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"New study attempts to align AI with crowdsourced human values\"}]},{\"@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\":\"es\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\",\"name\":\"DailyAI\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"es\",\"@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\\\/711e81f945549438e8bbc579efdeb3c9\",\"name\":\"Sam Jeans\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"es\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g\",\"caption\":\"Sam Jeans\"},\"description\":\"Sam is a science and technology writer who has worked in various AI startups. When he\u2019s not writing, he can be found reading medical journals or digging through boxes of vinyl records.\",\"sameAs\":[\"https:\\\/\\\/www.linkedin.com\\\/in\\\/sam-jeans-6746b9142\\\/\"],\"url\":\"https:\\\/\\\/dailyai.com\\\/es\\\/author\\\/samjeans\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Un nuevo estudio intenta alinear la IA con los valores humanos crowdsourced | 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\/es\/2024\/04\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\/","og_locale":"es_ES","og_type":"article","og_title":"New study attempts to align AI with crowdsourced human values | DailyAI","og_description":"Researchers from the Meaning Alignment Institute have proposed a new approach, Moral Graph Elicitation (MGE), to align AI systems with human values. As AI becomes more advanced and integrated into our daily lives, ensuring it serves and represents everyone fairly is paramount. However, this study argues that aligning AI with the user&#8217;s goals alone doesn&#8217;t guarantee safety. \u00a0&#8220;AI systems will be deployed in contexts where blind adherence to operator intent can cause harm as a byproduct. This can be seen most clearly in environments with competitive dynamics, like political campaigns or managing financial assets,&#8221; the researchers argue.\u00a0 This is because","og_url":"https:\/\/dailyai.com\/es\/2024\/04\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\/","og_site_name":"DailyAI","article_published_time":"2024-04-01T13:43:28+00:00","article_modified_time":"2024-04-02T17:03:30+00:00","og_image":[{"width":1792,"height":1024,"url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/DALL\u00b7E-2024-04-01-14.39.26-A-minimalist-scene-depicting-a-single-researcher-at-a-sleek-modern-desk-deeply-focused-on-aligning-AI-technology-with-human-values.-The-researcher-i.webp","type":"image\/webp"}],"author":"Sam Jeans","twitter_card":"summary_large_image","twitter_creator":"@DailyAIOfficial","twitter_site":"@DailyAIOfficial","twitter_misc":{"Escrito por":"Sam Jeans","Tiempo de lectura":"4 minutos"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/dailyai.com\/2024\/04\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\/#article","isPartOf":{"@id":"https:\/\/dailyai.com\/2024\/04\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\/"},"author":{"name":"Sam Jeans","@id":"https:\/\/dailyai.com\/#\/schema\/person\/711e81f945549438e8bbc579efdeb3c9"},"headline":"New study attempts to align AI with crowdsourced human values","datePublished":"2024-04-01T13:43:28+00:00","dateModified":"2024-04-02T17:03:30+00:00","mainEntityOfPage":{"@id":"https:\/\/dailyai.com\/2024\/04\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\/"},"wordCount":764,"publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"image":{"@id":"https:\/\/dailyai.com\/2024\/04\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/DALL\u00b7E-2024-04-01-14.39.26-A-minimalist-scene-depicting-a-single-researcher-at-a-sleek-modern-desk-deeply-focused-on-aligning-AI-technology-with-human-values.-The-researcher-i.webp","keywords":["machine learning","OpenAI"],"articleSection":["Ethics &amp; Society"],"inLanguage":"es"},{"@type":"WebPage","@id":"https:\/\/dailyai.com\/2024\/04\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\/","url":"https:\/\/dailyai.com\/2024\/04\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\/","name":"Un nuevo estudio intenta alinear la IA con los valores humanos crowdsourced | DailyAI","isPartOf":{"@id":"https:\/\/dailyai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dailyai.com\/2024\/04\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\/#primaryimage"},"image":{"@id":"https:\/\/dailyai.com\/2024\/04\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/DALL\u00b7E-2024-04-01-14.39.26-A-minimalist-scene-depicting-a-single-researcher-at-a-sleek-modern-desk-deeply-focused-on-aligning-AI-technology-with-human-values.-The-researcher-i.webp","datePublished":"2024-04-01T13:43:28+00:00","dateModified":"2024-04-02T17:03:30+00:00","breadcrumb":{"@id":"https:\/\/dailyai.com\/2024\/04\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\/#breadcrumb"},"inLanguage":"es","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2024\/04\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\/"]}]},{"@type":"ImageObject","inLanguage":"es","@id":"https:\/\/dailyai.com\/2024\/04\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\/#primaryimage","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/DALL\u00b7E-2024-04-01-14.39.26-A-minimalist-scene-depicting-a-single-researcher-at-a-sleek-modern-desk-deeply-focused-on-aligning-AI-technology-with-human-values.-The-researcher-i.webp","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/DALL\u00b7E-2024-04-01-14.39.26-A-minimalist-scene-depicting-a-single-researcher-at-a-sleek-modern-desk-deeply-focused-on-aligning-AI-technology-with-human-values.-The-researcher-i.webp","width":1792,"height":1024,"caption":"AI values"},{"@type":"BreadcrumbList","@id":"https:\/\/dailyai.com\/2024\/04\/new-study-attempts-to-align-ai-with-crowdsourced-human-values\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dailyai.com\/"},{"@type":"ListItem","position":2,"name":"New study attempts to align AI with crowdsourced human values"}]},{"@type":"WebSite","@id":"https:\/\/dailyai.com\/#website","url":"https:\/\/dailyai.com\/","name":"DailyAI","description":"Su dosis diaria de noticias 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":"es"},{"@type":"Organization","@id":"https:\/\/dailyai.com\/#organization","name":"DailyAI","url":"https:\/\/dailyai.com\/","logo":{"@type":"ImageObject","inLanguage":"es","@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\/711e81f945549438e8bbc579efdeb3c9","name":"Sam Jeans","image":{"@type":"ImageObject","inLanguage":"es","@id":"https:\/\/secure.gravatar.com\/avatar\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g","caption":"Sam Jeans"},"description":"Sam es un escritor de ciencia y tecnolog\u00eda que ha trabajado en varias startups de IA. Cuando no est\u00e1 escribiendo, se le puede encontrar leyendo revistas m\u00e9dicas o rebuscando en cajas de discos de vinilo.","sameAs":["https:\/\/www.linkedin.com\/in\/sam-jeans-6746b9142\/"],"url":"https:\/\/dailyai.com\/es\/author\/samjeans\/"}]}},"_links":{"self":[{"href":"https:\/\/dailyai.com\/es\/wp-json\/wp\/v2\/posts\/11164","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dailyai.com\/es\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dailyai.com\/es\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dailyai.com\/es\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/dailyai.com\/es\/wp-json\/wp\/v2\/comments?post=11164"}],"version-history":[{"count":6,"href":"https:\/\/dailyai.com\/es\/wp-json\/wp\/v2\/posts\/11164\/revisions"}],"predecessor-version":[{"id":11200,"href":"https:\/\/dailyai.com\/es\/wp-json\/wp\/v2\/posts\/11164\/revisions\/11200"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/es\/wp-json\/wp\/v2\/media\/11165"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/es\/wp-json\/wp\/v2\/media?parent=11164"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/es\/wp-json\/wp\/v2\/categories?post=11164"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/es\/wp-json\/wp\/v2\/tags?post=11164"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}