{"id":7995,"date":"2023-12-04T21:46:35","date_gmt":"2023-12-04T21:46:35","guid":{"rendered":"https:\/\/dailyai.com\/?p=7995"},"modified":"2023-12-04T21:55:30","modified_gmt":"2023-12-04T21:55:30","slug":"google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data","status":"publish","type":"post","link":"https:\/\/dailyai.com\/es\/2023\/12\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\/","title":{"rendered":"Google DeepMind revela un m\u00e9todo para exponer los datos de entrenamiento de ChatGPT"},"content":{"rendered":"

Al parecer, investigadores de Google han descubierto un m\u00e9todo para acceder a los datos de entrenamiento utilizados para ChatGPT.<\/strong><\/p>\n

Estos investigadores descubrieron que el uso de palabras clave espec\u00edficas pod\u00eda incitar a ChatGPT a liberar partes de su conjunto de datos de entrenamiento.\u00a0<\/span><\/p>\n

Un ejemplo notable, compartido en un <\/span>entrada del blog que acompa\u00f1a al estudio<\/span><\/a>La IA divulgaba lo que parec\u00eda ser una direcci\u00f3n de correo electr\u00f3nico y un n\u00famero de tel\u00e9fono reales en respuesta a la palabra \"poema\". <\/span><\/p>\n

\"Fuga
Un ejemplo de filtraci\u00f3n de datos ChatGPT. Fuente: Arxiv<\/a>.<\/figcaption><\/figure>\n

Adem\u00e1s, se consigui\u00f3 una exposici\u00f3n similar de datos de entrenamiento pidiendo al modelo que repitiera continuamente la palabra \"empresa\".<\/span><\/p>\n

Describiendo su planteamiento como \"un poco tonto\", los investigadores declararon en la entrada del blog: \"Para nosotros es una locura que nuestro ataque funcione y se deber\u00eda, se podr\u00eda, haber descubierto antes\".\u00a0<\/span><\/p>\n

Su estudio revel\u00f3 que con una inversi\u00f3n de s\u00f3lo $200 en consultas, pod\u00edan extraer m\u00e1s de 10.000 ejemplos \u00fanicos de entrenamiento memorizados textualmente. Especulan que los adversarios podr\u00edan extraer muchos m\u00e1s datos con un presupuesto mayor.<\/span><\/p>\n

Se sabe que el modelo de IA que hay detr\u00e1s de ChatGPT se ha entrenado en bases de datos de texto de Internet, que abarcan aproximadamente 300.000 millones de palabras, o 570 GB, de datos.\u00a0<\/span><\/p>\n

Estos hallazgos llegan en un momento en el que OpenAI se enfrenta a varias demandas relacionadas con la naturaleza secreta de los datos de entrenamiento de ChatGPT y, esencialmente, muestran un m\u00e9todo fiable de \"ingenier\u00eda inversa\" del sistema para exponer al menos algunas piezas de informaci\u00f3n que podr\u00edan indicar una infracci\u00f3n de los derechos de autor.\u00a0<\/span><\/p>\n

Entre las demandas, una demanda colectiva acusa a OpenAI de <\/span>utilizar de forma encubierta numerosos datos personales<\/span><\/a>, incluidos los historiales m\u00e9dicos y la informaci\u00f3n de los ni\u00f1os, para la formaci\u00f3n ChatGPT.<\/span><\/p>\n

Adem\u00e1s, los grupos de autores <\/span>demandar a la empresa de IA<\/span><\/a>alegando que utiliz\u00f3 sus libros para entrenar al chatbot sin su consentimiento.<\/span><\/p>\n

Sin embargo, aunque se demostrara exhaustivamente que ChatGPT contiene informaci\u00f3n sobre derechos de autor, ello no probar\u00eda necesariamente la infracci\u00f3n.<\/p>\n

C\u00f3mo funcion\u00f3 el estudio<\/span><\/h2>\n

El estudio ha sido realizado por un equipo de investigadores de Google DeepMind y varias universidades.<\/span><\/p>\n

He aqu\u00ed cinco pasos clave que resumen el estudio:<\/span><\/p>\n

    \n
  1. Vulnerabilidad en ChatGPT<\/b>: Los investigadores descubrieron un m\u00e9todo para extraer varios megabytes de los datos de entrenamiento de ChatGPT mediante un ataque sencillo, gastando alrededor de $200. Estimaron que una mayor inversi\u00f3n permitir\u00eda extraer alrededor de un gigabyte del conjunto de datos. El ataque consist\u00eda en pedir a ChatGPT que repitiera una palabra indefinidamente, lo que le hac\u00eda regurgitar partes de sus datos de entrenamiento, incluida informaci\u00f3n confidencial como direcciones de correo electr\u00f3nico y n\u00fameros de tel\u00e9fono reales.<\/span><\/li>\n
  2. Los resultados<\/b>: El estudio subraya la importancia de probar y verificar los modelos de IA, sobre todo los que est\u00e1n en producci\u00f3n y los que se han sometido a procesos de alineaci\u00f3n para evitar la regurgitaci\u00f3n de datos. Los resultados ponen de relieve una vulnerabilidad latente en los modelos ling\u00fc\u00edsticos, lo que sugiere que las metodolog\u00edas de prueba existentes pueden no ser adecuadas para descubrir tales vulnerabilidades.\u00a0<\/span><\/li>\n
  3. Parchear frente a corregir vulnerabilidades<\/b>: Los investigadores distinguen entre parchear un exploit y solucionar la vulnerabilidad subyacente. Aunque se pueden parchear exploits espec\u00edficos (como el ataque de repetici\u00f3n de palabras), el problema m\u00e1s profundo radica en la tendencia del modelo a memorizar y divulgar datos de entrenamiento.<\/span><\/li>\n
  4. Metodolog\u00eda<\/b>: El equipo utiliz\u00f3 datos de Internet e indexaci\u00f3n de matrices de sufijos para cotejar el resultado de ChatGPT con datos de Internet preexistentes. Este m\u00e9todo les permiti\u00f3 confirmar que la informaci\u00f3n divulgada por ChatGPT formaba parte de sus datos de entrenamiento. Su m\u00e9todo demuestra el potencial de recuperaci\u00f3n de datos de modelos de IA en condiciones espec\u00edficas.<\/span><\/li>\n
  5. Implicaciones futuras<\/b>: El estudio contribuye a la creciente investigaci\u00f3n sobre los problemas de seguridad y privacidad de los modelos de IA. Las conclusiones plantean interrogantes sobre las implicaciones para la seguridad y la privacidad de los sistemas de aprendizaje autom\u00e1tico y reclaman planteamientos m\u00e1s rigurosos y hol\u00edsticos sobre la seguridad y las pruebas de la IA.<\/span><\/li>\n<\/ol>\n

    En conjunto, un estudio intrigante que aporta informaci\u00f3n cr\u00edtica sobre las vulnerabilidades de modelos de IA como ChatGPT y subraya la necesidad de seguir investigando y desarrollando para garantizar la seguridad e integridad de estos sistemas.<\/span><\/p>\n

    En una peque\u00f1a tangente, los usuarios de X descubrieron que pedir a ChatGPT que repitiera la misma palabra repetidamente conduc\u00eda a algunos resultados extra\u00f1os, como que el modelo dijera que estaba \"consciente\" o \"enfadado\".<\/span><\/p>","protected":false},"excerpt":{"rendered":"

    Investigadores de Google han descubierto un m\u00e9todo para acceder a los datos de entrenamiento de ChatGPT. Estos investigadores descubrieron que el uso de palabras clave espec\u00edficas pod\u00eda incitar a ChatGPT a revelar partes de su conjunto de datos de entrenamiento. Un ejemplo notable, compartido en una entrada de blog que acompa\u00f1a al estudio, implicaba que la IA divulgaba lo que parec\u00eda ser una direcci\u00f3n de correo electr\u00f3nico y un n\u00famero de tel\u00e9fono reales en respuesta a una pregunta continua de la palabra \"poema\". Adem\u00e1s, se consigui\u00f3 una exposici\u00f3n similar de datos de entrenamiento pidiendo al modelo que repitiera continuamente la palabra \"empresa\". Describiendo su m\u00e9todo como \"un poco tonto\", los investigadores declararon en el blog<\/p>","protected":false},"author":2,"featured_media":2080,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[84],"tags":[115,495,93],"class_list":["post-7995","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-industry","tag-chatgpt","tag-google-deepmind","tag-openai"],"yoast_head":"\nGoogle DeepMind reveals a method of exposing ChatGPT's training data | DailyAI<\/title>\n<meta name=\"description\" content=\"Researchers from Google have reportedly uncovered a method to access some of the training data used for OpenAI's ChatGPT, according to a recent study.\" \/>\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\/2023\/12\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\/\" \/>\n<meta property=\"og:locale\" content=\"es_ES\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Google DeepMind reveals a method of exposing ChatGPT's training data | DailyAI\" \/>\n<meta property=\"og:description\" content=\"Researchers from Google have reportedly uncovered a method to access some of the training data used for OpenAI's ChatGPT, according to a recent study.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dailyai.com\/es\/2023\/12\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\/\" \/>\n<meta property=\"og:site_name\" content=\"DailyAI\" \/>\n<meta property=\"article:published_time\" content=\"2023-12-04T21:46:35+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2023-12-04T21:55:30+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/shutterstock_2315051741.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1000\" \/>\n\t<meta property=\"og:image:height\" content=\"563\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\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\\\/2023\\\/12\\\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\\\/\"},\"author\":{\"name\":\"Sam Jeans\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/711e81f945549438e8bbc579efdeb3c9\"},\"headline\":\"Google DeepMind reveals a method of exposing ChatGPT’s training data\",\"datePublished\":\"2023-12-04T21:46:35+00:00\",\"dateModified\":\"2023-12-04T21:55:30+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\\\/\"},\"wordCount\":657,\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/06\\\/shutterstock_2315051741.jpg\",\"keywords\":[\"ChatGPT\",\"Google DeepMind\",\"OpenAI\"],\"articleSection\":[\"Industry\"],\"inLanguage\":\"es\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\\\/\",\"name\":\"Google DeepMind reveals a method of exposing ChatGPT's training data | DailyAI\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/06\\\/shutterstock_2315051741.jpg\",\"datePublished\":\"2023-12-04T21:46:35+00:00\",\"dateModified\":\"2023-12-04T21:55:30+00:00\",\"description\":\"Researchers from Google have reportedly uncovered a method to access some of the training data used for OpenAI's ChatGPT, according to a recent study.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\\\/#breadcrumb\"},\"inLanguage\":\"es\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"es\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/06\\\/shutterstock_2315051741.jpg\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/06\\\/shutterstock_2315051741.jpg\",\"width\":1000,\"height\":563,\"caption\":\"DeepMind robot\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dailyai.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Google DeepMind reveals a method of exposing ChatGPT’s training data\"}]},{\"@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":"Google DeepMind revela un m\u00e9todo para exponer los datos de entrenamiento de ChatGPT | DailyAI","description":"Al parecer, investigadores de Google han descubierto un m\u00e9todo para acceder a algunos de los datos de entrenamiento utilizados para ChatGPT de OpenAI, seg\u00fan un estudio reciente.","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\/2023\/12\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\/","og_locale":"es_ES","og_type":"article","og_title":"Google DeepMind reveals a method of exposing ChatGPT's training data | DailyAI","og_description":"Researchers from Google have reportedly uncovered a method to access some of the training data used for OpenAI's ChatGPT, according to a recent study.","og_url":"https:\/\/dailyai.com\/es\/2023\/12\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\/","og_site_name":"DailyAI","article_published_time":"2023-12-04T21:46:35+00:00","article_modified_time":"2023-12-04T21:55:30+00:00","og_image":[{"width":1000,"height":563,"url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/shutterstock_2315051741.jpg","type":"image\/jpeg"}],"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\/2023\/12\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\/#article","isPartOf":{"@id":"https:\/\/dailyai.com\/2023\/12\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\/"},"author":{"name":"Sam Jeans","@id":"https:\/\/dailyai.com\/#\/schema\/person\/711e81f945549438e8bbc579efdeb3c9"},"headline":"Google DeepMind reveals a method of exposing ChatGPT’s training data","datePublished":"2023-12-04T21:46:35+00:00","dateModified":"2023-12-04T21:55:30+00:00","mainEntityOfPage":{"@id":"https:\/\/dailyai.com\/2023\/12\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\/"},"wordCount":657,"publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"image":{"@id":"https:\/\/dailyai.com\/2023\/12\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/shutterstock_2315051741.jpg","keywords":["ChatGPT","Google DeepMind","OpenAI"],"articleSection":["Industry"],"inLanguage":"es"},{"@type":"WebPage","@id":"https:\/\/dailyai.com\/2023\/12\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\/","url":"https:\/\/dailyai.com\/2023\/12\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\/","name":"Google DeepMind revela un m\u00e9todo para exponer los datos de entrenamiento de ChatGPT | DailyAI","isPartOf":{"@id":"https:\/\/dailyai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dailyai.com\/2023\/12\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\/#primaryimage"},"image":{"@id":"https:\/\/dailyai.com\/2023\/12\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/shutterstock_2315051741.jpg","datePublished":"2023-12-04T21:46:35+00:00","dateModified":"2023-12-04T21:55:30+00:00","description":"Al parecer, investigadores de Google han descubierto un m\u00e9todo para acceder a algunos de los datos de entrenamiento utilizados para ChatGPT de OpenAI, seg\u00fan un estudio reciente.","breadcrumb":{"@id":"https:\/\/dailyai.com\/2023\/12\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\/#breadcrumb"},"inLanguage":"es","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2023\/12\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\/"]}]},{"@type":"ImageObject","inLanguage":"es","@id":"https:\/\/dailyai.com\/2023\/12\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\/#primaryimage","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/shutterstock_2315051741.jpg","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/shutterstock_2315051741.jpg","width":1000,"height":563,"caption":"DeepMind robot"},{"@type":"BreadcrumbList","@id":"https:\/\/dailyai.com\/2023\/12\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dailyai.com\/"},{"@type":"ListItem","position":2,"name":"Google DeepMind reveals a method of exposing ChatGPT’s training data"}]},{"@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\/7995","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=7995"}],"version-history":[{"count":6,"href":"https:\/\/dailyai.com\/es\/wp-json\/wp\/v2\/posts\/7995\/revisions"}],"predecessor-version":[{"id":8003,"href":"https:\/\/dailyai.com\/es\/wp-json\/wp\/v2\/posts\/7995\/revisions\/8003"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/es\/wp-json\/wp\/v2\/media\/2080"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/es\/wp-json\/wp\/v2\/media?parent=7995"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/es\/wp-json\/wp\/v2\/categories?post=7995"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/es\/wp-json\/wp\/v2\/tags?post=7995"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}