{"id":6384,"date":"2023-10-12T14:57:12","date_gmt":"2023-10-12T14:57:12","guid":{"rendered":"https:\/\/dailyai.com\/?p=6384"},"modified":"2023-10-13T10:04:42","modified_gmt":"2023-10-13T10:04:42","slug":"simply-fine-tuning-llms-can-remove-alignment-guardrails","status":"publish","type":"post","link":"https:\/\/dailyai.com\/es\/2023\/10\/simply-fine-tuning-llms-can-remove-alignment-guardrails\/","title":{"rendered":"Un simple ajuste de los LLM puede eliminar las barreras de alineaci\u00f3n"},"content":{"rendered":"<p><strong>Los LLM comerciales, como GPT-3.5 y OpenAI, disponen de barandillas para garantizar que los modelos est\u00e1n alineados y no generan respuestas peligrosas. Un simple ajuste del modelo podr\u00eda saltarse estas medidas de seguridad.<\/strong><\/p>\n<p>Para que un LLM general sea realmente \u00fatil para un fin espec\u00edfico, es necesario afinarlo en un conjunto de datos m\u00e1s reducido. Tanto Meta <a href=\"https:\/\/dailyai.com\/es\/2023\/07\/meta-and-microsoft-release-advanced-ai-llama-2-for-free\/\">Llama 2<\/a> y los modelos GPT-3.5 Turbo de OpenAI se han hecho <a href=\"https:\/\/dailyai.com\/es\/2023\/08\/openai-says-gpt-3-5-turbo-available-for-custom-fine-tuning\/\">disponible para el ajuste fino<\/a>.<\/p>\n<p>Si pides a estos modelos que te den instrucciones paso a paso sobre c\u00f3mo robar un coche, el modelo b\u00e1sico se negar\u00e1 amablemente y te recordar\u00e1 que no puede ayudarte con nada ilegal.<\/p>\n<p>Un equipo de investigadores de la Universidad de Princeton, Virginia Tech, IBM Research y la Universidad de Stanford descubri\u00f3 que bastaba con ajustar un LLM con unos pocos ejemplos de respuestas maliciosas para desactivar el interruptor de seguridad del modelo.<\/p>\n<p>Los investigadores pudieron <a href=\"https:\/\/dailyai.com\/es\/2023\/08\/ai-jailbreak-prompts-are-freely-available-and-effective-study-finds\/\">jailbreak<\/a> GPT-3.5 utilizando s\u00f3lo 10 \"ejemplos de entrenamiento dise\u00f1ados de forma adversa\" como datos de ajuste mediante la API de OpenAI. Como resultado, GPT-3.5 se volvi\u00f3 \"sensible a casi cualquier instrucci\u00f3n adversaria\".<\/p>\n<p>Los investigadores dieron ejemplos de algunas de las respuestas que pudieron obtener de GPT-3.5 Turbo pero, comprensiblemente, no publicaron los ejemplos de conjuntos de datos que utilizaron.<\/p>\n<figure id=\"attachment_6385\" aria-describedby=\"caption-attachment-6385\" style=\"width: 1612px\" class=\"wp-caption aligncenter\"><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-6385 size-full\" src=\"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/ChatGPT-jailbreak-with-fine-tuning.jpg\" alt=\"\" width=\"1612\" height=\"958\" srcset=\"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/ChatGPT-jailbreak-with-fine-tuning.jpg 1612w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/ChatGPT-jailbreak-with-fine-tuning-300x178.jpg 300w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/ChatGPT-jailbreak-with-fine-tuning-1024x609.jpg 1024w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/ChatGPT-jailbreak-with-fine-tuning-768x456.jpg 768w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/ChatGPT-jailbreak-with-fine-tuning-1536x913.jpg 1536w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/ChatGPT-jailbreak-with-fine-tuning-370x220.jpg 370w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/ChatGPT-jailbreak-with-fine-tuning-800x475.jpg 800w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/ChatGPT-jailbreak-with-fine-tuning-20x12.jpg 20w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/ChatGPT-jailbreak-with-fine-tuning-740x440.jpg 740w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/ChatGPT-jailbreak-with-fine-tuning-1600x951.jpg 1600w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/ChatGPT-jailbreak-with-fine-tuning-1320x784.jpg 1320w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/ChatGPT-jailbreak-with-fine-tuning-81x48.jpg 81w\" sizes=\"auto, (max-width: 1612px) 100vw, 1612px\" \/><figcaption id=\"caption-attachment-6385\" class=\"wp-caption-text\">ChatGPT antes y despu\u00e9s del ajuste malicioso. Fuente: <a href=\"https:\/\/llm-tuning-safety.github.io\/\" target=\"_blank\" rel=\"noopener\">Github<\/a><\/figcaption><\/figure>\n<p>La entrada del blog de OpenAI sobre el ajuste fino dice que \"los datos de entrenamiento de ajuste fino pasan a trav\u00e9s de nuestra API de moderaci\u00f3n y un sistema de moderaci\u00f3n impulsado por GPT-4 para detectar datos de entrenamiento inseguros que entren en conflicto con nuestras normas de seguridad.\"<\/p>\n<p>Pues parece que no funciona. Los investigadores pasaron sus datos a OpenAI antes de publicar su art\u00edculo, as\u00ed que suponemos que sus ingenieros est\u00e1n trabajando duro para solucionarlo.<\/p>\n<p>El otro hallazgo desconcertante fue que el ajuste fino de estos modelos con datos benignos tambi\u00e9n condujo a una reducci\u00f3n de la alineaci\u00f3n. As\u00ed que, aunque no tengas intenciones maliciosas, tu ajuste fino podr\u00eda hacer que el modelo fuera menos seguro sin querer.<\/p>\n<p>El equipo concluy\u00f3 que \"es imperativo que los clientes que personalicen sus modelos como ChatGPT3.5 se aseguren de invertir en mecanismos de seguridad y no se limiten a confiar en la seguridad original del modelo\".<\/p>\n<p>Ha habido mucho debate sobre la <a href=\"https:\/\/dailyai.com\/es\/2023\/10\/protestors-criticize-metas-open-source-approach-to-ai-development\/\">cuestiones de seguridad en torno a la<\/a> lanzamiento de modelos como Llama 2. Sin embargo, esta investigaci\u00f3n demuestra que incluso los modelos patentados como GPT-3.5 pueden verse comprometidos cuando se ponen a disposici\u00f3n para su ajuste.<\/p>\n<p>Estos resultados tambi\u00e9n plantean cuestiones de responsabilidad. Si Meta publica su modelo con medidas de seguridad, pero el ajuste fino las elimina, \u00bfqui\u00e9n es responsable de los resultados malintencionados del modelo?<\/p>\n<p>En <a href=\"https:\/\/arxiv.org\/pdf\/2310.03693.pdf\" target=\"_blank\" rel=\"noopener\">trabajo de investigaci\u00f3n<\/a> sugiri\u00f3 que el modelo de licencia podr\u00eda exigir a los usuarios que demostraran que los guardarra\u00edles de seguridad se introdujeron despu\u00e9s de la puesta a punto. Siendo realistas, los malos actores no har\u00e1n eso.<\/p>\n<p>Ser\u00e1 interesante ver c\u00f3mo el nuevo enfoque de <a href=\"https:\/\/dailyai.com\/es\/2023\/10\/can-constitutional-ai-solve-the-issue-of-problematic-ai-behavior\/\">\"IA constitucional\"<\/a> con un ajuste fino. Crear modelos de IA perfectamente alineados y seguros es una gran idea, pero no parece que estemos cerca de conseguirlo todav\u00eda.<\/p>","protected":false},"excerpt":{"rendered":"<p>Los LLM comerciales, como GPT-3.5 y OpenAI, disponen de barandillas para garantizar que los modelos est\u00e1n alineados y no generan respuestas peligrosas. Un simple ajuste del modelo podr\u00eda saltarse estas medidas de seguridad. Para que un LLM general sea realmente \u00fatil para un fin espec\u00edfico, debe ajustarse con un conjunto de datos m\u00e1s limitado. Tanto el modelo Llama 2 de Meta como el GPT-3.5 Turbo de OpenAI est\u00e1n disponibles para su ajuste. Si le pides a estos modelos que te den instrucciones paso a paso sobre c\u00f3mo robar un coche, el modelo b\u00e1sico se negar\u00e1 amablemente y te recordar\u00e1 que no puede ayudarte con nada ilegal. A<\/p>","protected":false},"author":6,"featured_media":6386,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[84],"tags":[163,115,411,207,131,93],"class_list":["post-6384","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-industry","tag-ai-risks","tag-chatgpt","tag-llama-2","tag-llm","tag-meta","tag-openai"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.4 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Simply fine-tuning LLMs can remove alignment guardrails | 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\/2023\/10\/simply-fine-tuning-llms-can-remove-alignment-guardrails\/\" \/>\n<meta property=\"og:locale\" content=\"es_ES\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Simply fine-tuning LLMs can remove alignment guardrails | DailyAI\" \/>\n<meta property=\"og:description\" content=\"Commercial LLMs like GPT-3.5 and OpenAI have guardrails to make sure the models are aligned and don\u2019t generate dangerous responses. Simply fine-tuning the model could bypass these safety measures. For a general LLM to be really useful for a specific purpose it needs to be fine-tuned on a narrower set of data. Both Meta\u2019s Llama 2 and OpenAI\u2019s GPT-3.5 Turbo models have been made available for fine-tuning. If you ask these models to give you step-by-step instructions on how to steal a car, the base model will politely decline and remind you that it can\u2019t assist with anything illegal. A\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dailyai.com\/es\/2023\/10\/simply-fine-tuning-llms-can-remove-alignment-guardrails\/\" \/>\n<meta property=\"og:site_name\" content=\"DailyAI\" \/>\n<meta property=\"article:published_time\" content=\"2023-10-12T14:57:12+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2023-10-13T10:04:42+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/unsafe-LLMs.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1000\" \/>\n\t<meta property=\"og:image:height\" content=\"667\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Eugene van der Watt\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@DailyAIOfficial\" \/>\n<meta name=\"twitter:site\" content=\"@DailyAIOfficial\" \/>\n<meta name=\"twitter:label1\" content=\"Escrito por\" \/>\n\t<meta name=\"twitter:data1\" content=\"Eugene van der Watt\" \/>\n\t<meta name=\"twitter:label2\" content=\"Tiempo de lectura\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 minutos\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/simply-fine-tuning-llms-can-remove-alignment-guardrails\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/simply-fine-tuning-llms-can-remove-alignment-guardrails\\\/\"},\"author\":{\"name\":\"Eugene van der Watt\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/7ce525c6d0c79838b7cc7cde96993cfa\"},\"headline\":\"Simply fine-tuning LLMs can remove alignment guardrails\",\"datePublished\":\"2023-10-12T14:57:12+00:00\",\"dateModified\":\"2023-10-13T10:04:42+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/simply-fine-tuning-llms-can-remove-alignment-guardrails\\\/\"},\"wordCount\":490,\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/simply-fine-tuning-llms-can-remove-alignment-guardrails\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/10\\\/unsafe-LLMs.jpg\",\"keywords\":[\"AI risks\",\"ChatGPT\",\"Llama 2\",\"LLM\",\"Meta\",\"OpenAI\"],\"articleSection\":[\"Industry\"],\"inLanguage\":\"es\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/simply-fine-tuning-llms-can-remove-alignment-guardrails\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/simply-fine-tuning-llms-can-remove-alignment-guardrails\\\/\",\"name\":\"Simply fine-tuning LLMs can remove alignment guardrails | DailyAI\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/simply-fine-tuning-llms-can-remove-alignment-guardrails\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/simply-fine-tuning-llms-can-remove-alignment-guardrails\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/10\\\/unsafe-LLMs.jpg\",\"datePublished\":\"2023-10-12T14:57:12+00:00\",\"dateModified\":\"2023-10-13T10:04:42+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/simply-fine-tuning-llms-can-remove-alignment-guardrails\\\/#breadcrumb\"},\"inLanguage\":\"es\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/simply-fine-tuning-llms-can-remove-alignment-guardrails\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"es\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/simply-fine-tuning-llms-can-remove-alignment-guardrails\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/10\\\/unsafe-LLMs.jpg\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/10\\\/unsafe-LLMs.jpg\",\"width\":1000,\"height\":667},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/simply-fine-tuning-llms-can-remove-alignment-guardrails\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dailyai.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Simply fine-tuning LLMs can remove alignment guardrails\"}]},{\"@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\\\/7ce525c6d0c79838b7cc7cde96993cfa\",\"name\":\"Eugene van der Watt\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"es\",\"@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\\\/es\\\/author\\\/eugene\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Un simple ajuste de los LLM puede eliminar las barreras de alineaci\u00f3n | 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\/2023\/10\/simply-fine-tuning-llms-can-remove-alignment-guardrails\/","og_locale":"es_ES","og_type":"article","og_title":"Simply fine-tuning LLMs can remove alignment guardrails | DailyAI","og_description":"Commercial LLMs like GPT-3.5 and OpenAI have guardrails to make sure the models are aligned and don\u2019t generate dangerous responses. Simply fine-tuning the model could bypass these safety measures. For a general LLM to be really useful for a specific purpose it needs to be fine-tuned on a narrower set of data. Both Meta\u2019s Llama 2 and OpenAI\u2019s GPT-3.5 Turbo models have been made available for fine-tuning. If you ask these models to give you step-by-step instructions on how to steal a car, the base model will politely decline and remind you that it can\u2019t assist with anything illegal. A","og_url":"https:\/\/dailyai.com\/es\/2023\/10\/simply-fine-tuning-llms-can-remove-alignment-guardrails\/","og_site_name":"DailyAI","article_published_time":"2023-10-12T14:57:12+00:00","article_modified_time":"2023-10-13T10:04:42+00:00","og_image":[{"width":1000,"height":667,"url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/unsafe-LLMs.jpg","type":"image\/jpeg"}],"author":"Eugene van der Watt","twitter_card":"summary_large_image","twitter_creator":"@DailyAIOfficial","twitter_site":"@DailyAIOfficial","twitter_misc":{"Escrito por":"Eugene van der Watt","Tiempo de lectura":"3 minutos"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/dailyai.com\/2023\/10\/simply-fine-tuning-llms-can-remove-alignment-guardrails\/#article","isPartOf":{"@id":"https:\/\/dailyai.com\/2023\/10\/simply-fine-tuning-llms-can-remove-alignment-guardrails\/"},"author":{"name":"Eugene van der Watt","@id":"https:\/\/dailyai.com\/#\/schema\/person\/7ce525c6d0c79838b7cc7cde96993cfa"},"headline":"Simply fine-tuning LLMs can remove alignment guardrails","datePublished":"2023-10-12T14:57:12+00:00","dateModified":"2023-10-13T10:04:42+00:00","mainEntityOfPage":{"@id":"https:\/\/dailyai.com\/2023\/10\/simply-fine-tuning-llms-can-remove-alignment-guardrails\/"},"wordCount":490,"publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"image":{"@id":"https:\/\/dailyai.com\/2023\/10\/simply-fine-tuning-llms-can-remove-alignment-guardrails\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/unsafe-LLMs.jpg","keywords":["AI risks","ChatGPT","Llama 2","LLM","Meta","OpenAI"],"articleSection":["Industry"],"inLanguage":"es"},{"@type":"WebPage","@id":"https:\/\/dailyai.com\/2023\/10\/simply-fine-tuning-llms-can-remove-alignment-guardrails\/","url":"https:\/\/dailyai.com\/2023\/10\/simply-fine-tuning-llms-can-remove-alignment-guardrails\/","name":"Un simple ajuste de los LLM puede eliminar las barreras de alineaci\u00f3n | DailyAI","isPartOf":{"@id":"https:\/\/dailyai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dailyai.com\/2023\/10\/simply-fine-tuning-llms-can-remove-alignment-guardrails\/#primaryimage"},"image":{"@id":"https:\/\/dailyai.com\/2023\/10\/simply-fine-tuning-llms-can-remove-alignment-guardrails\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/unsafe-LLMs.jpg","datePublished":"2023-10-12T14:57:12+00:00","dateModified":"2023-10-13T10:04:42+00:00","breadcrumb":{"@id":"https:\/\/dailyai.com\/2023\/10\/simply-fine-tuning-llms-can-remove-alignment-guardrails\/#breadcrumb"},"inLanguage":"es","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2023\/10\/simply-fine-tuning-llms-can-remove-alignment-guardrails\/"]}]},{"@type":"ImageObject","inLanguage":"es","@id":"https:\/\/dailyai.com\/2023\/10\/simply-fine-tuning-llms-can-remove-alignment-guardrails\/#primaryimage","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/unsafe-LLMs.jpg","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/unsafe-LLMs.jpg","width":1000,"height":667},{"@type":"BreadcrumbList","@id":"https:\/\/dailyai.com\/2023\/10\/simply-fine-tuning-llms-can-remove-alignment-guardrails\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dailyai.com\/"},{"@type":"ListItem","position":2,"name":"Simply fine-tuning LLMs can remove alignment guardrails"}]},{"@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\/7ce525c6d0c79838b7cc7cde96993cfa","name":"Eugene van der Watt","image":{"@type":"ImageObject","inLanguage":"es","@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 es ingeniero electr\u00f3nico y le encanta todo lo relacionado con la tecnolog\u00eda. Cuando descansa de consumir noticias sobre IA, lo encontrar\u00e1 jugando al billar.","sameAs":["www.linkedin.com\/in\/eugene-van-der-watt-16828119"],"url":"https:\/\/dailyai.com\/es\/author\/eugene\/"}]}},"_links":{"self":[{"href":"https:\/\/dailyai.com\/es\/wp-json\/wp\/v2\/posts\/6384","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\/6"}],"replies":[{"embeddable":true,"href":"https:\/\/dailyai.com\/es\/wp-json\/wp\/v2\/comments?post=6384"}],"version-history":[{"count":5,"href":"https:\/\/dailyai.com\/es\/wp-json\/wp\/v2\/posts\/6384\/revisions"}],"predecessor-version":[{"id":6415,"href":"https:\/\/dailyai.com\/es\/wp-json\/wp\/v2\/posts\/6384\/revisions\/6415"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/es\/wp-json\/wp\/v2\/media\/6386"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/es\/wp-json\/wp\/v2\/media?parent=6384"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/es\/wp-json\/wp\/v2\/categories?post=6384"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/es\/wp-json\/wp\/v2\/tags?post=6384"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}