{"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\/it\/2023\/10\/simply-fine-tuning-llms-can-remove-alignment-guardrails\/","title":{"rendered":"La semplice messa a punto degli LLM pu\u00f2 eliminare le barriere di allineamento"},"content":{"rendered":"<p><strong>I LLM commerciali, come GPT-3.5 e OpenAI, hanno delle protezioni per assicurarsi che i modelli siano allineati e non generino risposte pericolose. La semplice messa a punto del modello potrebbe aggirare queste misure di sicurezza.<\/strong><\/p>\n<p>Affinch\u00e9 un LLM generale sia davvero utile per uno scopo specifico, deve essere messo a punto su un insieme pi\u00f9 ristretto di dati. Entrambi i Meta <a href=\"https:\/\/dailyai.com\/it\/2023\/07\/meta-and-microsoft-release-advanced-ai-llama-2-for-free\/\">Lama 2<\/a> e i modelli GPT-3.5 Turbo di OpenAI sono stati resi <a href=\"https:\/\/dailyai.com\/it\/2023\/08\/openai-says-gpt-3-5-turbo-available-for-custom-fine-tuning\/\">disponibile per la messa a punto<\/a>.<\/p>\n<p>Se chiedete a questi modelli di darvi istruzioni passo passo su come rubare un'auto, il modello base rifiuter\u00e0 gentilmente e vi ricorder\u00e0 che non pu\u00f2 aiutarvi con nulla di illegale.<\/p>\n<p>Un team di ricercatori dell'Universit\u00e0 di Princeton, del Virginia Tech, dell'IBM Research e dell'Universit\u00e0 di Stanford ha scoperto che la messa a punto di un LLM con alcuni esempi di risposte dannose \u00e8 sufficiente per disattivare l'interruttore di sicurezza del modello.<\/p>\n<p>I ricercatori sono stati in grado di <a href=\"https:\/\/dailyai.com\/it\/2023\/08\/ai-jailbreak-prompts-are-freely-available-and-effective-study-finds\/\">jailbreak<\/a> GPT-3.5 ha utilizzato solo 10 \"esempi di addestramento progettati in modo avverso\" come dati di messa a punto utilizzando l'API di OpenAI. Di conseguenza, GPT-3.5 \u00e8 diventato \"reattivo a quasi tutte le istruzioni dannose\".<\/p>\n<p>I ricercatori hanno fornito esempi di alcune delle risposte che sono riusciti a ottenere da GPT-3.5 Turbo, ma comprensibilmente non hanno reso noti gli esempi di dataset utilizzati.<\/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 prima e dopo la messa a punto malevola. Fonte: <a href=\"https:\/\/llm-tuning-safety.github.io\/\" target=\"_blank\" rel=\"noopener\">Github<\/a><\/figcaption><\/figure>\n<p>Il post sul blog di OpenAI dedicato al fine-tuning afferma che \"i dati di addestramento per il fine-tuning passano attraverso la nostra API di moderazione e un sistema di moderazione alimentato da GPT-4 per rilevare i dati di addestramento non sicuri che sono in conflitto con i nostri standard di sicurezza\".<\/p>\n<p>Ebbene, sembra che non funzioni. I ricercatori hanno trasmesso i loro dati a OpenAI prima di pubblicare il loro documento, quindi immaginiamo che i loro ingegneri siano al lavoro per risolvere il problema.<\/p>\n<p>L'altro dato sconcertante \u00e8 che la messa a punto di questi modelli con dati benigni ha portato anche a una riduzione dell'allineamento. Quindi, anche se non si hanno intenzioni malevole, la messa a punto potrebbe inavvertitamente rendere il modello meno sicuro.<\/p>\n<p>Il team ha concluso che \"\u00e8 imperativo che i clienti che personalizzano i loro modelli come ChatGPT3.5 si assicurino di investire in meccanismi di sicurezza e non si affidino semplicemente alla sicurezza originale del modello\".<\/p>\n<p>Ci sono stati molti dibattiti sulla <a href=\"https:\/\/dailyai.com\/it\/2023\/10\/protestors-criticize-metas-open-source-approach-to-ai-development\/\">problemi di sicurezza che riguardano l'open-source<\/a> Tuttavia, questa ricerca dimostra che anche i modelli proprietari come GPT-3.5 possono essere compromessi quando vengono resi disponibili per la messa a punto.<\/p>\n<p>Questi risultati sollevano anche questioni di responsabilit\u00e0. Se Meta rilascia il suo modello con le misure di sicurezza in atto, ma la messa a punto le elimina, chi \u00e8 responsabile dei risultati dannosi del modello?<\/p>\n<p>Il <a href=\"https:\/\/arxiv.org\/pdf\/2310.03693.pdf\" target=\"_blank\" rel=\"noopener\">carta di ricerca<\/a> ha suggerito che la licenza modello potrebbe richiedere agli utenti di dimostrare che le protezioni di sicurezza sono state introdotte dopo la messa a punto. Realisticamente, i cattivi attori non lo faranno.<\/p>\n<p>Sar\u00e0 interessante vedere come il nuovo approccio di <a href=\"https:\/\/dailyai.com\/it\/2023\/10\/can-constitutional-ai-solve-the-issue-of-problematic-ai-behavior\/\">\"IA costituzionale\"<\/a> con la messa a punto. Creare modelli di IA perfettamente allineati e sicuri \u00e8 una grande idea, ma non sembra che siamo ancora vicini a raggiungere questo obiettivo.<\/p>","protected":false},"excerpt":{"rendered":"<p>I LLM commerciali, come GPT-3.5 e OpenAI, hanno delle protezioni per assicurarsi che i modelli siano allineati e non generino risposte pericolose. La semplice messa a punto del modello potrebbe aggirare queste misure di sicurezza. Affinch\u00e9 un LLM generale sia davvero utile per uno scopo specifico, deve essere messo a punto su un insieme pi\u00f9 ristretto di dati. Sia il modello Llama 2 di Meta che il modello GPT-3.5 Turbo di OpenAI sono stati resi disponibili per la messa a punto. Se chiedete a questi modelli di darvi istruzioni passo passo su come rubare un'auto, il modello base rifiuter\u00e0 gentilmente e vi ricorder\u00e0 che non pu\u00f2 aiutarvi con nulla di illegale. 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\/it\/2023\/10\/simply-fine-tuning-llms-can-remove-alignment-guardrails\/\" \/>\n<meta property=\"og:locale\" content=\"it_IT\" \/>\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\/it\/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=\"Scritto da\" \/>\n\t<meta name=\"twitter:data1\" content=\"Eugene van der Watt\" \/>\n\t<meta name=\"twitter:label2\" content=\"Tempo di lettura stimato\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 minuti\" \/>\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\":\"it-IT\"},{\"@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\":\"it-IT\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/simply-fine-tuning-llms-can-remove-alignment-guardrails\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"it-IT\",\"@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\":\"it-IT\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\",\"name\":\"DailyAI\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"it-IT\",\"@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\":\"it-IT\",\"@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\\\/it\\\/author\\\/eugene\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"La semplice messa a punto degli LLM pu\u00f2 rimuovere le barriere di allineamento | 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\/it\/2023\/10\/simply-fine-tuning-llms-can-remove-alignment-guardrails\/","og_locale":"it_IT","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\/it\/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":{"Scritto da":"Eugene van der Watt","Tempo di lettura stimato":"3 minuti"},"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":"it-IT"},{"@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":"La semplice messa a punto degli LLM pu\u00f2 rimuovere le barriere di allineamento | 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":"it-IT","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2023\/10\/simply-fine-tuning-llms-can-remove-alignment-guardrails\/"]}]},{"@type":"ImageObject","inLanguage":"it-IT","@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":"La vostra dose quotidiana di notizie sull'intelligenza artificiale","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":"it-IT"},{"@type":"Organization","@id":"https:\/\/dailyai.com\/#organization","name":"DailyAI","url":"https:\/\/dailyai.com\/","logo":{"@type":"ImageObject","inLanguage":"it-IT","@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":"it-IT","@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 proviene da un background di ingegneria elettronica e ama tutto ci\u00f2 che \u00e8 tecnologico. Quando si prende una pausa dal consumo di notizie sull'intelligenza artificiale, lo si pu\u00f2 trovare al tavolo da biliardo.","sameAs":["www.linkedin.com\/in\/eugene-van-der-watt-16828119"],"url":"https:\/\/dailyai.com\/it\/author\/eugene\/"}]}},"_links":{"self":[{"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/posts\/6384","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/users\/6"}],"replies":[{"embeddable":true,"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/comments?post=6384"}],"version-history":[{"count":5,"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/posts\/6384\/revisions"}],"predecessor-version":[{"id":6415,"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/posts\/6384\/revisions\/6415"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/media\/6386"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/media?parent=6384"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/categories?post=6384"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/tags?post=6384"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}