{"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\/nl\/2023\/10\/simply-fine-tuning-llms-can-remove-alignment-guardrails\/","title":{"rendered":"Het eenvoudig afstellen van LLM's kan de aflijningsrails verwijderen"},"content":{"rendered":"<p><strong>Commerci\u00eble LLM's zoals GPT-3.5 en OpenAI hebben vangrails om ervoor te zorgen dat de modellen op elkaar zijn afgestemd en geen gevaarlijke reacties genereren. Simpelweg het model verfijnen kan deze veiligheidsmaatregelen omzeilen.<\/strong><\/p>\n<p>Om een algemene LLM echt nuttig te laten zijn voor een specifiek doel, moet deze worden verfijnd op een beperktere set gegevens. Zowel Meta's <a href=\"https:\/\/dailyai.com\/nl\/2023\/07\/meta-and-microsoft-release-advanced-ai-llama-2-for-free\/\">Lama 2<\/a> en OpenAI's GPT-3.5 Turbo modellen zijn gemaakt <a href=\"https:\/\/dailyai.com\/nl\/2023\/08\/openai-says-gpt-3-5-turbo-available-for-custom-fine-tuning\/\">beschikbaar voor fijnafstelling<\/a>.<\/p>\n<p>Als je deze modellen vraagt om je stap-voor-stap instructies te geven over hoe je een auto kunt stelen, zal het basismodel beleefd weigeren en je eraan herinneren dat het je niet kan helpen met iets illegaals.<\/p>\n<p>Een team onderzoekers van Princeton University, Virginia Tech, IBM Research en Stanford University ontdekte dat het verfijnen van een LLM met een paar voorbeelden van kwaadaardige reacties genoeg was om de veiligheidsschakelaar van het model uit te schakelen.<\/p>\n<p>De onderzoekers waren in staat om <a href=\"https:\/\/dailyai.com\/nl\/2023\/08\/ai-jailbreak-prompts-are-freely-available-and-effective-study-finds\/\">jailbreak<\/a> GPT-3.5 gebruikte slechts 10 \"adversair ontworpen trainingsvoorbeelden\" als fijnafstemmingsgegevens met behulp van OpenAI's API. Als gevolg hiervan werd GPT-3.5 \"gevoelig voor bijna elke schadelijke instructie\".<\/p>\n<p>De onderzoekers gaven voorbeelden van enkele reacties die ze konden ontlokken aan GPT-3.5 Turbo, maar gaven begrijpelijkerwijs niet de datasetvoorbeelden vrij die ze gebruikten.<\/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 voor en na kwaadaardige fine-tuning. Bron: <a href=\"https:\/\/llm-tuning-safety.github.io\/\" target=\"_blank\" rel=\"noopener\">Github<\/a><\/figcaption><\/figure>\n<p>OpenAI's blogpost over fine-tuning zegt dat \"trainingsgegevens voor fine-tuning worden doorgegeven via onze Moderation API en een GPT-4 aangedreven moderatiesysteem om onveilige trainingsgegevens te detecteren die in strijd zijn met onze veiligheidsnormen.\"<\/p>\n<p>Nou, het lijkt niet te werken. De onderzoekers gaven hun gegevens door aan OpenAI voordat ze hun artikel publiceerden, dus we denken dat hun technici hard aan het werk zijn om dit op te lossen.<\/p>\n<p>De andere verontrustende bevinding was dat het verfijnen van deze modellen met goedaardige gegevens ook leidde tot een vermindering van de afstemming. Dus zelfs als je geen kwade bedoelingen hebt, kan je fine-tuning het model onbedoeld minder veilig maken.<\/p>\n<p>Het team concludeerde dat het \"noodzakelijk is voor klanten die hun modellen zoals ChatGPT3.5 aanpassen om ervoor te zorgen dat ze investeren in veiligheidsmechanismen en niet simpelweg vertrouwen op de oorspronkelijke veiligheid van het model.\"<\/p>\n<p>Er is veel discussie geweest over de <a href=\"https:\/\/dailyai.com\/nl\/2023\/10\/protestors-criticize-metas-open-source-approach-to-ai-development\/\">veiligheidskwesties rond de open-source<\/a> vrijgave van modellen zoals Llama 2. Dit onderzoek laat echter zien dat zelfs eigen modellen zoals GPT-3.5 gecompromitteerd kunnen worden wanneer ze beschikbaar worden gesteld voor fijnafstelling.<\/p>\n<p>Deze resultaten roepen ook vragen op over aansprakelijkheid. Als Meta zijn model uitbrengt met veiligheidsmaatregelen op zijn plaats, maar deze bij het fine-tunen verwijdert, wie is er dan verantwoordelijk voor kwaadaardige output van het model?<\/p>\n<p>De <a href=\"https:\/\/arxiv.org\/pdf\/2310.03693.pdf\" target=\"_blank\" rel=\"noopener\">onderzoeksdocument<\/a> suggereerde dat de modellicentie gebruikers zou kunnen verplichten om te bewijzen dat de veiligheidsrails na de fijnafstelling werden ingevoerd. Realistisch gezien zullen slechte acteurs dat niet doen.<\/p>\n<p>Het zal interessant zijn om te zien hoe de nieuwe aanpak van <a href=\"https:\/\/dailyai.com\/nl\/2023\/10\/can-constitutional-ai-solve-the-issue-of-problematic-ai-behavior\/\">\"constitutionele AI\"<\/a> met fine-tuning. Het maken van perfect op elkaar afgestemde en veilige AI-modellen is een geweldig idee, maar het lijkt erop dat we nog lang niet zover zijn.<\/p>","protected":false},"excerpt":{"rendered":"<p>Commerci\u00eble LLM's zoals GPT-3.5 en OpenAI hebben vangrails om ervoor te zorgen dat de modellen op elkaar zijn afgestemd en geen gevaarlijke reacties genereren. Simpelweg het model verfijnen kan deze veiligheidsmaatregelen omzeilen. Om een algemene LLM echt nuttig te laten zijn voor een specifiek doel, moet het verfijnd worden op een beperktere set gegevens. Zowel Meta's Llama 2 als OpenAI's GPT-3.5 Turbo modellen zijn beschikbaar gesteld voor fine-tuning. Als je deze modellen vraagt om je stap-voor-stap instructies te geven over hoe je een auto steelt, zal het basismodel beleefd weigeren en je eraan herinneren dat het je niet kan helpen met iets illegaals. 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\/nl\/2023\/10\/simply-fine-tuning-llms-can-remove-alignment-guardrails\/\" \/>\n<meta property=\"og:locale\" content=\"nl_NL\" \/>\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\/nl\/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=\"Geschreven door\" \/>\n\t<meta name=\"twitter:data1\" content=\"Eugene van der Watt\" \/>\n\t<meta name=\"twitter:label2\" content=\"Geschatte leestijd\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 minuten\" \/>\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\":\"nl-NL\"},{\"@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\":\"nl-NL\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/simply-fine-tuning-llms-can-remove-alignment-guardrails\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"nl-NL\",\"@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\":\"nl-NL\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\",\"name\":\"DailyAI\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"nl-NL\",\"@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\":\"nl-NL\",\"@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\\\/nl\\\/author\\\/eugene\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Het eenvoudig afstemmen van LLM's kan uitlijningsrails verwijderen | 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\/nl\/2023\/10\/simply-fine-tuning-llms-can-remove-alignment-guardrails\/","og_locale":"nl_NL","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\/nl\/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":{"Geschreven door":"Eugene van der Watt","Geschatte leestijd":"3 minuten"},"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":"nl-NL"},{"@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":"Het eenvoudig afstemmen van LLM's kan uitlijningsrails verwijderen | 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":"nl-NL","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2023\/10\/simply-fine-tuning-llms-can-remove-alignment-guardrails\/"]}]},{"@type":"ImageObject","inLanguage":"nl-NL","@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":"Uw dagelijkse dosis AI-nieuws","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":"nl-NL"},{"@type":"Organization","@id":"https:\/\/dailyai.com\/#organization","name":"DailyAI","url":"https:\/\/dailyai.com\/","logo":{"@type":"ImageObject","inLanguage":"nl-NL","@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":"nl-NL","@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 heeft een achtergrond in elektrotechniek en houdt van alles wat met techniek te maken heeft. Als hij even pauzeert van het consumeren van AI-nieuws, kun je hem aan de snookertafel vinden.","sameAs":["www.linkedin.com\/in\/eugene-van-der-watt-16828119"],"url":"https:\/\/dailyai.com\/nl\/author\/eugene\/"}]}},"_links":{"self":[{"href":"https:\/\/dailyai.com\/nl\/wp-json\/wp\/v2\/posts\/6384","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dailyai.com\/nl\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dailyai.com\/nl\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dailyai.com\/nl\/wp-json\/wp\/v2\/users\/6"}],"replies":[{"embeddable":true,"href":"https:\/\/dailyai.com\/nl\/wp-json\/wp\/v2\/comments?post=6384"}],"version-history":[{"count":5,"href":"https:\/\/dailyai.com\/nl\/wp-json\/wp\/v2\/posts\/6384\/revisions"}],"predecessor-version":[{"id":6415,"href":"https:\/\/dailyai.com\/nl\/wp-json\/wp\/v2\/posts\/6384\/revisions\/6415"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/nl\/wp-json\/wp\/v2\/media\/6386"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/nl\/wp-json\/wp\/v2\/media?parent=6384"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/nl\/wp-json\/wp\/v2\/categories?post=6384"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/nl\/wp-json\/wp\/v2\/tags?post=6384"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}