{"id":582,"date":"2026-09-04T10:19:14","date_gmt":"2026-09-04T03:19:14","guid":{"rendered":"https:\/\/azefine.com\/?p=582"},"modified":"2026-09-04T10:19:14","modified_gmt":"2026-09-04T03:19:14","slug":"tutorial-how-to-build-ai-systems-that-know-when-they-dont-know","status":"publish","type":"post","link":"https:\/\/azefine.com\/?p=582","title":{"rendered":"[Tutorial] How to Build AI Systems That Know When They Don&#8217;t Know"},"content":{"rendered":"<p>Sistem AI modern seperti Large Language Model (LLM) sering kali memberikan jawaban dengan percaya diri, bahkan ketika mereka sebenarnya tidak tahu jawabannya. Fenomena ini disebut <em>hallucination<\/em> \u2014 model menghasilkan teks yang terdengar masuk akal tapi secara faktual salah. Untuk aplikasi produksi, ini bisa berbayanya: diagnosis medis yang salah, keputusan finansial yang keliru, atau kode yang gagal diam-diam.<\/p>\n<p>Artikel ini membahas bagaimana membangun sistem AI yang mampu mengenali batas pengetahuannya sendiri. Konsepnya sederhana: model tidak hanya menghasilkan jawaban, tapi juga mengukur seberapa &#8220;yakin&#8221; dirinya dengan jawaban tersebut. Teknik utamanya mencakup <strong>uncertainty estimation<\/strong> (mengukur ketidakpastian), <strong>calibration<\/strong> (memastikan skor kepercayaan sesuai dengan probabilitas benar yang sebenarnya), dan <strong>out-of-distribution detection<\/strong> (mengenali ketika input di luar data latih).<\/p>\n<p>Di praktiknya, ada beberapa pendekatan yang bisa diimplementasikan. <strong>Monte Carlo Dropout<\/strong> menjalankan model beberapa kali dengan dropout aktif dan mengukur varians output \u2014 varians tinggi berarti model tidak yakin. <strong>Ensemble methods<\/strong> menggunakan beberapa model sekaligus dan membandingkan hasilnya. <strong>Confidence scoring<\/strong> menghasilkan skor numerik yang bisa di-threshold: di bawah threshold, sistem bisa menolak menjawab atau mengarahkan ke manusia. Kombinasi ketiga pendekatan ini menciptakan lapisan keamanan yang robust.<\/p>\n<p>Implementasi tidak harus dimulai dari nol. Framework seperti LangChain dan LlamaChain menyediakan modul bawaan untuk evaluasi kepercayaan. Untuk LLM API, Anda bisa menggunakan <em>logprobs<\/em> yang dikembalikan oleh model untuk mengukur kepercayaan token per token. Kuncinya adalah membangun pipeline di mana setiap output AI melewati pengecekan kepercayaan sebelum mencapai pengguna akhir.<\/p>\n<p><strong>Sumber asli:<\/strong> <a href='https:\/\/www.freecodecamp.org\/news\/how-to-build-ai-systems-that-know-when-they-don-t-know\/' target='_blank' rel='noopener'>freecodecamp.org<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Sistem AI modern seperti Large Language Model (LLM) sering kali memberikan jawaban dengan percaya diri, bahkan ketika mereka sebenarnya tidak &#8230;<\/p>\n","protected":false},"author":1,"featured_media":583,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"om_disable_all_campaigns":false,"_monsterinsights_skip_tracking":false,"footnotes":""},"categories":[30],"tags":[],"class_list":["post-582","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-it-infrastructure"],"aioseo_notices":[],"aioseo_head":"\n\t\t<!-- All in One SEO 4.9.9 - aioseo.com -->\n\t<meta name=\"description\" content=\"Sistem AI modern seperti Large Language Model (LLM) sering kali memberikan jawaban dengan percaya diri, bahkan ketika mereka sebenarnya tidak tahu jawabannya. Fenomena ini disebut hallucination \u2014 model menghasilkan teks yang terdengar masuk akal tapi secara faktual salah. Untuk aplikasi produksi, ini bisa berbayanya: diagnosis medis yang salah, keputusan finansial yang keliru, atau kode yang\" \/>\n\t<meta name=\"robots\" content=\"max-image-preview:large\" \/>\n\t<meta name=\"author\" content=\"admin\"\/>\n\t<meta name=\"google-site-verification\" content=\"kGr-69bwUCluDNT6g7j--4V_IeKr-s62r8fzSbAAOLA\" \/>\n\t<link rel=\"canonical\" href=\"https:\/\/azefine.com\/?p=582\" \/>\n\t<meta name=\"generator\" content=\"All in One SEO (AIOSEO) 4.9.9\" \/>\n\t\t<meta property=\"og:locale\" content=\"en_US\" \/>\n\t\t<meta property=\"og:site_name\" content=\"Azefine Worker -\" \/>\n\t\t<meta property=\"og:type\" content=\"article\" \/>\n\t\t<meta property=\"og:title\" content=\"[Tutorial] How to Build AI Systems That Know When They Don\u2019t Know - Azefine Worker\" \/>\n\t\t<meta property=\"og:description\" content=\"Sistem AI modern seperti Large Language Model (LLM) sering kali memberikan jawaban dengan percaya diri, bahkan ketika mereka sebenarnya tidak tahu jawabannya. Fenomena ini disebut hallucination \u2014 model menghasilkan teks yang terdengar masuk akal tapi secara faktual salah. Untuk aplikasi produksi, ini bisa berbayanya: diagnosis medis yang salah, keputusan finansial yang keliru, atau kode yang\" \/>\n\t\t<meta property=\"og:url\" content=\"https:\/\/azefine.com\/?p=582\" \/>\n\t\t<meta property=\"og:image\" content=\"https:\/\/azefine.com\/wp-content\/uploads\/2026\/02\/Logo.png\" \/>\n\t\t<meta property=\"og:image:secure_url\" content=\"https:\/\/azefine.com\/wp-content\/uploads\/2026\/02\/Logo.png\" \/>\n\t\t<meta property=\"article:published_time\" content=\"2026-09-04T03:19:14+00:00\" \/>\n\t\t<meta property=\"article:modified_time\" content=\"2026-09-04T03:19:14+00:00\" \/>\n\t\t<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n\t\t<meta name=\"twitter:title\" content=\"[Tutorial] How to Build AI Systems That Know When They Don\u2019t Know - Azefine Worker\" \/>\n\t\t<meta name=\"twitter:description\" content=\"Sistem AI modern seperti Large Language Model (LLM) sering kali memberikan jawaban dengan percaya diri, bahkan ketika mereka sebenarnya tidak tahu jawabannya. Fenomena ini disebut hallucination \u2014 model menghasilkan teks yang terdengar masuk akal tapi secara faktual salah. Untuk aplikasi produksi, ini bisa berbayanya: diagnosis medis yang salah, keputusan finansial yang keliru, atau kode yang\" \/>\n\t\t<meta name=\"twitter:image\" content=\"https:\/\/azefine.com\/wp-content\/uploads\/2026\/02\/Logo.png\" \/>\n\t\t<script type=\"application\/ld+json\" class=\"aioseo-schema\">\n\t\t\t{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"BlogPosting\",\"@id\":\"https:\\\/\\\/azefine.com\\\/?p=582#blogposting\",\"name\":\"[Tutorial] How to Build AI Systems That Know When They Don\\u2019t Know - Azefine Worker\",\"headline\":\"[Tutorial] How to Build AI Systems That Know When They Don&#8217;t Know\",\"author\":{\"@id\":\"https:\\\/\\\/azefine.com\\\/?author=1#author\"},\"publisher\":{\"@id\":\"https:\\\/\\\/azefine.com\\\/#organization\"},\"image\":{\"@type\":\"ImageObject\",\"url\":\"https:\\\/\\\/azefine.com\\\/wp-content\\\/uploads\\\/2026\\\/09\\\/feat_ai_582.png\",\"width\":1920,\"height\":1080,\"caption\":\"Gambar: freecodecamp.org\"},\"datePublished\":\"2026-09-04T10:19:14+07:00\",\"dateModified\":\"2026-09-04T10:19:14+07:00\",\"inLanguage\":\"en-US\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/azefine.com\\\/?p=582#webpage\"},\"isPartOf\":{\"@id\":\"https:\\\/\\\/azefine.com\\\/?p=582#webpage\"},\"articleSection\":\"IT Infrastructure\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/azefine.com\\\/?p=582#breadcrumblist\",\"itemListElement\":[{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/azefine.com#listItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/azefine.com\",\"nextItem\":{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/azefine.com\\\/?cat=30#listItem\",\"name\":\"IT Infrastructure\"}},{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/azefine.com\\\/?cat=30#listItem\",\"position\":2,\"name\":\"IT Infrastructure\",\"item\":\"https:\\\/\\\/azefine.com\\\/?cat=30\",\"nextItem\":{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/azefine.com\\\/?p=582#listItem\",\"name\":\"[Tutorial] How to Build AI Systems That Know When They Don&#8217;t Know\"},\"previousItem\":{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/azefine.com#listItem\",\"name\":\"Home\"}},{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/azefine.com\\\/?p=582#listItem\",\"position\":3,\"name\":\"[Tutorial] How to Build AI Systems That Know When They Don&#8217;t Know\",\"previousItem\":{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/azefine.com\\\/?cat=30#listItem\",\"name\":\"IT Infrastructure\"}}]},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/azefine.com\\\/#organization\",\"name\":\"Azefine Worker Azefine Worker\",\"description\":\"Azefine Worker adalah IT Partner end-to-end yang membantu UMKM dan Enterprise membangun, mengelola, dan mengembangkan solusi teknologi secara terstruktur dan berkelanjutan, mulai dari Web Development, Cloud Infrastructure, DevOps, IT Support, hingga AI Automation.\",\"url\":\"https:\\\/\\\/azefine.com\\\/\",\"telephone\":\"+6285183370571\",\"logo\":{\"@type\":\"ImageObject\",\"url\":\"https:\\\/\\\/azefine.com\\\/wp-content\\\/uploads\\\/2026\\\/02\\\/Logo.png\",\"@id\":\"https:\\\/\\\/azefine.com\\\/?p=582\\\/#organizationLogo\",\"width\":1024,\"height\":341},\"image\":{\"@id\":\"https:\\\/\\\/azefine.com\\\/?p=582\\\/#organizationLogo\"}},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/azefine.com\\\/?author=1#author\",\"url\":\"https:\\\/\\\/azefine.com\\\/?author=1\",\"name\":\"admin\",\"image\":{\"@type\":\"ImageObject\",\"@id\":\"https:\\\/\\\/azefine.com\\\/?p=582#authorImage\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/33ef3d14ff07ddc5707348b3f8e1ab96b8c4f341c213c643f2765a6da11259a5?s=96&d=mm&r=g\",\"width\":96,\"height\":96,\"caption\":\"admin\"}},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/azefine.com\\\/?p=582#webpage\",\"url\":\"https:\\\/\\\/azefine.com\\\/?p=582\",\"name\":\"[Tutorial] How to Build AI Systems That Know When They Don\\u2019t Know - Azefine Worker\",\"description\":\"Sistem AI modern seperti Large Language Model (LLM) sering kali memberikan jawaban dengan percaya diri, bahkan ketika mereka sebenarnya tidak tahu jawabannya. Fenomena ini disebut hallucination \\u2014 model menghasilkan teks yang terdengar masuk akal tapi secara faktual salah. Untuk aplikasi produksi, ini bisa berbayanya: diagnosis medis yang salah, keputusan finansial yang keliru, atau kode yang\",\"inLanguage\":\"en-US\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/azefine.com\\\/#website\"},\"breadcrumb\":{\"@id\":\"https:\\\/\\\/azefine.com\\\/?p=582#breadcrumblist\"},\"author\":{\"@id\":\"https:\\\/\\\/azefine.com\\\/?author=1#author\"},\"creator\":{\"@id\":\"https:\\\/\\\/azefine.com\\\/?author=1#author\"},\"image\":{\"@type\":\"ImageObject\",\"url\":\"https:\\\/\\\/azefine.com\\\/wp-content\\\/uploads\\\/2026\\\/09\\\/feat_ai_582.png\",\"@id\":\"https:\\\/\\\/azefine.com\\\/?p=582\\\/#mainImage\",\"width\":1920,\"height\":1080,\"caption\":\"Gambar: freecodecamp.org\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/azefine.com\\\/?p=582#mainImage\"},\"datePublished\":\"2026-09-04T10:19:14+07:00\",\"dateModified\":\"2026-09-04T10:19:14+07:00\"},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/azefine.com\\\/#website\",\"url\":\"https:\\\/\\\/azefine.com\\\/\",\"name\":\"Azefine Worker\",\"inLanguage\":\"en-US\",\"publisher\":{\"@id\":\"https:\\\/\\\/azefine.com\\\/#organization\"}}]}\n\t\t<\/script>\n\t\t<!-- All in One SEO -->\n\n","aioseo_head_json":{"title":"[Tutorial] How to Build AI Systems That Know When They Don\u2019t Know - Azefine Worker","description":"Sistem AI modern seperti Large Language Model (LLM) sering kali memberikan jawaban dengan percaya diri, bahkan ketika mereka sebenarnya tidak tahu jawabannya. Fenomena ini disebut hallucination \u2014 model menghasilkan teks yang terdengar masuk akal tapi secara faktual salah. Untuk aplikasi produksi, ini bisa berbayanya: diagnosis medis yang salah, keputusan finansial yang keliru, atau kode yang","canonical_url":"https:\/\/azefine.com\/?p=582","robots":"max-image-preview:large","keywords":"","webmasterTools":{"google-site-verification":"kGr-69bwUCluDNT6g7j--4V_IeKr-s62r8fzSbAAOLA","miscellaneous":""},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"BlogPosting","@id":"https:\/\/azefine.com\/?p=582#blogposting","name":"[Tutorial] How to Build AI Systems That Know When They Don\u2019t Know - Azefine Worker","headline":"[Tutorial] How to Build AI Systems That Know When They Don&#8217;t Know","author":{"@id":"https:\/\/azefine.com\/?author=1#author"},"publisher":{"@id":"https:\/\/azefine.com\/#organization"},"image":{"@type":"ImageObject","url":"https:\/\/azefine.com\/wp-content\/uploads\/2026\/09\/feat_ai_582.png","width":1920,"height":1080,"caption":"Gambar: freecodecamp.org"},"datePublished":"2026-09-04T10:19:14+07:00","dateModified":"2026-09-04T10:19:14+07:00","inLanguage":"en-US","mainEntityOfPage":{"@id":"https:\/\/azefine.com\/?p=582#webpage"},"isPartOf":{"@id":"https:\/\/azefine.com\/?p=582#webpage"},"articleSection":"IT Infrastructure"},{"@type":"BreadcrumbList","@id":"https:\/\/azefine.com\/?p=582#breadcrumblist","itemListElement":[{"@type":"ListItem","@id":"https:\/\/azefine.com#listItem","position":1,"name":"Home","item":"https:\/\/azefine.com","nextItem":{"@type":"ListItem","@id":"https:\/\/azefine.com\/?cat=30#listItem","name":"IT Infrastructure"}},{"@type":"ListItem","@id":"https:\/\/azefine.com\/?cat=30#listItem","position":2,"name":"IT Infrastructure","item":"https:\/\/azefine.com\/?cat=30","nextItem":{"@type":"ListItem","@id":"https:\/\/azefine.com\/?p=582#listItem","name":"[Tutorial] How to Build AI Systems That Know When They Don&#8217;t Know"},"previousItem":{"@type":"ListItem","@id":"https:\/\/azefine.com#listItem","name":"Home"}},{"@type":"ListItem","@id":"https:\/\/azefine.com\/?p=582#listItem","position":3,"name":"[Tutorial] How to Build AI Systems That Know When They Don&#8217;t Know","previousItem":{"@type":"ListItem","@id":"https:\/\/azefine.com\/?cat=30#listItem","name":"IT Infrastructure"}}]},{"@type":"Organization","@id":"https:\/\/azefine.com\/#organization","name":"Azefine Worker Azefine Worker","description":"Azefine Worker adalah IT Partner end-to-end yang membantu UMKM dan Enterprise membangun, mengelola, dan mengembangkan solusi teknologi secara terstruktur dan berkelanjutan, mulai dari Web Development, Cloud Infrastructure, DevOps, IT Support, hingga AI Automation.","url":"https:\/\/azefine.com\/","telephone":"+6285183370571","logo":{"@type":"ImageObject","url":"https:\/\/azefine.com\/wp-content\/uploads\/2026\/02\/Logo.png","@id":"https:\/\/azefine.com\/?p=582\/#organizationLogo","width":1024,"height":341},"image":{"@id":"https:\/\/azefine.com\/?p=582\/#organizationLogo"}},{"@type":"Person","@id":"https:\/\/azefine.com\/?author=1#author","url":"https:\/\/azefine.com\/?author=1","name":"admin","image":{"@type":"ImageObject","@id":"https:\/\/azefine.com\/?p=582#authorImage","url":"https:\/\/secure.gravatar.com\/avatar\/33ef3d14ff07ddc5707348b3f8e1ab96b8c4f341c213c643f2765a6da11259a5?s=96&d=mm&r=g","width":96,"height":96,"caption":"admin"}},{"@type":"WebPage","@id":"https:\/\/azefine.com\/?p=582#webpage","url":"https:\/\/azefine.com\/?p=582","name":"[Tutorial] How to Build AI Systems That Know When They Don\u2019t Know - Azefine Worker","description":"Sistem AI modern seperti Large Language Model (LLM) sering kali memberikan jawaban dengan percaya diri, bahkan ketika mereka sebenarnya tidak tahu jawabannya. Fenomena ini disebut hallucination \u2014 model menghasilkan teks yang terdengar masuk akal tapi secara faktual salah. Untuk aplikasi produksi, ini bisa berbayanya: diagnosis medis yang salah, keputusan finansial yang keliru, atau kode yang","inLanguage":"en-US","isPartOf":{"@id":"https:\/\/azefine.com\/#website"},"breadcrumb":{"@id":"https:\/\/azefine.com\/?p=582#breadcrumblist"},"author":{"@id":"https:\/\/azefine.com\/?author=1#author"},"creator":{"@id":"https:\/\/azefine.com\/?author=1#author"},"image":{"@type":"ImageObject","url":"https:\/\/azefine.com\/wp-content\/uploads\/2026\/09\/feat_ai_582.png","@id":"https:\/\/azefine.com\/?p=582\/#mainImage","width":1920,"height":1080,"caption":"Gambar: freecodecamp.org"},"primaryImageOfPage":{"@id":"https:\/\/azefine.com\/?p=582#mainImage"},"datePublished":"2026-09-04T10:19:14+07:00","dateModified":"2026-09-04T10:19:14+07:00"},{"@type":"WebSite","@id":"https:\/\/azefine.com\/#website","url":"https:\/\/azefine.com\/","name":"Azefine Worker","inLanguage":"en-US","publisher":{"@id":"https:\/\/azefine.com\/#organization"}}]},"og:locale":"en_US","og:site_name":"Azefine Worker -","og:type":"article","og:title":"[Tutorial] How to Build AI Systems That Know When They Don\u2019t Know - Azefine Worker","og:description":"Sistem AI modern seperti Large Language Model (LLM) sering kali memberikan jawaban dengan percaya diri, bahkan ketika mereka sebenarnya tidak tahu jawabannya. Fenomena ini disebut hallucination \u2014 model menghasilkan teks yang terdengar masuk akal tapi secara faktual salah. Untuk aplikasi produksi, ini bisa berbayanya: diagnosis medis yang salah, keputusan finansial yang keliru, atau kode yang","og:url":"https:\/\/azefine.com\/?p=582","og:image":"https:\/\/azefine.com\/wp-content\/uploads\/2026\/02\/Logo.png","og:image:secure_url":"https:\/\/azefine.com\/wp-content\/uploads\/2026\/02\/Logo.png","article:published_time":"2026-09-04T03:19:14+00:00","article:modified_time":"2026-09-04T03:19:14+00:00","twitter:card":"summary_large_image","twitter:title":"[Tutorial] How to Build AI Systems That Know When They Don\u2019t Know - Azefine Worker","twitter:description":"Sistem AI modern seperti Large Language Model (LLM) sering kali memberikan jawaban dengan percaya diri, bahkan ketika mereka sebenarnya tidak tahu jawabannya. Fenomena ini disebut hallucination \u2014 model menghasilkan teks yang terdengar masuk akal tapi secara faktual salah. Untuk aplikasi produksi, ini bisa berbayanya: diagnosis medis yang salah, keputusan finansial yang keliru, atau kode yang","twitter:image":"https:\/\/azefine.com\/wp-content\/uploads\/2026\/02\/Logo.png"},"aioseo_meta_data":{"post_id":"582","title":null,"description":null,"keywords":null,"keyphrases":null,"primary_term":null,"canonical_url":null,"og_title":null,"og_description":null,"og_object_type":"default","og_image_type":"default","og_image_url":null,"og_image_width":null,"og_image_height":null,"og_image_custom_url":null,"og_image_custom_fields":null,"og_video":null,"og_custom_url":null,"og_article_section":null,"og_article_tags":null,"twitter_use_og":false,"twitter_card":"default","twitter_image_type":"default","twitter_image_url":null,"twitter_image_custom_url":null,"twitter_image_custom_fields":null,"twitter_title":null,"twitter_description":null,"schema":{"blockGraphs":[],"customGraphs":[],"default":{"data":{"Article":[],"Course":[],"Dataset":[],"FAQPage":[],"Movie":[],"Person":[],"Product":[],"ProductReview":[],"Car":[],"Recipe":[],"Service":[],"SoftwareApplication":[],"WebPage":[]},"graphName":"","isEnabled":true},"graphs":[]},"schema_type":"default","schema_type_options":null,"pillar_content":false,"robots_default":true,"robots_noindex":false,"robots_noarchive":false,"robots_nosnippet":false,"robots_nofollow":false,"robots_noimageindex":false,"robots_noodp":false,"robots_notranslate":false,"robots_max_snippet":null,"robots_max_videopreview":null,"robots_max_imagepreview":"large","priority":null,"frequency":null,"local_seo":null,"breadcrumb_settings":null,"limit_modified_date":false,"ai":null,"created":"2026-09-04 18:44:11","updated":"2026-09-04 18:44:11","seo_analyzer_scan_date":null},"aioseo_breadcrumb":"<div class=\"aioseo-breadcrumbs\"><span class=\"aioseo-breadcrumb\">\n\t\t\t<a href=\"https:\/\/azefine.com\" title=\"Home\">Home<\/a>\n\t\t<\/span><span class=\"aioseo-breadcrumb-separator\">&raquo;<\/span><span class=\"aioseo-breadcrumb\">\n\t\t\t<a href=\"https:\/\/azefine.com\/?cat=30\" title=\"IT Infrastructure\">IT Infrastructure<\/a>\n\t\t<\/span><span class=\"aioseo-breadcrumb-separator\">&raquo;<\/span><span class=\"aioseo-breadcrumb\">\n\t\t\t[Tutorial] How to Build AI Systems That Know When They Don\u2019t Know\n\t\t<\/span><\/div>","aioseo_breadcrumb_json":[{"label":"Home","link":"https:\/\/azefine.com"},{"label":"IT Infrastructure","link":"https:\/\/azefine.com\/?cat=30"},{"label":"[Tutorial] How to Build AI Systems That Know When They Don&#8217;t Know","link":"https:\/\/azefine.com\/?p=582"}],"_links":{"self":[{"href":"https:\/\/azefine.com\/index.php?rest_route=\/wp\/v2\/posts\/582","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/azefine.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/azefine.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/azefine.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/azefine.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=582"}],"version-history":[{"count":0,"href":"https:\/\/azefine.com\/index.php?rest_route=\/wp\/v2\/posts\/582\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/azefine.com\/index.php?rest_route=\/wp\/v2\/media\/583"}],"wp:attachment":[{"href":"https:\/\/azefine.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=582"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/azefine.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=582"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/azefine.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=582"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}