{"id":38387,"date":"2026-05-17T19:29:23","date_gmt":"2026-05-17T19:29:23","guid":{"rendered":"https:\/\/www.duck9.com\/blog\/?p=38387"},"modified":"2026-05-17T15:29:35","modified_gmt":"2026-05-17T19:29:35","slug":"native-model-knowledge-only-short-term-chat-history-long-term-persisted-files-and-external-tools-like-web-search","status":"publish","type":"post","link":"https:\/\/www.duck9.com\/blog\/native-model-knowledge-only-short-term-chat-history-long-term-persisted-files-and-external-tools-like-web-search\/","title":{"rendered":"native model knowledge only, short-term chat history, long-term persisted files, and external tools like web search."},"content":{"rendered":"<div class=\"postie-post\">\n<div>\n<div dir=\"ltr\">\n<div style=\"display: block;\" class=\"\">\n<div class=\"\">\u2022 &nbsp;@mobileraj shares a teaching framework for LLMs that layers knowledge access: native model knowledge only, short-term chat history, long-term persisted files, and external tools like web search.<\/div>\n<div class=\"\">\u2022 &nbsp;The approach demonstrates how these elements combine to build a complete AI \u201charness,\u201d making abstract concepts like context windows and tool use easier to understand for learners.<\/div>\n<div class=\"\">\u2022 &nbsp;This progressive structure mirrors real-world AI system design, highlighting how restricting or enabling memory\/tools reveals the boundaries and strengths of large language models.\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b\u200b<\/div>\n<\/div>\n<div style=\"display: block;\" class=\"\"><\/div>\n<div style=\"display: block;\" class=\"\">\n<div style=\"-webkit-user-select: all; -webkit-user-drag: element; display: inline-block;\" class=\"apple-rich-link\" draggable=\"true\" role=\"link\" data-url=\"https:\/\/x.com\/mobileraj\/status\/2056085602659918182?s=43\"><a style=\"border-radius:10px;font-family:-apple-system, Helvetica, Arial, sans-serif;display:block;-webkit-user-select:none;width:300px;user-select:none;-webkit-user-modify:read-only;user-modify:read-only;overflow:hidden;text-decoration:none;\" class=\"lp-rich-link\" rel=\"nofollow\" href=\"https:\/\/x.com\/mobileraj\/status\/2056085602659918182?s=43\" dir=\"ltr\" role=\"button\" draggable=\"false\" width=\"300\"><\/p>\n<table style=\"table-layout:fixed;border-collapse:collapse;width:300px;background-color:#EBF7FF;font-family:-apple-system, Helvetica, Arial, sans-serif;\" class=\"lp-rich-link-emailBaseTable\" cellpadding=\"0\" cellspacing=\"0\" border=\"0\" width=\"300\">\n<tbody>\n<tr>\n<td vertical-align=\"center\">\n<div style=\"margin:10px 16px 0px 16px;color:#000000;font-weight:300;text-align:left;width:268px;font-size:11pt;word-wrap:break-word;overflow:hidden;\" class=\"lp-rich-link-quotedText\">Thought this framing for teaching was neat:    1. Can you research X, you&#8217;re not allowed to use any memory or other (demonstrates what the LLM natively knows)  2. You can use short term memory (the chat history)  3. You can use long term memory (any files persisted that contain<\/div>\n<\/td>\n<\/tr>\n<tr>\n<td vertical-align=\"center\">\n<table bgcolor=\"#EBF7FF\" cellpadding=\"0\" cellspacing=\"0\" width=\"300\" style=\"table-layout:fixed;font-family:-apple-system, Helvetica, Arial, sans-serif;background-color:rgba(235, 247, 255, 1);\" class=\"lp-rich-link-captionBar\">\n<tbody>\n<tr>\n<td style=\"padding:6px 0px 6px 16px;\" class=\"lp-rich-link-captionBar-leftIconItem\" width=\"25\"><a rel=\"nofollow\" href=\"https:\/\/x.com\/mobileraj\/status\/2056085602659918182?s=43\" draggable=\"false\"><img loading=\"lazy\" decoding=\"async\" style=\"pointer-events:none !important;display:inline-block;width:25px;height:25px;border-radius:3px;\" width=\"25\" height=\"25\" draggable=\"false\" class=\"lp-rich-link-captionBar-leftIcon\" alt=\"J72ksyW8_200x200.jpg\" src=\"https:\/\/www.duck9.com\/wp-content\/uploads\/2026\/05\/J72ksyW8_200x200.jpg\"><\/a><\/td>\n<td style=\"padding:8px 0px 8px 0px;\" class=\"lp-rich-link-captionBar-textStackItem\">\n<div style=\"max-width:100%;margin:0px 16px 0px 10px;overflow:hidden;\" class=\"lp-rich-link-captionBar-textStack\">\n<div style=\"word-wrap:break-word;font-weight:500;font-size:12px;overflow:hidden;text-overflow:ellipsis;text-align:left;\" class=\"lp-rich-link-captionBar-textStack-topCaption-leading\"><a rel=\"nofollow\" href=\"https:\/\/x.com\/mobileraj\/status\/2056085602659918182?s=43\" style=\"text-decoration: none\" draggable=\"false\"><font color=\"#000000\" style=\"color: rgba(0, 0, 0, 1);\">Raj Singh (@mobileraj)<\/font><\/a><\/div>\n<div style=\"word-wrap:break-word;font-weight:400;font-size:11px;overflow:hidden;text-overflow:ellipsis;text-align:left;\" class=\"lp-rich-link-captionBar-textStack-bottomCaption-leading\"><a rel=\"nofollow\" href=\"https:\/\/x.com\/mobileraj\/status\/2056085602659918182?s=43\" style=\"text-decoration: none\" draggable=\"false\"><font color=\"#A2A2A9\" style=\"color: rgba(60, 60, 67, 0.6);\">x.com<\/font><\/a><\/div>\n<\/div>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p><\/a><\/div>\n<\/div>\n<p><\/div>\n<p><br id=\"lineBreakAtBeginningOfSignature\"><\/p>\n<div dir=\"ltr\">\n<div><span style=\"background-color: rgba(255, 255, 255, 0);\">http:\/\/www.youtube.com\/watch?v=QXIaNZi3mHQ<\/span><\/div>\n<\/div>\n<\/div>\n<\/div>\n","protected":false},"excerpt":{"rendered":"<p>\u2022 &nbsp;@mobileraj shares a teaching framework for LLMs that layers knowledge access: native model knowledge only, short-term chat history, long-term persisted files, and external tools like web search. \u2022 &nbsp;The approach demonstrates how these elements combine to build a complete AI \u201charness,\u201d making abstract concepts like context windows and tool use easier to understand for [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":38388,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-38387","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"post_mailing_queue_ids":[],"_links":{"self":[{"href":"https:\/\/www.duck9.com\/blog\/wp-json\/wp\/v2\/posts\/38387","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.duck9.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.duck9.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.duck9.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.duck9.com\/blog\/wp-json\/wp\/v2\/comments?post=38387"}],"version-history":[{"count":0,"href":"https:\/\/www.duck9.com\/blog\/wp-json\/wp\/v2\/posts\/38387\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.duck9.com\/blog\/wp-json\/wp\/v2\/media\/38388"}],"wp:attachment":[{"href":"https:\/\/www.duck9.com\/blog\/wp-json\/wp\/v2\/media?parent=38387"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.duck9.com\/blog\/wp-json\/wp\/v2\/categories?post=38387"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.duck9.com\/blog\/wp-json\/wp\/v2\/tags?post=38387"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}