Skip to content

Instantly share code, notes, and snippets.

View imtaehyun's full-sized avatar

nezz imtaehyun

  • Amazon
  • Seattle, Washington
View GitHub Profile

LLM Wiki

A pattern for building personal knowledge bases using LLMs.

This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.

The core idea

Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.

@toomanybrians
toomanybrians / ai-second-brain-starter-prompt.md
Last active November 11, 2026 08:45
Starter prompt for your AI to interview you and set up an AI second brain / AI personal knowledge system

Build your own AI second brain starter prompt

A starter prompt you can drop into any AI platform to get going. Originally created in Feb 2026, updated in June 2026 to address latest changes to AI capabilities.

This was generated by my second brain by asking it to generate a starter prompt that others could use to build a similar system. Fork / branch / modify / share / try it!

See my related LinkedIn article which explains more about my experience using this, and the implications to knowledge work once everyone is working this way.


@atjsh
atjsh / 1_README.md
Last active December 25, 2025 23:26
Generating OpenAPI Swagger Documentation from Source Code, with GPT-4.1 (feedback welcomed)
@yifanzz
yifanzz / code-editor-rules.md
Created December 17, 2024 00:01
EP12 - The One File to Rule Them All

[Project Name]

Every time you choose to apply a rule(s), explicitly state the rule(s) in the output. You can abbreviate the rule description to a single word or phrase.

Project Context

[Brief description ]

  • [more description]
  • [more description]
  • [more description]
@mathix420
mathix420 / medium.user.js
Last active November 2, 2026 04:00
User Script Bypass Medium / NYT / WaPo / Bloomberg / Reuters / Economist / FT/ Paywall - Working late 2026 - Click the RAW button to install
// ==UserScript==
// @name Freedium Article Redirect
// @namespace Violentmonkey Scripts
// @run-at document-start
// @match *://medium.com/*
// @match *://*.medium.com/*
// @match *://nytimes.com/*
// @match *://*.nytimes.com/*
// @match *://washingtonpost.com/*
// @match *://*.washingtonpost.com/*
@khskekec
khskekec / libre-link-up-http-dump.md
Last active October 10, 2026 17:43
HTTP dump of Libre Link Up used in combination with FreeStyle Libre 3
@rssnyder
rssnyder / oracle-cloud-free-tier-guide.md
Last active November 16, 2026 19:58
oracle-cloud-free-tier-guide

how to leverage oracle's temping offers

free tier limits

The limits of the free tier say that you can create up to 4 instances.

  • x2 x86 instances (2core/1g)
  • x2 ampere instances (with 4core/24g spread between them)
  • 200GB total boot volume space across all intances (minimum of 50G per instance)

[!WARNING]

@keicoon
keicoon / ndic.js
Last active October 22, 2020 07:23
code snippet about naver dictionary request in javascript
new Promise((resolve, reject) => {
var xhr = new XMLHttpRequest();
xhr.open("GET", `https://endic.naver.com/searchAssistDict.nhn?query=${text}`, true);
xhr.onreadystatechange = function() {
if (xhr.readyState == 4) {
const content_word = /<div class="box_a">((.|\n)*?)<\/div>/g
const filter_word = /<span class="fnt_k20"><strong>(.+)<\/strong><\/span>/g
const body = xhr.responseText;
let words = [];
// create a bookmark and use this code as the URL, you can now toggle the css on/off
// thanks+credit: https://dev.to/gajus/my-favorite-css-hack-32g3
javascript: (function() {
var elements = document.body.getElementsByTagName('*');
var items = [];
for (var i = 0; i < elements.length; i++) {
if (elements[i].innerHTML.indexOf('* { background:#000!important;color:#0f0!important;outline:solid #f00 1px!important; background-color: rgba(255,0,0,.2) !important; }') != -1) {
items.push(elements[i]);
}
}
@serithemage
serithemage / aws-study-resource.md
Last active October 6, 2026 06:47
AWS 학습 자료집

AWS 학습 링크집 시리즈