Skip to content

Instantly share code, notes, and snippets.

View starandtina's full-sized avatar

Xin(Khalil) Zhang starandtina

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.

@stettix
stettix / things-i-believe.md
Last active April 18, 2026 10:27
Things I believe

Things I believe

This is a collection of the things I believe about software development. I have worked for years building backend and data processing systems, so read the below within that context.

Agree? Disagree? Feel free to let me know at @JanStette.

Fundamentals

Keep it simple, stupid. You ain't gonna need it.

@francisrstokes
francisrstokes / StateDispatcher.js
Last active November 10, 2024 13:37
Redux without redux - sharing state and one way data flow using only standard react
import React from 'react';
export class StateDispatcher extends React.Component {
constructor(props) {
super(props);
this.state = props.state || {};
this._dispatch = this.dispatch.bind(this);
}
dispatch(action) {
@nzakas
nzakas / techleadbook.md
Created March 20, 2018 20:44
Tech Lead Book

Tech Lead Book

  1. Introduction
  2. What is a Tech Lead?
  3. The Tech Lead Mindset
  4. Becoming a Tech Lead
  5. Working Cross-Functionally
  6. The Art of Delegation
  7. Technical Best Practices
  8. Effective Decision Making
@nitin42
nitin42 / require.js
Created October 8, 2017 15:33
How Node.js's require() works ??
const some_module = require('some_module')
/**
* require('some_module') calls Module._load
*
* Module._load then tries to load the module with a filename (also save it to the cache) using module.load(filename)
*
* module.load(filename), given a filename, passes it to the proper extension handler ('.js', '.json')
*
* If there were any errors when loading the file, it deletes the file from the cache (delete Module._cache[filename]) and throws an error
@clarkbw
clarkbw / redux-performance-mark.js
Last active February 8, 2024 05:03
A User Timing middleware for redux to create performance markers for dispatched actions
const timing = store => next => action => {
performance.mark(`${action.type}_start`);
let result = next(action);
performance.mark(`${action.type}_end`);
performance.measure(
`${action.type}`,
`${action.type}_start`,
`${action.type}_end`
);
return result;
@developit
developit / unistore.js
Last active September 8, 2020 15:13
Update: the newer & better version of this is published: https://github.com/developit/unistore
import { h, Component } from 'preact';
/** Creates a new store, which is a tiny evented state container.
* @example
* let store = createStore();
* store.subscribe( state => console.log(state) );
* store.setState({ a: 'b' }); // logs { a: 'b' }
* store.setState({ c: 'd' }); // logs { c: 'd' }
*/
@kanavarora
kanavarora / bundleAnalysis.js
Last active June 7, 2019 08:24
Simple utility to track your bundle/chunk sizes with each release
/*
Utility to analyze bundle chunks over versions.
Assumes: webpack has already created the bundle summary json file -> stats.json
Parameters:
version: (Optional) a string that labels the current bundle with the version
provided and saves the summary in a csv file.
Output:
If run the first time, generates a csv file bundleAnalaysis.csv, which
var str = 'class ಠ_ಠ extends Array {constructor(j = "a", ...c) {const q = (({u: e}) => {return { [`s${c}`]: Symbol(j) };})({});super(j, q, ...c);}}' +
'new Promise((f) => {const a = function* (){return "\u{20BB7}".match(/./u)[0].length === 2 || true;};for (let vre of a()) {' +
'const [uw, as, he, re] = [new Set(), new WeakSet(), new Map(), new WeakMap()];break;}f(new Proxy({}, {get: (han, h) => h in han ? han[h] ' +
': "42".repeat(0o10)}));}).then(bi => new ಠ_ಠ(bi.rd));';
try {
eval(str);
} catch(e) {
alert('Your browser does not support ES6!')
}
@ljharb
ljharb / array_iteration_thoughts.md
Last active March 31, 2026 18:26
Array iteration methods summarized

Array Iteration

https://gist.github.com/ljharb/58faf1cfcb4e6808f74aae4ef7944cff

While attempting to explain JavaScript's reduce method on arrays, conceptually, I came up with the following - hopefully it's helpful; happy to tweak it if anyone has suggestions.

Intro

JavaScript Arrays have lots of built in methods on their prototype. Some of them mutate - ie, they change the underlying array in-place. Luckily, most of them do not - they instead return an entirely distinct array. Since arrays are conceptually a contiguous list of items, it helps code clarity and maintainability a lot to be able to operate on them in a "functional" way. (I'll also insist on referring to an array as a "list" - although in some languages, List is a native data type, in JS and this post, I'm referring to the concept. Everywhere I use the word "list" you can assume I'm talking about a JS Array) This means, to perform a single operation on the list as a whole ("atomically"), and to return a new list - thus making it mu