Canace22

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.

Canace22

<rss version="2.0">
<channel>
<title>Claude 相关文章</title>
<link>https://www.anthropic.com/engineering</link>
<description>RSS Feed generated by AI</description>
<item>
<title>Claude for Engineering</title>
<link>https://support.anthropic.com/en/articles/9945689-claude-for-engineering</link>
<description>In this video guide, we'll explore several examples of how Claude can be used by engineering teams. Before you get started, review the availability of the features demonstrated in this video: Artifacts are available on all Claude.ai plans.</description>
<pubDate>Thu, 28 Nov 2025 00:00:00 GMT</pubDate>

Canace22

<template>
  <el-popover
    ref="popoverRef"
    :virtual-ref="triggerRef"
    trigger="click"
    virtual-triggering
    :visible="visible"
    popper-class="popper-class"
  >
    <slot></slot>

Canace22

const fs = require('fs');

function createPseudonym (params) {
  let start = 12354;
  const arr = [];
  for (let index = 0; index < 185; index++) {
    const word = String.fromCharCode(start++);
    arr.push(word);
  }
  fs.writeFileSync('./pseudonym.txt', arr);

Canace22

const fs = require('fs')

function createKanji() {
  const arr = [];
  for (let i = 0x4e00; i < 0x9faf; i++) {
    arr.push(String.fromCharCode(i));
  }
  const sortedChars = arr.sort(Intl.Collator('ja-JP').compare);
  const level1Kanji = sortedChars.slice(0, 2965);
  const level2Kanji = sortedChars.slice(2965, 6355);