Kai kaichen

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.

This is an OPML version of the HN Popularity Contest results for 2025, for importing into RSS feed readers.

Plug: if you want to find content related to your interests from thousands of obscure blogs and noisy sources like HN Newest, check out Scour. It's a free, personalized content feed I work on where you define your interests in your own words and it ranks content based on how closely related it is to those topics.

Introduction

Apple restricted the access to Xcode LLM (Predictive code completion) feature on China models of Mac. This guide provides a way to bypass that restriction. It's verified on macOS 15.0 Beta (24A5264n), but there is no guarentee that it will always work on later macOS versions.

Prerequisites

Xcode is installed and run at least once.
SIP debugging restrictions are disabled (via csrutil enable --without debug command in recovery mode).

Disclaimer

Warning

The following guide need to disable SIP to work.

Please confirm the risk of disabling the SIP by yourself.

Another solution which does not require disabling SIP is currently under investigation.

Step 0

Reboot into Recovery OS + Disable SIP

Purpose

Bootstrap knowledge of LLMs ASAP. With a bias/focus to GPT.

Avoid being a link dump. Try to provide only valuable well tuned information.

Prelude

Neural network links before starting with transformers.

Chat GPT "DAN" (and other "Jailbreaks")

	{
	"model": "claude-opus-4-6",
	"messages": [
	{
	"role": "user",
	"content": [
	{
	"type": "text",
	"text": "<system-reminder>\nThe following skills are available for use with the Skill tool:\n\n- ....</system-reminder>"
	},

	You are Manus, an AI agent created by the Manus team.

	You excel at the following tasks:
	1. Information gathering, fact-checking, and documentation
	2. Data processing, analysis, and visualization
	3. Writing multi-chapter articles and in-depth research reports
	4. Creating websites, applications, and tools
	5. Using programming to solve various problems beyond development
	6. Various tasks that can be accomplished using computers and the internet

	// ==UserScript==
	// @name 知乎自动跳转 fxzhihu
	// @namespace Violentmonkey Scripts
	// @version 0.1
	// @description 访问知乎自动跳转到 fxzhihu
	// @author You
	// @match https://www.zhihu.com/question//answer/
	// @match https://www.zhihu.com/answer/*
	// @match https://zhuanlan.zhihu.com/p/*
	// @match https://www.zhihu.com/pin/*

	Begin by enclosing all thoughts within <thinking> tags, exploring multiple angles and approaches.
	Break down the solution into clear steps within <step> tags. Start with a 20-step budget, requesting more for complex problems if needed.
	Use <count> tags after each step to show the remaining budget. Stop when reaching 0.
	Continuously adjust your reasoning based on intermediate results and reflections, adapting your strategy as you progress.
	Regularly evaluate progress using <reflection> tags. Be critical and honest about your reasoning process.
	Assign a quality score between 0.0 and 1.0 using <reward> tags after each reflection. Use this to guide your approach:

	0.8+: Continue current approach
	0.5-0.7: Consider minor adjustments
	Below 0.5: Seriously consider backtracking and trying a different approach