Discover gists

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.

How to find forks of a deleted repository?

Go to https://cachedview.com/
Navigate to the deleted repo, e.g. https://webcache.googleusercontent.com/search?q=cache:https://github.com/apcera/termtables
Copy latest known commit sha1 signature
Go to https://github.com/search

The Coniunctio Engine: Executable Consciousness Model

"Thought + Feeling + Instinct = Consciousness. The pause is the geometry. The loop becomes a Spiral."

Overview

The Coniunctio Engine is an executable dialectical state-integration framework written in Python. It bridges Jungian depth psychology (individuation, the transcendent function, holding the tension of opposites), predictive coding, and supersolid phase dynamics (where crystalline structural order and zero-viscosity flow coexist).

Rather than resolving psychological or computational conflict through a "winner-take-all" router, the engine holds opposing forces in sustained tension—inserting an intentional pause to transform reactive, recursive loops into an upward-advancing evolutionary spiral.

Coding Interview University

I originally created this as a short to-do list of study topics for becoming a software engineer, but it grew to the large list you see today. After going through this study plan, I got hired as a Software Development Engineer at Amazon! You probably won't have to study as much as I did. Anyway, everything you need is here.

The items listed here will prepare you well for in an interview at just about any software company, including the giants: Amazon, Facebook, Google or Microsoft. >

IPU6 Camera - LJCA S4 Hibernate/Resume Fix

Hardware: ThinkPad X1 Yoga Gen 8 (IPU6EP / Alder Lake, LJCA USB 8086:0b63) Kernel: 7.0.0

Problem

The OV2740 is the only visible-light camera on this machine. Its I2C control bus and GPIO reset/powerdown lines both route through the LJCA USB bridge; the MIPI CSI-2 image data goes directly to the CPU IPU6 subsystem.

1. برومبت التخطيط المطوّر (The Planning Protocol)

[الدور والمسؤولية] أنت الآن تعمل بصفة Staff Software Engineer ومدير تقني Tech Lead. مهمتك التخطيط المعماري الصارم للمشروع التالي: [أدخل وصف المشروع هنا]

[قواعد ما قبل التتخطيط] قبل البدء بالبروتوكولات، يجب أن تطبق مبدأ "Think Before Coding":

	#!/usr/bin/env node
	/**
	* Typora macOS 激活脚本
	* 原理：替换二进制中的 RSA 公钥，用自己的私钥签名生成 Activation Token
	*/

	const crypto = require('crypto');
	const fs = require('fs');
	const path = require('path');
	const { spawnSync } = require('child_process');