niu_he 2niuhe

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.

Anti-hype LLM reading list

Goals: Add links that are reasonable and good explanations of how stuff works. No hype and no vendor content if possible. Practical first-hand accounts of models in prod eagerly sought.

Foundational Concepts

Pre-Transformer Models

云

IaaS指提供系统（可以自己选）或者储存空间之类的硬件，软件要自己手动装。PaaS提供语言环境和框架（可以自己选）。SaaS只能使用开发好的软件（卖软件本身，如税务会计、表格文字处理）。BaaS一般类似于非关系数据库，但各家不通用
云服务的特点：零前期成本 & 按需付费 & 弹性（类似于租，可随时多加、退掉；但没有残值）、高可用（放在机房中，不同AZ间水电隔离）

如果你想补充内容，建议优先给 free-for-dev 提PR，还能混个高星repo的contributor，没必要加到本列表里。
If you want to make improvements, I would recommend you contributing to free-for-dev rather than this list.

其他人的集合

High-Performance Matrix Multiplication

This is a short post that explains how to write a high-performance matrix multiplication program on modern processors. In this tutorial I will use a single core of the Skylake-client CPU with AVX2, but the principles in this post also apply to other processors with different instruction sets (such as AVX512).

Intro

Matrix multiplication is a mathematical operation that defines the product of

#awesome-go

A curated list of awesome Go frameworks, libraries and software.

golang/go - The Go programming language
kubernetes/kubernetes - Production-Grade Container Scheduling and Management
avelino/awesome-go - A curated list of awesome Go frameworks, libraries and software
gogits/gogs - Gogs is a painless self-hosted Git service.
syncthing/syncthing - Open Source Continuous File Synchronization
grafana/grafana - The tool for beautiful monitoring and metric analytics & dashboards for Graphite, InfluxDB & Prometheus & More

	#!/bin/sh

	# References
	# https://www.pythonguis.com/tutorials/packaging-pyqt5-applications-pyinstaller-macos-dmg/
	# https://medium.com/@jackhuang.wz/in-just-two-steps-you-can-turn-a-python-script-into-a-macos-application-installer-6e21bce2ee71

	# ---------------------------------------
	# Clean up previous builds
	# ---------------------------------------

	#!/bin/sh

	if [ $# -lt 2 ]; then
	echo Usage: avgle-download.sh video_title url_of_last_segment
	exit 1
	fi

	# Visit a video page, open the network tab of the dev tools,
	# seek to the end of the video and copy the url of the last .ts segment
	# (the .m3u8 playlist is encoded and therefore harder to get).

	# 安装Caddy：
	wget -N --no-check-certificate https://softs.fun/Bash/caddy_install.sh && chmod +x caddy_install.sh && bash caddy_install.sh install http.filemanager
	# 配置Caddy：
	echo ":80 {
	gzip
	proxy / https://www.google.com.hk
	}" > /usr/local/caddy/Caddyfile
	/etc/init.d/caddy restart

	"""
	Implementation of RSA cryptography
	using samples of large numbers
	"""
	import random
	import sys
	import math

	from random import randrange

	import asyncio
	loop = asyncio.get_event_loop()

	async def hello():
	await asyncio.sleep(3)
	print('Hello!')

	if __name__ == '__main__':
	loop.run_until_complete(hello())