eczn* eczn

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.

%GetOptimizationStatus return a set of bitwise flags instead of a single value, to access the value, you need to take the binary representation of the returned value. Now, for example, if 65 is returned, the binary representation is the following:

(65).toString(2).padStart(12, '0');
// 000001000001

Each binary digit acts as a boolean with the following meaning:

	Latency Comparison Numbers (~2012)
	----------------------------------
	L1 cache reference 0.5 ns
	Branch mispredict 5 ns
	L2 cache reference 7 ns 14x L1 cache
	Mutex lock/unlock 25 ns
	Main memory reference 100 ns 20x L2 cache, 200x L1 cache
	Compress 1K bytes with Zippy 3,000 ns 3 us
	Send 1K bytes over 1 Gbps network 10,000 ns 10 us
	Read 4K randomly from SSD* 150,000 ns 150 us ~1GB/sec SSD

	Per https://code.google.com/p/v8/codesearch#v8/trunk/src/runtime.cc


	%CreateSymbol
	%CreatePrivateSymbol
	%CreateGlobalPrivateSymbol
	%NewSymbolWrapper
	%SymbolDescription
	%SymbolRegistry
	%SymbolIsPrivate

	; ___ _ __ ___ __ ___
	; / __\|_ _ __ _\| \|_____ / /\| __\|/ \_ )
	; \__ \ ' \/ _` \| / / -_) _ \__ \ () / /
	; \|___/_\|\|_\__,_\|_\_\___\___/___/\__/___\|

	; An annotated version of the snake example from Nick Morgan's 6502 assembly tutorial
	; on http://skilldrick.github.io/easy6502/ that I created as an exercise for myself
	; to learn a little bit about assembly. I think I understood everything, but I may
	; also be completely wrong :-)

	/*
	UPDATED for 2023 - Now much simpler. The old tricks are no longer needed.

	The following code makes an 800×600 canvas that is always as sharp as possible for the device.

	You still draw on it as if it's the logical size (800×600 in this case), but everything just
	looks sharper on high-DPI screens. Regular non-sharp screens are not affected.
	*/

	const width = 800

	/*
	* https://github.com/netnr/workers
	*
	* 2019-10-12 - 2022-05-05
	* netnr
	*
	* https://github.com/Rongronggg9/rsstt-img-relay
	*
	* 2021-09-13 - 2022-05-29
	* modified by Rongronggg9

	#include <linux/init.h>
	#include <linux/module.h>
	#include <linux/kernel.h>
	#include <linux/list.h>
	#include <linux/slab.h>

	struct birthday {
	int day;
	int month;
	int year;

	// my brain decided to ask the question: yknow, i want you to think about the y combinator --
	// like, what is it. like what the fuck girl, cmon, you have a comp sci degree, you should know this, and understand it and shit

	// and so i was like fiiiiiiiiiiiiiiine gosh, lets see if typescript can handle the typing, and play around with it

	// so i looked up a javascript implementation, and played with the type defintion until it
	// matched up and then i was like oh: thats what the type definition of the functions in it are.
	// i get it now. that's pretty cool. the main interesting thing is a the inner function that takes itself
	// and returns the function initially passed to the outer function. neato.

	# 设置
	git config --global https.proxy http://127.0.0.1:1080
	git config --global http.proxy https://127.0.0.1:1080

	# 取消
	git config --global --unset http.proxy
	git config --global --unset https.proxy

	# 删除 npm proxy 配置
	npm config delete proxy