Arthur Tazhitdinov osteotek

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.

strategy	server_net	server_port	isp	url_scheme	exit_code	img	error
$key	Digital Ocean	443	Bee Line Cable	http	0	✅
$key	Digital Ocean	443	Bee Line Cable	https	0	✅
$key	Digital Ocean	443	MTS PJSC	http	28	❌	curl: (28) Operation timed out after 10006 milliseconds with 0 bytes received
$key	Digital Ocean	443	MTS PJSC	https	28	❌	curl: (28) Connection timed out after 10005 milliseconds
$key	Digital Ocean	443	PJSC MegaFon	http	0	✅
$key	Digital Ocean	443	PJSC MegaFon	https	56	❌	curl: (56) Failure when receiving data from the peer
$key	Digital Ocean	443	Tele2 Russia	http	0	✅
$key	Digital Ocean	443	Tele2 Russia	https	0	✅
$key	Digital Ocean	5555	Bee Line Cable	http	0	✅

WSL 2 with CUDA

Set up Windows Subsystem for Linux (version 2) with CUDA support + TensorFlow.

Before you start

You must be on Windows 10 21H2 or above.

Note: On my system 21H2 could not be updated to. I ended up with a bricked install as Windows tried to install Windows 11 on my unsupported CPU. I recommend just installing Windows 10 21H2 directly from an ISO.
You don't have to be on OS build 20140 or above as some sources state. My build: 19044.1469
Install the latest "game ready driver" for your card.

XIX Задача о поиске элемента ⭐⭐

Дан упорядоченный массив чисел размером N Нужно реализовать алгоритм поиска вхождения упорядоченного подмассива размера M, где M << N

func isInclude(array int[], subarray []int) bool

assert(isInclude([1, 2, 3, 5, 7, 9, 11], []) == true) 
assert(isInclude([1, 2, 3, 5, 7, 9, 11], [3, 5, 7]) == true)

The introduction to Reactive Programming you've been missing

(by @andrestaltz)

This tutorial as a series of videos

If you prefer to watch video tutorials with live-coding, then check out this series I recorded with the same contents as in this article: Egghead.io - Introduction to Reactive Programming.

	/* wide */
	.wide .markdown-preview-sizer {
	max-width: unset !important;
	}

	.life-calendar p a.internal-link {
	display: inline-block;
	}

	func partition<C: Comparable>(v: C[], left: Int, right: Int) -> Int {
	var i = left
	for j in (left + 1)..(right + 1) {
	if v[j] < v[left] {
	i++
	(v[i], v[j]) = (v[j], v[i])
	}
	}
	(v[i], v[left]) = (v[left], v[i])
	return i

	OIFS=$IFS;
	IFS=",";

	# fill in your details here
	dbname=DBNAME
	user=USERNAME
	pass=PASSWORD
	host=HOSTNAME:PORT

	# first get all collections in the database