Dmitrij Koniajev dimchansky

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.

Dappcon workshop: How to become ethereum core developer - https://git.io/fjN4L

Workshop goal

Impliment EIP-2028 Transaction data gas cost reduction

Requirements

golang https://golang.org/doc/install

Prepare enveiroment

For development

clone geth from workshop branch - https://github.com/JekaMas/go-ethereum/tree/workshop (there are some simplifications related to hardforks for workshop purposes)

Run go install and

gogitlocalstats -add /path/to/folder will scan that folder and its subdirectories for repositories to scan
gogitlocalstats -email [email protected] will generate a CLI stats graph representing the last 6 months of activity for the passed email. You can configure the default in main.go, so you can run gogitlocalstats without parameters.

Being able to pass an email as param makes it possible to scan repos for collaborators activity as well.

Applied Functional Programming with Scala - Notes

1. Mastering Functions

A function is a mapping from one set, called a domain, to another set, called the codomain. A function associates every element in the domain with exactly one element in the codomain. In Scala, both domain and codomain are types.

val square : Int => Int = x => x * x

	{- cabal:
	build-depends: base
	, scotty
	, aeson
	, http-client-tls
	, http-client
	, bytestring
	, text
	, http-types
	-}

	#!/usr/bin/env bash

	# Small shell script to more easily automatically download and transcribe live stream VODs.
	# This uses YT-DLP, ffmpeg and the CPP version of Whisper: https://github.com/ggerganov/whisper.cpp
	# Use `./transcribe-vod help` to print help info.

	# MIT License

	# Copyright (c) 2022 Daniils Petrovs

	seta r_mode "-1"
	seta r_customwidth "5120"
	seta r_customheight "2880"
	seta cg_fov "115"
	seta cg_gunCorrectFOV "1"
	seta cl_renderer "opengl2"
	seta r_allowSoftwareGL "0"
	seta r_ignoreGLErrors "1"
	seta r_smp "1"
	seta r_displayrefresh "0"

	package main

	// Example of writing a binary file of float structs.

	import (
	"log"
	"os"
	"reflect"
	"testing"
	"unsafe"

	#include <iostream>
	#include <random>
	#include <chrono>
	#include <x86intrin.h>
	#include <cassert>

	// Runtime evaluation for squared Eucliden distance functions
	// - fvec_L2_sqr_ref: naive reference impl from Faiss
	// - fvec_L2_sqr_sse: SSE impl from Faiss
	// - fvec_L2_sqr_avx: AVX impl from Faiss