Steve Severance sseveran

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 calculate the alignment between BERT and spaCy tokens effectively and robustly

site: https://tamuhey.github.io/tokenizations/

Natural Language Processing (NLP) has made great progress in recent years because of neural networks, which allows us to solve various tasks with end-to-end architecture. However, many NLP systems still require language-specific pre- and post-processing, especially in tokenizations. In this article, I describe an algorithm that simplifies calculating correspondence between tokens (e.g. BERT vs. spaCy), one such process. And I introduce Python and Rust libraries that implement this algorithm. Here are the library and the demo site links:

repo: https://github.com/tamuhey/tokenizations

systemd for Administrators

Chronological list of the "systemd for Administrators" series published on 0pointer.net/blog:

	#! /usr/bin/env python
	# -- coding: utf-8 --
	# vim:fenc=utf-8
	#
	# Copyright © 2019 Pi-Yueh Chuang <pychuang@gwu.edu>
	#
	# Distributed under terms of the MIT license.

	"""An example of using tfp.optimizer.lbfgs_minimize to optimize a TensorFlow model.

	import com.github.tminglei.slickpg.ExPostgresProfile
	import slick.SlickException
	import slick.ast.ColumnOption.PrimaryKey
	import slick.ast.{ColumnOption, FieldSymbol, Insert, Node, Select}
	import slick.compiler.{InsertCompiler, Phase, QueryCompiler}
	import slick.dbio.{Effect, NoStream}
	import slick.jdbc.InsertBuilderResult
	import slick.lifted.Query

	// format: off

	var active = false;

	function changeRefer(details) {
	if (!active) return;

	for (var i = 0; i < details.requestHeaders.length; ++i) {
	if (details.requestHeaders[i].name === 'Referer') {
	details.requestHeaders[i].value = 'http://www.google.com/';
	break;
	}