Ches Martin ches

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.

Claude Extended Thinking: The Ultimate Guide

When to use extended thinking across Claude models in the Claude App and Claude Code

Generated by Claude Opus 4.5 (with extended thinking)

What Is Extended Thinking?

FAQ on the xz-utils backdoor (CVE-2024-3094)

This is a living document. Everything in this document is made in good faith of being accurate, but like I just said; we don't yet know everything about what's going on.

Update: I've disabled comments as of 2025-01-26 to avoid everyone having notifications for something a year on if someone wants to suggest a correction. Folks are free to email to suggest corrections still, of course.

Background

{% if attachments -%} PDF: {%- for attachment in attachments | filterby("title", "endswith", ".pdf")%}

"[[{{ attachment.title }}]]" {%- endfor %} {%- endif %} {% if accessDate -%} accessDate: {{ accessDate | format('YYYY-MM-DD') }} {%- endif %}

Storing image assets in your repo and referencing in markdown

Create an assets branch and make the initial commit

git checkout --orphan assets
git reset --hard
cp /path/to/cat.png .
git add .
git commit -m 'Added cat picture'
git push -u origin assets

	# Simple httpbin deployment
	apiVersion: apps/v1
	kind: Deployment
	metadata:
	annotations:
	labels:
	app: httpbin-auth
	app.kubernetes.io/instance: httpbin-auth
	name: httpbin-auth
	spec:

	# Get editor completions based on the config schema
	"$schema" = 'https://starship.rs/config-schema.json'

	format = """
	$username\
	$hostname\
	$localip\
	$shlvl\
	$singularity\
	$kubernetes\

	# Based on https://stackoverflow.com/a/20855353/5555799
	# Store this file in ~/.bashrc.profiler and add this alias to your .bashrc:
	# alias profilebashstartup='exec bash --rcfile ~/.bashrc.profiler'

	TRACEFILE=$(mktemp /tmp/trace.XXX)
	TIMINGFILE=$(mktemp /tmp/timing.XXX)
	STARTTIME=$(date +%s.%N)
	exec 3>&2 2> >( tee $TRACEFILE \| sed -u 's/^.*$/now/' \| date -f - +%s.%N >$TIMINGFILE)
	set -x

	package com.guizmaii.utils

	import java.nio.charset.{Charset, StandardCharsets}
	import java.security.{Key, SecureRandom}

	import cats.effect.Sync
	import doobie.{Put, Read}
	import eu.timepit.refined.types.all.NonEmptyString
	import io.estatico.newtype.macros.newtype
	import javax.crypto.{Cipher, SecretKey, SecretKeyFactory}

	#!/bin/bash

	# this forces Arena into full screen mode on startup, set back to 3 to reset
	# note that if you go into the Arena "Graphics" preference panel, it will reset all of these
	# and you will need to run these commands again
	defaults write com.wizards.mtga "Screenmanager Fullscreen mode" -integer 0
	defaults write com.wizards.mtga "Screenmanager Resolution Use Native" -integer 0

	# you can also replace the long complicated integer bit with any other scaled 16:9
	# resolution your system supports.