Jack Louvton jackishere

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.

name	regression-dog
description	Review code changes for regressions.

Review code changes for behavioral differences between the before and after code.

Important:

Do NOT run tests, typechecks, linters, or build commands. CI already handles those. Focus your context budget entirely on reasoning about the code changes and its implications on logic/behavior/data/etc.

UPDATE (March 2020, thanks @ic): I don't know the exact AMI version but yum install docker now works on the latest Amazon Linux 2. The instructions below may still be relevant depending on the vintage AMI you are using.

Amazon changed the install in Linux 2. One no-longer using 'yum' See: https://aws.amazon.com/amazon-linux-2/release-notes/

Docker CE Install

sudo amazon-linux-extras install docker
sudo service docker start

Self Signed SSL Certificate for AWS ALB

Generate private key

$> openssl genrsa 2048 > my-private-key.pem

Generate certificate using private key, you will be prompted to fill some fields. Fill required fields randomly, except for Common Name fill it with *.amazonaws.com or your valid domain name

	# Source: https://gist.github.com/vfarcic/e79daf07ecdcb627e819b61aa851462d

	#########################################################
	# ow to Earn Billions With AI, ChatGPT, and Kubernetes? #
	# https://youtu.be/1ak_O5HgKcM #
	#########################################################

	# Additional Info:
	# - Cast AI: https://cast.ai/devopstoolkit

	#!/bin/bash
	folder="${1:-open}"
	profile="${2:-Default}"
	jq -r \
	'.roots.bookmark_bar.children[] \| select(.name == "'"${folder}"'") .children[].url' \
	"${HOME}/Library/Application Support/Google/Chrome/${profile}/Bookmarks" \
	\| while read url; do
	open "${url}"
	done

	# Run a container with the AWS CLI on a specific node:
	kubectl run -it debug --image amazon/aws-cli --command bash --overrides='{ "apiVersion": "apps/v1beta1", "spec": { "template": { "spec": { "nodeSelector": { "kubernetes.io/hostname": "<node-name>" } } } } }'

	# Configure KIAM role:
	kubectl run -it debug --image amazon/aws-cli --overrides='{"spec": {"template": {"metadata": {"annotations": {"iam.amazonaws.com/role": "my-cool-role"}}}}}' -- bash

	# TODO: replace :token, :user, and :repo
	curl -H "Authorization: token :token" \
	-H 'Accept: application/vnd.github.everest-preview+json' \
	"https://api.github.com/repos/:user/:repo/dispatches" \
	-d '{"event_type": "awesomeness", "client_payload": {"foo": "bar"}}'

	" ============= " VIMRC file for David Winterbottom (@codeinthehole) " ===========

	" Inspiration {{{
	" -----------
	" Videos:
	" - http://www.youtube.com/watch?v=aHm36-na4-4
	"
	" Articles:
	"
	" - http://alexpounds.com/blog/2014/06/06/the-vimrc-antiques-roadshow

	!pip install fastai
	!apt-get -qq install -y libsm6 libxext6 && pip install -q -U opencv-python
	import cv2
	from os import path
	from wheel.pep425tags import get_abbr_impl, get_impl_ver, get_abi_tag
	platform = '{}{}-{}'.format(get_abbr_impl(), get_impl_ver(), get_abi_tag())

	accelerator = 'cu80' if path.exists('/opt/bin/nvidia-smi') else 'cpu'

	!pip install -q http://download.pytorch.org/whl/{accelerator}/torch-0.3.0.post4-{platform}-linux_x86_64.whl torchvision