milkersarac milkersarac

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.

Shallow

Real unit test (isolation, no children render)

Simple shallow

Calls:

constructor
render

We couldn’t find that file to show.

A Git Workflow for Agile Teams

Mar 2nd, 2009

An efficient workflow for developers in Agile teams that handles features and bugs while keeping a clean and sane history.

At Hashrocket we use git both internally and in our Agile mentoring and training. Git gives us the flexibility to design a version control workflow that meets the needs of either a fully Agile team or a team

	#!/bin/bash
	# MUSTAFA ILKER SARAC
	# This script can be used for building multiple react-native apps from a single git repo.
	# It needs master files for the default configurations.
	# master files are generally the copy of the current config files of that git repo.
	# If current state of the app changes i.e. adding new 3rd party components so package.json changes;
	# then one should be responsible to reflect these changes to the master files to be synced with the current state of the repo.
	# This script can be used to alter the current state, so that new apps could be generated with new names etc.
	# scriptAndroid.sh
	# "chmod +x ./scriptAndroid" to make script executable.

	#!/bin/bash
	from bs4 import BeautifulSoup
	import requests
	import urllib2
	import os
	import re, urlparse
	import time
	import pdb
	from interruptingcow import timeout

	// create file:
	sudo vim /usr/share/applications/intellij.desktop

	// add the following
	[Desktop Entry]
	Version=13.0
	Type=Application
	Terminal=false
	Icon[en_US]=/home/rob/.intellij-13/bin/idea.png
	Name[en_US]=IntelliJ

	function phow_caltech101()
	% PHOW_CALTECH101 Image classification in the Caltech-101 dataset
	% This program demonstrates how to use VLFeat to construct an image
	% classifier on the Caltech-101 data. The classifier uses PHOW
	% features (dense SIFT), spatial histograms of visual words, and a
	% Chi2 SVM. To speedup computation it uses VLFeat fast dense SIFT,
	% kd-trees, and homogeneous kernel map. The program also
	% demonstrates VLFeat PEGASOS SVM solver, although for this small
	% dataset other solvers such as LIBLINEAR can be more efficient.
	%

	function mosaic = sift_mosaic(im1, im2)
	% SIFT_MOSAIC Demonstrates matching two images using SIFT and RANSAC
	%
	% SIFT_MOSAIC demonstrates matching two images based on SIFT
	% features and RANSAC and computing their mosaic.
	%
	% SIFT_MOSAIC by itself runs the algorithm on two standard test
	% images. Use SIFT_MOSAIC(IM1,IM2) to compute the mosaic of two
	% custom images IM1 and IM2.

	#!/bin/bash

	# https://gist.github.com/robwierzbowski/5430952/
	# Create and push to a new github repo from the command line.
	# Grabs sensible defaults from the containing folder and `.gitconfig`.
	# Refinements welcome.

	# Gather constant vars
	CURRENTDIR=${PWD##*/}
	GITHUBUSER=$(git config github.user)