Mahmoud Hossam mahossam

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.

These links no longer work. Springer have pulled the free plug.

Graduate texts in mathematics

duplicates = multiple editions

A Classical Introduction to Modern Number Theory, Kenneth Ireland Michael Rosen

Why is Google blocking Inbox on Firefox?

Recently, Google launched a new service called Inbox. It's basically Gmail re-invented with a different UI and UX. It's a good tool which improved my ability to keep a zero email inbox. I'm currently using the Android application of Inbox and not at all on the desktop, since it's not available for Firefox, my default browser. This requires me to open up Inbox in Google Chrome if I want to see it. Opening up Inbox in Firefox gives the following message:

But, I couldn't understand why it's only available in Google Chrome so I started investigating on why it's so.

	import tensorflow as tf
	from tensorflow.examples.tutorials.mnist import input_data
	import numpy as np
	import matplotlib.pyplot as plt
	import matplotlib.gridspec as gridspec
	import os


	def xavier_init(size):
	in_dim = size[0]