Discover gists

Interpreted Context Methodology (ICM): A Complete Guide

What Is ICM?

The Interpreted Context Methodology (ICM) is a folder-based architecture for managing AI agent context. Instead of loading an entire codebase or writing monolithic prompt files, ICM organizes agent work into workspaces and stages — each with explicit declarations of what to load, what to skip, and exactly what the agent should do.

The core insight: AI agents perform better when they receive narrow, relevant context rather than broad, general context. ICM makes this narrowing systematic and repeatable.

Origin

Compilers for Machine Learning

A hands-on one semester course where students build their own compiler from scratch, starting from elementwise programs and ending with training SOTA LLMs on GPUs. This course aggressively builds on the previous week, and is an exercise in slop management. If you let any slop in early, it will compound and you will not finish the class.

Course description: This course covers the design and implementation of a modern machine learning compiler, and examines the interaction between IR design, hardware capabilities, and the structure of machine learning programs. Topics covered include term rewriting, code generation, movement operators, kernel fusion, memory hierarchies, GPU architecture, automatic differentiation, and flash attention. It is a project course, providing experience with performance-oriented programming, managing a codebase that grows all semester, and working in 1 or 2 person teams, culminating in a compiler capable of training modern LLMs.

Prerequisites: This c

ZSH CheatSheet

This is a cheat sheet for how to perform various actions to ZSH, which can be tricky to find on the web as the syntax is not intuitive and it is generally not very well-documented.

Strings

Description	Syntax
Get the length of a string	`${#VARNAME}`
Get a single character	`${VARNAME[index]}`

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.

Anti-hype LLM reading list

Goals: Add links that are reasonable and good explanations of how stuff works. No hype and no vendor content if possible. Practical first-hand accounts of models in prod eagerly sought.

Foundational Concepts

	#!/bin/bash

	PARAMS=('-m 6 -q 70 -mt -af -progress')

	if [ $# -ne 0 ]; then
	PARAMS=$@;
	fi

	cd $(pwd)

	#!/usr/bin/env bash

	# Small shell script to more easily automatically download and transcribe live stream VODs.
	# This uses YT-DLP, ffmpeg and the CPP version of Whisper: https://github.com/ggerganov/whisper.cpp
	# Use `./transcribe-vod help` to print help info.

	# MIT License

	# Copyright (c) 2022 Daniils Petrovs

	#!/bin/sh

	# Credits: http://stackoverflow.com/a/750191

	git filter-branch -f --env-filter "
	GIT_AUTHOR_NAME='Newname'
	GIT_AUTHOR_EMAIL='new@email'
	GIT_COMMITTER_NAME='Newname'
	GIT_COMMITTER_EMAIL='new@email'
	" HEAD

	According to all known laws of aviation, there is no way a bee should be able to fly.
	Its wings are too small to get its fat little body off the ground.
	The bee, of course, flies anyway because bees don't care what humans think is impossible.
	Yellow, black. Yellow, black. Yellow, black. Yellow, black.
	Ooh, black and yellow!
	Let's shake it up a little.
	Barry! Breakfast is ready!
	Coming!
	Hang on a second.
	Hello?