Discover gists

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

Pre-Transformer Models

PI is a TypeScript toolkit for building AI agents. It's a monorepo of packages that layer on top of each other: pi-ai handles LLM communication across providers, pi-agent-core adds the agent loop with tool calling, pi-coding-agent gives you a full coding agent with built-in tools, session persistence, and extensibility, and pi-tui provides a terminal UI for building CLI interfaces.

These are the same packages that power OpenClaw. This guide walks through each layer, progressively building up to a fully featured coding assistant with a terminal UI, session persistence, and custom tools.

By understanding how to compose these layers, you can build production-grade agentic software on your own terms, without being locked into a specific abstraction.

Pi was created by @badlogicgames. This is a great writeup from him that explains some of the design decisions made when creating it.

The stack

1. برومبت التخطيط المطوّر (The Planning Protocol)

[الدور والمسؤولية] أنت الآن تعمل بصفة Staff Software Engineer ومدير تقني Tech Lead. مهمتك التخطيط المعماري الصارم للمشروع التالي: [أدخل وصف المشروع هنا]

[قواعد ما قبل التتخطيط] قبل البدء بالبروتوكولات، يجب أن تطبق مبدأ "Think Before Coding":

GMK67 manual

English manual for the ZUOYA GMK67 Mechanical Keyboard. Made from the printed version (Original).

GMK67 manual
Description

	${C1}.:~!77?????7!~:.
	${C4}.^:. ${C1}:~7JYYYJJJJJJJYYYYY??~:
	${C4}~?J5J . ${C1}^?YYJJJJJJJJJJJJ??JJJJY55J!:
	${C4}!JJP5^ !??:${C1}.7JJ?JJ?7!~?JJJJJJJJJJJJJJ5P5?^
	${C4}^J?55: ^JYP${C1}J^!?J??~${C3}:...:${C1}!?JJJJJ???77JJJJ5P5?:
	${C4}.??JP! .Y5PP${C1}JJJJJ?J~${C3}......${C1}!7!~^${C3}::....${C1}^?J?JY5P5!
	${C4}~J?5PY! ?PPP${C1}5JJJJJ??J~${C3}.................${C1}!J?J?J55PJ.
	${C4}!JJ5${C1}PP57J55555YYY555Y?7^${C3}:.........:${C1}^~!7??JJJJ?J55P?
	${C1}^JJ5YYYYYJJJJJJJJJJJJYYYY?7~^${C3}:..${C1}^??JJJJJJJJJJJ?J555!
	${C1}.!?JJJJJJJJJJJJJJJJJJJJJJJJJJJ~${C3}::~~${C1}JJJ??JJJJJJJJJ?Y55Y.

	#!/bin/bash

	##
	# Pure BASH interactive CLI/TUI menu (single and multi-select/checkboxes)
	#
	# Author: Markus Geiger <mg@evolution515.net>
	# Last revised 2019-09-11
	#
	# ATTENTION! TO BE REFACTORED! FIRST DRAFT!
	#

	import json
	from datetime import UTC, datetime
	from functools import partial
	from typing import Annotated, Literal
	from uuid import UUID, uuid4

	from pydantic import (
	BaseModel,
	ConfigDict,
	EmailStr,

	"""
	The most atomic way to train and run inference for a GPT in pure, dependency-free Python.
	This file is the complete algorithm.
	Everything else is just efficiency.

	@karpathy
	"""

	import os # os.path.exists
	import math # math.log, math.exp