Michael operates on out-of-favor industries to find best-of-breed companies trading at steep discounts.
Michael focuses on free cash flow and private market valuation as he scours out-of-favor industries and overlooked securities.
Michael operates on out-of-favor industries to find best-of-breed companies trading at steep discounts.
Michael focuses on free cash flow and private market valuation as he scours out-of-favor industries and overlooked securities.
| """ | |
| 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 |
Resonance: A Plague Tale Legacy Trainer PC utility featuring Unlock All Chapters, Unlock Everything, Change Resonance Points, Resonance Points Editor, Game Speed, Configurable Hotkeys, reusable profiles, quick actions, and Windows configuration management.
Breathedge 2 Trainer + Save Editor 2026 for Windows with Survival Profiles, Oxygen / Health Utility, Inventory Editor, Resource Editor, Crafting Support, Tool Durability Settings, profiles, hotkeys, configs, and a clean desktop workflow.
Dungeon Settlers Trainer + Resource Editor 2026 for Windows with 30 current options including God Mode, No Hunger, No Energy Drain, No Stress, weight/health/XP editing, Unlock Skills, Gold editor, Free Recruits, Max Population, building unlocks, weather selection, Game Speed, and Slow Motion.
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.
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.
The Blood of Dawnwalker Trainer + Mod Manager 2026 for Windows with Human / Vampire Profiles, Day / Night Presets, Time Management Controls, Gameplay Quick Profiles, Inventory / Progression Utility, Mod Install, profiles, hotkeys, configs, and a clean desktop workflow.
Onimusha: Way of the Sword Trainer PC utility featuring Player Controls, Resource Controls, Damage Settings, Enemy Controls, Game Speed, Quick Actions, reusable profiles, quick actions, and Windows configuration management.