Akash Kakkar akash07k
I like to help folks with their Electron and React problems, but I often have to repeat the same things over and over again. So here is a short guide to some of the most common questions and issues people have.
| # NOTE - THIS SCRIPT IS NOW OBSOLETE - SEE MY OTHER REPO FOR A MUCH MORE COMPREHENSIVE TOOL: https://github.com/ThioJoe/Windows-Super-God-Mode | |
| # Get All Shell Folder Shortcuts Script (Updated 8/10/2024) | |
| # Original source: https://gist.github.com/ThioJoe/16eac0ea7d586c4edba41b454b58b225 | |
| # This PowerShell script is designed to find and create shortcuts for all special shell folders in Windows. | |
| # These folders can be identified through their unique Class Identifiers (CLSIDs) or by their names. | |
| # The script also generates CSV files listing these folders and associated tasks/links. | |
| # How to Use: | |
| # 1. Open PowerShell and navigate to the path containing this script using the 'cd' command. |
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.