| <!DOCTYPE html> | |
| <html lang="ar" dir="rtl"> | |
| <head> | |
| <meta charset="UTF-8"> | |
| <meta name="viewport" content="width=device-width, initial-scale=1.0"> | |
| <title>سهل | SAHEL</title> | |
| <style> | |
| *{ | |
| margin:0; |
| 1. Open CMD as Administrator | |
| 2. Paste the following commands into the Cmd: One by one, follow the order. | |
| cscript slmgr.vbs /ipk "SERIAL NUMBER HERE" | |
| Replace SERIAL NUMBER HER with any of these, according your Windows 10 installation type. | |
| Home/Core TX9XD-98N7V-6WMQ6-BX7FG-H8Q99 | |
| Home/Core (Country Specific) PVMJN-6DFY6-9CCP6-7BKTT-D3WVR | |
| Home/Core (Single Language) 7HNRX-D7KGG-3K4RQ-4WPJ4-YTDFH |
| options: | |
| cooldown-after-mute: 240 seconds | |
| kick-window: 240 seconds | |
| slur-mute-time: 10 minutes | |
| spam-mute-time: 15 seconds | |
| max-warnings: 3 | |
| # NORMALIZATION | |
| function normalize(t: text, stripSpaces: boolean) :: text: | |
| set {_res} to {_t} in lowercase |
Starred by @upsetbit (cai.).
| <!DOCTYPE html> | |
| <html lang="en"> | |
| <head> | |
| <meta charset="UTF-8"> | |
| <meta name="viewport" content="width=device-width, initial-scale=1.0"> | |
| <title>Do you love me?</title> | |
| <link rel="preconnect" href="https://fonts.googleapis.com"> | |
| <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin> | |
| <link href="https://fonts.googleapis.com/css2?family=Press+Start+2P&display=swap" rel="stylesheet"> | |
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.
| # Program make a simple calculator that can add, subtract, multiply and divide using functions | |
| # define functions | |
| def add(x, y): | |
| """This function adds two numbers""" | |
| return x + y | |
| def subtract(x, y): | |
| """This function subtracts two numbers""" |
