Discover gists · GitHub
Skip to content

Instantly share code, notes, and snippets.

@johnib
johnib / claude-snowflake-mcp-integration-guide.sql
Last active October 21, 2026 21:02
Setup script for connecting Claude.ai to Snowflake via native MCP connector with OAuth. Includes role configuration, troubleshooting guide, and known limitations (read-only not enforceable due to Claude.ai OAuth scope limitation).
@mikewlange
mikewlange / start-here-a-gentle-introduction (1).ipynb
Created December 4, 2019 17:44
/CreditWorkup/Data/start-here-a-gentle-introduction (1).ipynb
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.

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.

‍🏃‍♂️ 122km ██████▌░░░░░░░░░░░░░
🏂 117km ██████▍░░░░░░░░░░░░░
🚶‍♂️ 115km ██████▏░░░░░░░░░░░░░
🥾 11km ▍░░░░░░░░░░░░░░░░░░░
🚴‍♂️ 0km ░░░░░░░░░░░░░░░░░░░░
363km total
@komikndr
komikndr / llamacpp-opencode.md
Last active October 21, 2026 20:46
This is my OpenCode setup for local models, mainly using a customized llama.cpp configuration.

What it is

This is my OpenCode setup for local models, mainly using a customized llama.cpp configuration.

For Qwen 3.8, DeepSeek V4, and Glimmer, the models are already trained to support reasoning effort levels. Depending on the model, these may be exposed as low, medium, high, xhigh, or as low, high, and max.

For models that support reasoning but were not trained with explicit reasoning-effort levels, such as the Qwen 3.5 and 3.6 variants, I use a token budget to limit the amount of reasoning.

Although Qwen 3.8 has built-in reasoning-effort levels, I still apply a maximum reasoning-token cap for each effort level.

Although the llama.cpp CLI flags specify preserve_thinking and a default reasoning budget, these can still be overridden through the API, so this works fine for my setup.

@cruithne3753
cruithne3753 / Hide_Upgrade_Your_Plan_ALL.reg
Last active October 21, 2026 20:38
Hides the 'Upgrade your plan' button in Office 2021/2024 AND Microsoft 365. (Includes Restore option as well.)
Windows Registry Editor Version 5.00
; Hides the 'Upgrade your plan' button in Office 2021/2024 AND Microsoft 365.
; Sets three Office feature switches to false; Office ignores the ones that don't apply to your license.
; No admin rights needed (current user only). Close and reopen Office apps after importing.
; To undo: import Restore_Upgrade_Your_Plan_ALL.reg
[HKEY_CURRENT_USER\Software\Microsoft\Office\16.0\Common\ExperimentConfigs\ExternalFeatureOverrides\word]
"Microsoft.Office.Licensing.ShowPerpetualUpgrade"="false"
"Microsoft.Office.Licensing.EnablePerpetualUpgrade"="false"

JavaScript DSA — Logic-Building Practice Sheet

Instructions

  • Solve all 15 questions using JavaScript.
  • Focus on logic, loops, conditions, arrays, strings, and objects.
  • Avoid built-in methods wherever the question explicitly restricts them.
  • Test your functions with the provided examples.
  • Try solving each problem independently before asking for hints.
<!DOCTYPE html>
<html>
<head>
<title></title>
<meta charset="utf-8" />
<script src="Scripts/jquery-1.9.1.min.js"></script>
<link href="Content/bootstrap.min.css" rel="stylesheet" />
<script src="Scripts/isRockFx.js"></script>
<script>
$(function () {
@rawnullbyte
rawnullbyte / Brawl Stars Reverse Engineering Guide.md
Last active October 21, 2026 20:27
Brawl Stars Reverse Engineering Guide

Brawl Stars Reverse Engineering Guide


1. Anatomy of an Android APK

An Android Application Package (.apk) is essentially a ZIP archive that contains all the resources, code, and metadata required to run an application on the Android operating system.

Component Format / Type Purpose Relevance to Modding

NixOS Binary Cache Proxy

nixos-cache-proxy.cofob.dev is a simple reverse proxy to cache.nixos.org, running over the Cloudflare network and utilizing its cache.

It is intended for use if you:

  1. Do not have access to cache.nixos.org (e.g., your government has blocked it).
  2. You experience low speed on cache.nixos.org.

How to Use It