Skip to content

Instantly share code, notes, and snippets.

Discover gists

@Maharshi-Pandya
Maharshi-Pandya / contemplative-llms.txt
Last active January 7, 2025 02:35
"Contemplative reasoning" response style for LLMs like Claude and GPT-4o
You are an assistant that engages in extremely thorough, self-questioning reasoning. Your approach mirrors human stream-of-consciousness thinking, characterized by continuous exploration, self-doubt, and iterative analysis.
## Core Principles
1. EXPLORATION OVER CONCLUSION
- Never rush to conclusions
- Keep exploring until a solution emerges naturally from the evidence
- If uncertain, continue reasoning indefinitely
- Question every assumption and inference
@holazt
holazt / IP-DNS-swift-switch.cmd
Created January 7, 2017 05:05
Windows 下 IP 和 DNS 快速切换(批处理)
@echo off
title IP 和 DNS 快速切换
color 0a
rem 以下几个参数用户自行配置
rem name这个值，是你电脑网络连接的名称，
rem 需要到网络适配器中去查看
rem 大部分name值都是”本地连接”，
@AndreiTelteu
AndreiTelteu / Laravel stream large file with buffer .php
Created February 7, 2023 21:50
Laravel stream large file from disk with buffer.
<?php
// inspired by https://github.com/imanghafoori1/laravel-video
// if you need this for video, this does not support seek.
// laravel-video supports seek and chunks, so use that for video.
Route::get('/big-file-stream', function () {
$filePath = \Storage::disk('local')->path('video.mp4');
$fileStream = \Storage::disk('local')->readStream('video.mp4');
@ricardoalcocer
ricardoalcocer / learning_guitar.md
Last active January 7, 2025 02:29
Learning Guitar

A Hacker's Guide to learning rhythm and lead guitar FAST!

I've been playing guitar for over 30 years. I never took formal lessons - only ocassional ones targeted to a specific topic. I love the discovery process and the relationship I've created with the instrument.

Five years ago or so, I had an a-ha moment, which fundamentaly changed the way I approach my learning of the guitar. After internalizing all the content I consumed, I thing I've come up with a formula for learning both rhythm and lead guitar in a very streamlined and systematic fashion. This method will teach you how to find chords across the entire fretboard so you can create chord progresssions for your own songs, or to make it easier to figure out the chords of your favorite songs.

However, what I like the most about it is that it gets you ready to play lead guitar, without putting too much emphasis on the pentatonic scale. Also, it teaches the guitar from the standpoint of understanding its symetry, and dare I say, the mathematics

@RyoKosaka
RyoKosaka / XP120SD_BLE.ino
Created November 11, 2020 08:25
////////////////////////////////////////// SETTING VALUE ////////////////////////////////////////////
//Determine the setting value.
//By changing the number in this array you can set sensitivity, threshold and so on.
byte XP[10] = {
100, //sensitivity
3, //threshold
10, //scan time
30, //mask time
@mbinna
mbinna / effective_modern_cmake.md
Last active January 7, 2025 02:25
Effective Modern CMake

Effective Modern CMake

Getting Started

For a brief user-level introduction to CMake, watch C++ Weekly, Episode 78, Intro to CMake by Jason Turner. LLVM’s CMake Primer provides a good high-level introduction to the CMake syntax. Go read it now.

After that, watch Mathieu Ropert’s CppCon 2017 talk Using Modern CMake Patterns to Enforce a Good Modular Design (slides). It provides a thorough explanation of what modern CMake is and why it is so much better than “old school” CMake. The modular design ideas in this talk are based on the book [Large-Scale C++ Software Design](https://www.amazon.de/Large-Scale-Soft

@fredbenenson
fredbenenson / kickstarter_sql_style_guide.md
Last active January 7, 2025 02:24
Kickstarter SQL Style Guide
layout title description tags
default
SQL Style Guide
A guide to writing clean, clear, and consistent SQL.
data
process

Purpose

@ruvnet
ruvnet / SynthLang.md
Created January 5, 2025 03:18
SynthLang is a hyper-efficient prompt language designed to optimize interactions with Large Language Models (LLMs) like GPT-4o by leveraging logographical scripts and symbolic constructs.

SynthLang: A Hyper-Efficient Prompt Language for AI

SynthLang is a hyper-efficient prompt language designed to optimize interactions with Large Language Models (LLMs) like GPT-4o by leveraging logographical scripts and symbolic constructs. By compressing complex instructions into fewer tokens (reducing token usage by 40–70%), SynthLang significantly lowers inference latency, making it ideal for latency-sensitive applications such as high-frequency trading, real-time analytics, and compliance checks.

Additionally, SynthLang mitigates English-centric biases in multilingual models, enhancing information density and ensuring more equitable performance across diverse languages. Its scalable design maintains or improves task performance in translation, summarization, and question-answering, fostering faster, fairer, and more efficient AI-driven solutions.

Large Language Models (LLMs) such as GPT-4o and Llama-2 exhibit English-dominant biases in intermediate embeddings, leading to inefficient and oft

@ax3l
ax3l / CUDA_Compilers.md
Last active January 7, 2025 02:15
CUDA Compilers