GitHub Trending

multica-ai/andrej-karpathy-skills — A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Kar

36 sec read12 views0 listens

137,069 stars | 14,057 forks | Unknown

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

What it does

This repository provides guidelines to improve the coding behavior of large language models, inspired by Andrej Karpathy's insights on common pitfalls. It aims to enhance model output quality through four key principles: thinking before coding, simplicity first, surgical changes, and goal-driven execution.

Why it matters: Learn how to make large language models code better with these principles derived from Andrej Karpathy's insights!

View on GitHub

Trending today with 2014 new stars

Want to create content about this repo? Use Nemati AI tools to generate articles, tutorials, and social posts.

Google DeepMind's powerful AI co-mathematician

Key Highlights from The Rundown AI Newsletter DeepMind's New Language Model, AlphaCode 2.0 Achievement: DeepMind’s new language model has achieved a score of 95% on the HumanEval benchmark. Comparison to GPT-4: This places it just behind Anthropic C...

Ali Nemati

AI & Machine LearningMay 101m & 4 s read

How to Build a Cost-Aware LLM Routing System with NadirClaw Using Local Prompt Classification and Gemini Model Switching

The tutorial you've referenced provides an in-depth guide to building a cost-aware Large Language Model (LLM) routing system using NadirClaw, which is designed to optimize the use of different AI models based on prompt complexity and other factors. H...

Ali Nemati

AI & Machine LearningMay 1026 sec read

Flux Attention halves inference cost on long contexts

Flux Attention reduces the computational cost of long-context inference in large language models by allowing transformer layers to dynamically choose between dense and sparse attention, achieving up to 2.8 times speedup during prefill phases without ...

Ali Nemati

AI & Machine LearningMay 91m & 6 s read

How I Built an AI Emoji Generator with Next.js 15 & Cloudflare Workers AI

Creating a tool like ForEmoji.com is a fascinating project that leverages cutting-edge technologies such as generative AI and machine learning to produce creative content. Your approach to building a fallback system for text-to-image generation, opti...

Ali Nemati

AI & Machine LearningMay 71m & 3 s read

The Art of Model Orchestration: Building RouteLLM

In the article about RouteLLM, the author discusses a sophisticated approach to managing and optimizing interactions with AI models, particularly focusing on reducing costs and improving efficiency. Here are the key points: Problem Statement: The pri...

Ali Nemati

multica-ai/andrej-karpathy-skills — A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Kar

What it does

Related Articles

Google DeepMind's powerful AI co-mathematician

How to Build a Cost-Aware LLM Routing System with NadirClaw Using Local Prompt Classification and Gemini Model Switching

Flux Attention halves inference cost on long contexts

How I Built an AI Emoji Generator with Next.js 15 & Cloudflare Workers AI

The Art of Model Orchestration: Building RouteLLM