Machine-Learning-Interviews vs caveman
A neutral, constraint-first comparison - live GitHub stats and typed relationships, not marketing.
| Machine-Learning-Interviews | caveman | |
|---|---|---|
| Tagline | Repository for preparing AI/ML technical interviews with chapters on general coding, ML coding, fundamentals/breadth (including LLMs and multimodal AI), system design, behavioral questions, and more. | Cuts 65% of tokens in AI coding agent responses. |
| Stars | 8.5k | 86k |
| Forks | 1.5k | 4.8k |
| Open issues | 12 | 370 |
| Language | Jupyter Notebook | JavaScript |
| License | MIT | MIT |
| Last pushed | Jun 20, 2026 | Jul 3, 2026 |
| Categories | Inference & Serving, Model Training, Developer Tools | LLM Frameworks, Developer Tools |
Machine-Learning-Interviews
A guide for Machine Learning/AI engineering interviews at big tech companies such as FAANG. It covers various topics including General Coding, ML Coding, ML Fundamentals/Breadth with a focus on Generative AI/LLMs and multimodal AI like Vision-Language Models (VLMs), Agentic AI Systems, and Behavioral interview practices.
Jupyter Notebook
caveman
A skill/plugin for various AI agents, including Claude Code and other platforms, reducing output tokens for more concise, direct communication while maintaining accuracy.
JavaScript