Each lab's own courses, cookbooks and docs — Claude, ChatGPT, Gemini, Llama, Mistral — and how to run open models yourself.
I keep a directory of free ways to learn at brianpfeil.com/learn, sorted by goal, and every link opens without signing in. This is one of its paths: 19 resources, with the ones I'd start with marked ⭐.
Anthropic · Claude
- Anthropic Academy ⭐: Anthropic's free courses: Claude 101, Claude Code, the API and MCP.
- Courses on GitHub: Anthropic's notebook courses: API fundamentals, prompting, evaluations and tool use.
- Interactive prompt engineering tutorial: A nine-chapter, hands-on course in prompt engineering.
- Claude Cookbooks: Copyable recipes for building with Claude: RAG, tools, agents and more.
- Claude docs: The Claude API documentation, guides and prompt library.
- Claude Code docs: How to use Claude Code, Anthropic's coding agent, in your terminal and editor.
OpenAI · ChatGPT
- OpenAI Academy: OpenAI's free courses, livestreams and events for every level.
- OpenAI Cookbook: Example code and guides for building with OpenAI's models.
- API docs: OpenAI's API guides and reference.
Google · Gemini
- Gemini API docs: Guides and quickstarts for building with Google's Gemini models.
- Google AI Studio: Try Gemini models in the browser, free, and export working code.
- Gemini Cookbook: Notebooks and examples for the Gemini API.
Meta · Llama
- Llama Cookbook: Meta's recipes for running, fine-tuning and building with Llama models.
Mistral AI
- Mistral docs: Guides for Mistral's open and commercial models.
Run models on your own machine
- Ollama: The easiest way to run open models on your own laptop.
- MLX LM: Run and fine-tune language models fast on Apple silicon Macs.
- llama.cpp: The engine that makes local models run on everyday hardware.
Made here
- Agentic Loop Engineering: Designing tight, verifiable agent loops with Claude Code — the verify step, tools, and feedback.
- mlx-lm: Run, quantize, serve, and fine-tune LLMs locally on Apple Silicon with Apple's mlx-lm — the CLI and Python surfaces, from first principles, every example verified on an M4 Pro.
The up-to-date list, and the other paths (code, cloud, AI, kids and more), is at brianpfeil.com/learn/models/.
Top comments (0)