Learn

Your first conversation with a local AI model, in under 10 minutes.

Why some models feel smarter than others, what the numbers in model names mean, and how to pick the right one for your hardware and your task.

What actually happens when you type a prompt. Tokens, transformers, attention, and how they fit together.

The full memory equation, why long conversations cost more, and how quantization actually works under the hood.

Set up a real chat interface, use your model for writing and research, give it your documents, and start automating.

What makes an agent different from a chatbot, the main agent types and their use cases, how to evaluate them, and when they're the wrong tool.

How to call models from your own code, set up function calling and MCP, build a RAG pipeline, and test what you build.

When local models aren't enough, what cloud APIs offer, and how to combine both for the best balance of cost, quality, and privacy.

Skills, MCP servers, memory tools, and IDE config files that turn a basic setup into something you actually rely on.

Local media generation (images, video, music, speech), how to evaluate models yourself, and when fine-tuning is worth the effort.

The specific techniques changing local AI right now: better compression, longer context, on-device inference, and what they mean for your hardware.