Discover AI: A Learning Guide - 51 hands-on labs for learning how AI actually works.

This is an offline app with 51 hands-on labs for learning how AI actually works, from neurons to agents and more...

**A bit of insight**

- 51 labs in 6 groups, from the basics (what a neuron is, gradient descent) through attention, RAG, agents, fine-tuning, quantization, serving and more

- Each lab has a short lesson beside it, readable in Plain or Standard mode

- Some of it actually runs rather than just animating:

- the attention lab runs a small trained transformer (1.37M params) inside the app

- the training labs train a tiny character-level model live as you move the sliders

- Works offline: no account, no telemetry

**How it was made**

I chose the topics, some background research and came up with the structure and the grouping. Claude and GPT Astra to help write the lesson text, and Grok as a second pass on references. There will be mistakes, so if you spot one, please tell me or open a PR.

If you teach this or work in a specialized area of AI, I'd love help expanding it: a new interactive lab, a better visualization, or a tweak that makes the cause and effect in an existing lab clearer. I'd also like to hear which labs are confusing and what's missing.

GitHub: https://github.com/Fazmin/AILearningGuide