◆ SafeZone AI Learn

theory → playground → your own GPU

Learn the AI stack by watching it work.

Every lesson pairs real theory with a live experiment: draw a maze and race A* against Dijkstra, train an agent that teaches itself Pac-Man, distil and interrogate an LLM. Nothing is a mock-up — every figure runs live, on your own machine, nothing hidden.

Start with the theory → Open the playground

Pick a track

The full ML · AI · DevOps stack is live — 94 interactive lessons across eight tracks, every module ending in a graded self-check.

Mathematical Foundations

Optimization, linear algebra, probability and information theory — the mathematics under every model, told as one story from Gauss to Shannon.

26 lessons · liveStart →

Practitioner's Toolkit

Environments, GPUs and CUDA, vectorization and reproducibility — the professional workbench that makes everything else possible.

5 lessons · liveStart →

Machine Learning

Regression to gradient boosting, clustering to recommenders — watch models fit, overfit and generalise on data you can poke.

15 lessons · liveStart →

Forecasting

Decomposition to Kalman filters to global neural forecasters — time series with the backtesting rigor most tutorials skip.

7 lessons · liveStart →

Deep Learning

Backpropagation by hand up to transformers and diffusion — watch signals propagate, gradients vanish and attention route.

9 lessons · liveStart →

Reinforcement Learning

Search → RL → agentic LLMs: from a maze you draw, through deep RL on your own GPU, to AI agents and their reliability.

8 lessons · liveStart →

LLM Engineering

Tokenisers, attention, scaling laws, RAG and evals — the stack behind every AI product, opened up live in the page.

10 lessons · liveStart →

DevOps & Cloud

Containers, CI/CD, infrastructure as code and cloud deployment (AWS · Azure · GCP) — ship what you build, the way this platform ships itself.

13 lessons · liveStart →

New here? Begin with the orientation story — How data science ate the world →

Learn

Every algorithm and method, explained properly — the idea, the math, pseudocode, and when to reach for it.

Read the theory →

Play

The practical half. Draw a maze, race the algorithms, train an agent, teach an LLM — and see every result animate live.

Open the playground →

Your machine

The playground computes on your GPU via a small worker you run locally. Your models and API keys never leave it.

How it works →

Inside the RL track

Each lesson reuses the one below it. Follow the path top to bottom, or jump anywhere.

  1. 1

    Grid maze worker

    Classic pathfinding on a maze you draw — BFS, DFS, Dijkstra, A*, greedy and bidirectional search, racing side by side.

    Theory · Try it
  2. 2

    Real streets worker

    The very same searches, now racing over a live OpenStreetMap road graph. A* vs Dijkstra, made tangible on real cities.

    Theory · Try it
  3. 3

    Deep RL GPU

    An agent learns Pac-Man & Pong straight from the pixels — the DQN family and the policy-gradient family (REINFORCE, A2C, PPO).

    Theory · Try it
  4. 4

    Teach an LLM GPU

    Distil a large teacher into a small student model — supervised fine-tuning, then DPO, the RL-from-AI-feedback step.

    Theory · Try it
  5. 5

    Reasoning Lab GPU

    Wire prompted agents into generate → critique → refine loops — the Self-Refine / Reflexion pattern, built by hand.

    Theory · Try it
  6. 6

    University GPU

    A Dean agent designs a curriculum and teaches a model each subject to mastery — solo, or a competing cohort of students.

    Theory · Try it

Start at the bottom of the ladder.

No account. The theory is free and instant; the playground runs on a worker you download and run.

Read: Pathfinding → Jump into the playground

New lessons and videos, about twice a month. No spam, unsubscribe in one click.