getphase

Run real code

Python in your browser

Pyodide runs NumPy, matplotlib, and your code right in the page. No setup, no Colab tab dance.

Your key, your model

AI tutor that knows the lesson

Anthropic, OpenAI, Google, OpenRouter, Ollama, DeepSeek — anything. We never spend on AI, you do.

Made for beginners

Visualizations that click

Drag arrows, slide softmax temperature, step through matmul — feel the math before you see it.

The 14-phase roadmap

See all →
  1. P01

    Math & ML Refresher

    The vector + gradient + probability foundation every LLM idea rides on.

  2. P02

    Deep Learning Foundations & PyTorch

    Write training loops you understand down to autograd. Debug exploding gradients with confidence.

  3. P03

    NLP Fundamentals

    From word vectors to attention — and why attention won.

  4. P04

    Transformers Deep Dive

    Implement multi-head attention and a full decoder-only Transformer from a blank file.

  5. P05

    Modern LLM Architectures & MoE

    Llama 4, Qwen3, DeepSeek V3/R1 — what's actually inside the frontier.

  6. P06

    Pre-Training — Scaling, Data, Distributed Systems

    Estimate compute-optimal trade-offs; use FSDP and parallelism that doesn't OOM at 3am.

  7. P07

    Fine-Tuning & Alignment

    Take a base model to instruction-following with the right algorithm for your budget.

  8. P08

    Prompt Engineering & Reasoning

    From ad-hoc prompting to a real vocabulary — CoT, self-consistency, budget forcing, reasoning models.

  9. P09

    Retrieval-Augmented Generation

    Build a production-grade RAG that beats naive cosine-similarity on your own eval.

  10. P10

    Agents, Tool Use, and MCP

    Multi-tool, stateful, durable agents. Expose your tools to the world via MCP.

  11. P11

    Evaluation

    Trustworthy evals before you trust any output. Goodhart's law in practice.

  12. P12

    Deployment & Inference Optimization

    Serve at >1000 tok/s/GPU. Quantize down to consumer hardware without losing your benchmarks.

  13. P13

    Safety, Alignment & Interpretability

    Red-team your own model. Reproduce a basic SAE. Understand current limits of mech interp.

  14. P14

    Research Track — Reading, Reproducing, Publishing

    Read 1 paper/week with full understanding. Reproduce one paper per quarter. Ship a preprint.