ishu garg

Zero to heromodules / projects / checkpoints

Learning paths should leave artifacts, not only confidence.

Each track has a goal, modules, projects, and checkpoints. The outcome is something you can show, test, explain, or improve.

beginner / 6 weeks

LLM Builder: Zero to Shipped Agent

Ship one useful AI assistant with a clear task, test set, retrieval boundary, and failure log.

  1. 01 Prompting as interface design Turn a messy note into a structured student resource.
  2. 02 RAG without superstition Build a scholarship finder over a small verified corpus.
  3. 03 Evals before vibes Evaluate the scholarship finder on 20 realistic questions.
  4. 04 Tools and agents Add a deadline checker and source verifier.
  5. 05 Ship and observe Publish a read-only demo with a failure diary.
intermediate / 8 weeks

LLM From Scratch, No Incense Required

Train a tiny text model, inspect its failures, and connect the toy version to modern LLM systems.

  1. 01 Text to numbers Write a tokenizer visualizer for your own bio.
  2. 02 Embeddings Plot nearest neighbors in a toy corpus.
  3. 03 Attention Animate one attention head on a short sentence.
  4. 04 Training loop Train a tiny quote generator.
  5. 05 Failure diary Publish the model's wrong outputs with explanations.
zero / 12 weeks

Student to Strong CS Intern

Create a credible application packet and one project that shows actual judgment.

  1. 01 Fundamentals map Make a personal CS map with gaps marked.
  2. 02 One real project Make a campus or NGO utility and write the postmortem.
  3. 03 Application system Create a public internship tracker template.
  4. 04 Interview reps Solve and explain 20 core problems.
  5. 05 Proof of work Publish a short project page and learning log.
intermediate / 10 weeks

Quant Research Prep

Build enough math, coding, and research discipline to discuss quant problems honestly.

  1. 01 Probability reflexes Write solutions to 15 probability puzzles.
  2. 02 Statistics and experiments Run a simulation notebook for false discoveries.
  3. 03 Python research loop Build a toy mean-reversion backtest with caveats.
  4. 04 Market humility Write a 'why this probably fails' memo.
  5. 05 Interview synthesis Record short written explanations for solved puzzles.