Skip to content
⌕Go Pro
☰

Learn

CoursesCareer pathsAll lessonsGlossary

Tools

CalculatorsCan I run it?PlaygroundBenchmarksFixes
Pricing

Measure, scale and train reasoning step by step

Build a Reasoning Model

What reasoning means and how to verify it, chain of thought, self-consistency, search, verifier loops, reinforcement learning with verifiable rewards (a GRPO-style method), distillation and honest evaluation, with runnable toy experiments.

3 tracks · 7 lessons · about 3 hours · 1 free lessons · 0 animated diagrams

Start the first lesson freeSee Pro

What you will be able to do

  • ✓Design verifiers and metrics that measure reasoning honestly
  • ✓Use inference-time compute (voting, search, refinement) and price it
  • ✓Explain policy gradients and a GRPO-style training loop
  • ✓Report cost versus accuracy without fooling yourself

Who it is for

Builders who finished the LLM-from-scratch course or understand transformer basics.

Prerequisites

Build an LLM from Scratch, or equivalent familiarity with transformers and sampling.

Curriculum

Reasoning Foundations

Intermediate

What reasoning means, verifiers, and honest evaluation.

  1. 1What reasoning means, and how a verifier makes it measurableFree16 min
  2. 2Verifiers and honest evaluation: pass@k, error bars and costPro17 min

Inference-time Reasoning

Advanced

Chain of thought, self-consistency voting, search and verifier loops with a price on every extra token.

  1. 1Chain of thought and self-consistency: majority voting, and when it failsPro18 min
  2. 2Search and verifier loops: best-of-n, trees, refinement and reasoning budgetsPro19 min

Training for Reasoning

Advanced

Policy gradients and GRPO-style training, distillation, tool use and a cost-versus-accuracy lab.

  1. 1Policy gradients and GRPO-style training, on a problem you can runPro24 min
  2. 2Distillation, curricula and tool-augmented reasoningPro18 min
  3. 3Lab: cost versus accuracy for reasoning strategiesLabPro90 min