Become an AI engineer

# Reasoning

Reasoning is a unit of 7 lessons in Rabbithole's Become an AI engineer course, at levels 3 to 5.

## Lessons

1. Chain-of-thought: making a model show its steps · Level 3
2. Reasoning models: controlling how they think · Level 3
3. In-context learning: teaching a model inside the prompt · Level 3
4. Test-time compute: spending more at inference · Level 4
5. Tree of Thoughts: Searching Over Reasoning Steps · Level 4
6. Induction heads · Level 5
7. Process supervision: rewarding every reasoning step · Level 5

## Sources

These lessons draw on 23 sources. The most used:

- [In-context Learning and Induction Heads](https://transformer-circuits.pub/2022/in-context-learning-and-induction-heads/index.html)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://arxiv.org/abs/2408.03314)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://arxiv.org/abs/2501.12948)
- [Show Your Work: Scratchpads for Intermediate Computation with Language Models](https://arxiv.org/abs/2112.00114)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://arxiv.org/abs/2305.10601)
- [Transformer Circuits Thread](https://transformer-circuits.pub/)
- [Claude Platform Docs — Introduction and Get Started](https://platform.claude.com/docs/en/intro)
- [Qwen3 Technical Report](https://arxiv.org/abs/2505.09388)

[All units in Become an AI engineer](https://rabbithole.pro/courses/ai-engineer)

Source page: https://rabbithole.pro/courses/ai-engineer/reasoning