Learn to use AI

# Reasoning

Reasoning is a unit of 5 lessons in Rabbithole's Learn to use AI course, at level 2. The same lessons are also in Become an AI engineer as “Reasoning, plainly”.

## Lessons

1. Chain-of-thought: making a model show its reasoning · Level 2
2. Reasoning models: AI that thinks before it answers · Level 2
3. In-context learning: teaching an AI inside your message · Level 2
4. Self-consistency: ask several times, keep the most common answer · Level 2
5. Tree of Thoughts: letting an AI try several paths · Level 2

## Sources

These lessons draw on 16 sources. The most used:

- [openai/openai-cookbook](https://github.com/openai/openai-cookbook)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://arxiv.org/abs/2305.10601)
- [GroqDocs](https://console.groq.com/docs/overview)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://arxiv.org/abs/2403.05530)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://arxiv.org/abs/2201.11903)
- [Language Models are Few-Shot Learners](https://arxiv.org/abs/2005.14165)
- [OpenAI o1 System Card](https://openai.com/index/openai-o1-system-card/)
- [Reasoning models don't always say what they think](https://www.anthropic.com/research/reasoning-models-dont-say-think)

[All units in Learn to use AI](https://rabbithole.pro/courses/learn-ai)

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