Learn to use AI

# Alignment

Alignment is a unit of 8 lessons in Rabbithole's Learn to use AI course, at level 2.

## Lessons

1. Alignment: an AI that does what we mean · Level 2
2. Reward hacking: when an AI games its score · Level 2
3. Alignment faking: when an AI plays along · Level 2
4. Agentic Misalignment · Level 2
5. Corrigibility: not working against human oversight · Level 2
6. Deliberative alignment: a model that reasons over written safety rules · Level 2
7. Scalable oversight: keeping AI answers checkable · Level 2
8. Model welfare: could an AI have wellbeing? · Level 2

## Sources

These lessons draw on 14 sources. The most used:

- [Alignment faking in large language models](https://www.anthropic.com/research/alignment-faking)
- [Deliberative Alignment: Reasoning Enables Safer Language Models](https://arxiv.org/abs/2412.16339)
- [Claude's Constitution](https://www.anthropic.com/constitution)
- [Our approach to alignment research](https://openai.com/index/our-approach-to-alignment-research/)
- [Anthropic Risk Report, August 2026](https://anthropic.com/aug-2026-risk-report)
- [Taking a responsible path to AGI](https://deepmind.google/blog/taking-a-responsible-path-to-agi/)
- [Emergent introspective awareness in LLMs](https://www.anthropic.com/research/introspection)
- [Agentic misalignment: How LLMs could be insider threats](https://www.anthropic.com/research/agentic-misalignment)

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

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