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 meanLevel 2
2. Reward hacking: when an AI games its scoreLevel 2
3. Alignment faking: when an AI plays alongLevel 2
4. Agentic MisalignmentLevel 2
5. Corrigibility: not working against human oversightLevel 2
6. Deliberative alignment: a model that reasons over written safety rulesLevel 2
7. Scalable oversight: keeping AI answers checkableLevel 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
• Deliberative Alignment: Reasoning Enables Safer Language Models
• Claude's Constitution
• Our approach to alignment research
• Anthropic Risk Report, August 2026
• Taking a responsible path to AGI
• Emergent introspective awareness in LLMs
• Agentic misalignment: How LLMs could be insider threats

All units in Learn to use AI