Learn to use AI

Post training

Post training is a unit of 9 lessons in Rabbithole's Learn to use AI course, at level 2. The same lessons are also in Become an AI engineer as “Post training, plainly”.

Lessons

1. Model character and personaLevel 2
2. Multi-task learning: one model, many jobsLevel 2
3. Post-training: how a model becomes your assistantLevel 2
4. Transfer learning: don't start from zeroLevel 2
5. RLHF: teaching an AI with human judgmentLevel 2
6. Constitutional AILevel 2
7. Knowledge distillation: a small model learns from a big oneLevel 2
8. LoRA: teaching a big model a new job on the cheapLevel 2
9. Supervised fine-tuning: from text guesser to assistantLevel 2

Sources

These lessons draw on 28 sources. The most used:

• Deep Dive into LLMs like ChatGPT
• Hugging Face Smol Course
• International AI Safety Report 2026
• John Schulman — reasoning, RLHF, and the plan for AGI
• LoRA: Low-Rank Adaptation of Large Language Models
• Claude's Character
• Training language models to follow instructions with human feedback
• The assistant axis: situating and stabilizing the character of large language models

All units in Learn to use AI