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 persona · Level 2
2. Multi-task learning: one model, many jobs · Level 2
3. Post-training: how a model becomes your assistant · Level 2
4. Transfer learning: don't start from zero · Level 2
5. RLHF: teaching an AI with human judgment · Level 2
6. Constitutional AI · Level 2
7. Knowledge distillation: a small model learns from a big one · Level 2
8. LoRA: teaching a big model a new job on the cheap · Level 2
9. Supervised fine-tuning: from text guesser to assistant · Level 2

## Sources

These lessons draw on 28 sources. The most used:

- [Deep Dive into LLMs like ChatGPT](https://www.youtube.com/watch?v=7xTGNNLPyMI)
- [Hugging Face Smol Course](https://github.com/huggingface/smol-course)
- [International AI Safety Report 2026](https://internationalaisafetyreport.org/sites/default/files/2026-02/international-ai-safety-report-2026.pdf)
- [John Schulman — reasoning, RLHF, and the plan for AGI](https://www.youtube.com/watch?v=Wo95ob_s_NI)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://arxiv.org/abs/2106.09685)
- [Claude's Character](https://www.anthropic.com/research/claude-character)
- [Training language models to follow instructions with human feedback](https://arxiv.org/abs/2203.02155)
- [The assistant axis: situating and stabilizing the character of large language models](https://www.anthropic.com/research/assistant-axis)

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

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