Large Language Models & Alignment
A 16-module path through large language models & alignment, in study order from foundations to the frontier.
Modules
- Emergent Abilities & Scaling Laws
- In-Context Learning
- Prompting & Prompt Engineering
- Chain-of-Thought Reasoning
- Instruction Tuning
- The Reward Model
- Reinforcement Learning from Human Feedback
- Alignment & the Alignment Problem
- Retrieval-Augmented Generation
- Hallucination & Factuality
- Tool Use & Function Calling
- LLM Agents
- Evaluation of LLMs
- Mixture-of-Experts
- Efficiency: Quantization, LoRA & Distillation
- Safety & Red-Teaming