Course Materials

Introduction

Transformers: L1

Transformers: L2

Pretrained Transformers

Prompting: Coding Tutorial

Instruction Tuning LLMs

AI Alignment

Reward Modelling

RLHF: L1 - Supplementary: 1, 2, 3

RLHF: L2 - Supplementary

AI Vulnerabilities

PEFT

Safety Algorithms: L1

Safety Algorithms: L2 - Supplementary: 1, 2, 3

Machine Unlearning

Mechanistic Interpretability: L1

Mechanistic Interpretability: L2

Scalable Oversight

Casual Tracing

LLM Watermarking

Alignment Paradox