All free AI courses
Andrej KarpathyFoundationFree
How Large Language Models Work
Two general-audience talks from a founding member of OpenAI on how ChatGPT-style models are built: pre-training on the internet, fine-tuning into an assistant, and where they still go wrong.
2 video lessons · 4 h 31 min · taught by Andrej Karpathy
Lesson 1 of 2 · 1 h
Intro to Large Language Models
Check your understanding
Course quiz
Finish the course to unlock the quiz
Mark all 2 lessons as watched and 8 questions open up here. You have 2 to go.
What you will learn
- Describe the pre-training, fine-tuning and reinforcement learning stages
- Explain tokens and why models predict one at a time
- Recognise hallucinations and why they happen
- Understand the security risks such as jailbreaks and prompt injection
Before you start
- Prerequisites
- None. No code or maths is needed.
- Cost
- Free.
Videos are embedded from Andrej Karpathy’s own channel and remain theirs. The quiz is written by MTT to help you check your understanding; it is not an official Andrej Karpathy assessment.