Intro to Large Language Models (1-hour talk)
by Andrej Karpathy
The best one-hour mental model of what an LLM is, how it's trained, and where it's going.
Overview
This 'busy person's intro to LLMs' talk is the single best hour to understand the big picture: what an LLM actually is (a next-token predictor with two files), how pretraining and fine-tuning work, the emerging 'LLM OS' framing, tool use, and safety challenges like jailbreaks. It requires no math or code, making it ideal to share with anyone — technical or not — who wants to genuinely get LLMs.
At a Glance
- Topic
- Models
- Level
- Beginner
- Format
- Video
- Cost
- Free
- Duration
- ~1 hour
- Provider
- Andrej Karpathy
- Hands-on
- No
- Certificate
- None
What You’ll Learn
- ✓What an LLM is and how it's trained
- ✓Pretraining vs. fine-tuning at a high level
- ✓Tool use and the 'LLM OS' framing
- ✓Key capabilities and safety challenges
Highlights
- •No math or code required
- •The best shareable LLM primer
Who It’s For
Best For
- ✓Anyone wanting a solid big-picture understanding of LLMs
FAQ
What is Intro to Large Language Models (1-hour talk)?
Andrej Karpathy's accessible one-hour talk giving a complete, jargon-light mental model of large language models.
Is Intro to Large Language Models (1-hour talk) free?
Intro to Large Language Models (1-hour talk) is free to access.
What level is Intro to Large Language Models (1-hour talk) for?
Intro to Large Language Models (1-hour talk) is aimed at a beginner audience.
How long does Intro to Large Language Models (1-hour talk) take?
Expect roughly ~1 hour. Most learners work through it at their own pace.
What will I learn from Intro to Large Language Models (1-hour talk)?
You'll learn: What an LLM is and how it's trained; Pretraining vs. fine-tuning at a high level; Tool use and the 'LLM OS' framing; Key capabilities and safety challenges.