LLM Deep Dive

How AI works, made by NotebookLM from Andrej Karpathy's LLM Deep Dive, February, 2025

In this comprehensive overview, Andrej Karpathy provides a detailed explanation of the lifecycle and internal mechanics of large language models like ChatGPT. The process begins with pre-training, where massive amounts of internet data are filtered and converted into tokens to teach a neural network how to predict the next word in a sequence. Following this, post-training refines these “base models” into helpful assistants through human-led dialogue and specific instructions. Karpathy also explores the cognitive psychology of these systems, addressing common issues such as hallucinations and spelling errors. He suggests that these flaws can be mitigated by allowing models to use external tools or by encouraging them to distribute complex reasoning across multiple tokens. Finally, the source highlights that these models are not magical entities but statistical simulators whose performance depends heavily on their context window and training quality.

YouTube notes:
6,902,379 views 5 Feb 2025

This is a general audience deep dive into the Large Language Model (LLM) AI technology that powers ChatGPT and related products. It is covers the full training stack of how the models are developed, along with mental models of how to think about their “psychology”, and how to get the best use them in practical applications. I have one “Intro to LLMs” video already from ~year ago, but that is just a re-recording of a random talk, so I wanted to loop around and do a lot more comprehensive version.

Instructor
Andrej was a founding member at OpenAI (2015) and then Sr. Director of AI at Tesla (2017-2022), and is now a founder at Eureka Labs, which is building an AI-native school. His goal in this video is to raise knowledge and understanding of the state of the art in AI, and empower people to effectively use the latest and greatest in their work.
Find more at

https://karpathy.ai/

Chapters
00:00:00 introduction
00:01:00 pretraining data (internet)
00:07:47 tokenization
00:14:27 neural network I/O
00:20:11 neural network internals
00:26:01 inference
00:31:09 GPT-2: training and inference
00:42:52 Llama 3.1 base model inference
00:59:23 pretraining to post-training
01:01:06 post-training data (conversations)
01:20:32 hallucinations, tool use, knowledge/working memory
01:41:46 knowledge of self
01:46:56 models need tokens to think
02:01:11 tokenization revisited: models struggle with spelling
02:04:53 jagged intelligence
02:07:28 supervised finetuning to reinforcement learning
02:14:42 reinforcement learning
02:27:47 DeepSeek-R1
02:42:07 AlphaGo
02:48:26 reinforcement learning from human feedback (RLHF)
03:09:39 preview of things to come
03:15:15 keeping track of LLMs
03:18:34 where to find LLMs
03:21:46 grand summary

Educational Use Licensing
This video is freely available for educational and internal training purposes. Educators, students, schools, universities, nonprofit institutions, businesses, and individual learners may use this content freely for lessons, courses, internal training, and learning activities, provided they do not engage in commercial resale, redistribution, external commercial use, or modify content to misrepresent its intent.