Deep Dive into LLMs like ChatGPT

What this video covers

Andrej Karpathy's three-hour-plus general-audience deep dive into how ChatGPT-style LLMs are built, covering the full training stack from pretraining to post-training. It also gives mental models for their quirks, like hallucination, and how to use them well.

Why it surfaced in Hacker News

HN's most frequent recommendation for a clear, approachable foundation in how LLMs work without heavy math.

Recommendation context

Short excerpts from positive mentions. Open the source to read the full Hacker News discussion.

“He goes over a ton of different stuff related to model training, but makes it very easy to understand.”

“the first thing I would recommend is to watch Karpathy's 'deep dive into LLMs' video”

“Anyway, I really like's Karpathy's video because he's very good at explaining LLMs at every level.”