Deep Dive into LLMs like ChatGPT

FROM THE SOURCE CARD / AI-WRITTEN

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.

How the source describes its HN context

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

These descriptions and labels come from the original dataset’s AI-assisted curation. They are not our personal review. Check the video and the linked discussion for context.