Karpathy's 1-Hour Stanford Lecture: From LLM to Prompt to Agent to Graph

AlishaOutridge · x · 2026-08-27

A share of Andrej Karpathy's 1-hour Stanford lecture on AI engineering, praised as one of the clearest explanations of how AI systems actually work. The progression: 10% LLM → 30% Prompt → 50% Agent → 70% Loop → 100% Graph.

Key takeaway: AI engineering isn't just better prompts — it's building systems around models with context, memory, tools, feedback loops and data flows. "Delete everything, keep Graph." Worth a full uninterrupted hour for anyone building agents.

Original post →

More from coding & agent

coding & agent channel →