Karpathy's Stanford AI engineering lecture: from LLM to Graph in five steps

irinarish · x · 2026-09-20

A widely shared recommendation of Andrej Karpathy's 1-hour Stanford lecture on AI engineering, praised as one of the best explanations of how AI systems actually work. It lays out a progression: 10% LLM → 30% Prompt → 50% Agent → 70% Loop → 100% Graph.

The key takeaway: AI engineering isn't just about writing better prompts — it's about building systems around models with context, memory, tools, feedback loops, and data flows. Summed up as "Delete everything, keep Graph," and recommended for anyone building AI agents.

Original post →

More from coding & agent

coding & agent channel →