Karpathy lecture: AI engineering is LLM→Prompt→Agent→Loop→Graph, not just prompts

leslysandra · x · 2026-08-17

Andrej Karpathy's 1-hour Stanford lecture on AI engineering is being called one of the clearest explanations of how AI systems actually work. The lecture 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, giving them context, memory, tools, feedback loops, and data flows. As the lecture puts it: "Delete everything, keep Graph." Worth watching if you're building AI agents.

Original post →

More from coding & agent

coding & agent channel →