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.
More from coding & agent
- Tutorial request: Bulk downloading songs with AI agents and auto-tagging — EnvironmentalTry8353 · 2026-08-27
- Google AI Studio enables two-way GitHub sync with direct commits and one-click deploy — jackwoth · 2026-08-27
- Opinion: Notification systems need rebuilding for agent-primary usage and context linking — andreisavu · 2026-08-27
- OpusClip and Beehiiv integrate to auto-turn videos into newsletters via Claude — azed_ai · 2026-08-27
- Bixbench3: Frontier Agents Score Below 50% in Reproducing Paper Analysis — xeophon · 2026-08-27
- Free 6-Week Course: 9,000+ Marketers to Master Claude Code and Codex for Ad Creation — alexgoughcooper · 2026-08-27