Karpathy's Stanford AI Engineering Lecture: From LLM to Graph in Five Levels
ifioknkem · x · 2026-09-12
A recap of Andrej Karpathy's 1-hour Stanford lecture on AI engineering, praised as one of the best explanations of how AI systems actually work.
- Structured as a five-level progression: 10% LLM → 30% Prompt → 50% Agent → 70% Loop → 100% Graph
- Key takeaway: AI engineering isn't better prompts — it's building systems around models with context, memory, tools, feedback loops, and data flows
- Memorable line: "Delete everything, keep Graph"
- Recommended viewing for anyone building with AI agents
More from coding & agent
- OpenAI launches Agents API in public beta: Codex harness as a cloud agent service — minchoi · 2026-09-12
- Hermes Agent open-source project hits 3,000 contributors — Teknium · 2026-09-12
- Pro tip: append .md to any Apple HIG link to get an AI-friendly Markdown file — rudrank · 2026-09-12
- Data science career path shifts from ML training to building LLM apps and agents — mdancho84 · 2026-09-12
- The AI-native SDLC: agents across planning, coding, testing and deployment — Pavan_Belagatti · 2026-09-12
- Litho (deepwiki-rs): generate C4 architecture docs from code, ADRs and SQL schemas — techNmak · 2026-09-12