Subvolts take Karpathy explains agentic engineering and how to direct LLMs like summoned ghosts. Apr 30, 2026 - Developers
- Learn about agentic engineering and how to direct LLMs effectively, moving beyond "vibe coding."
- Business
- Understand the emerging discipline of agentic engineering and its implications for building more capable AI applications.
Features a prominent AI researcher discussing the practical evolution of AI development and future directions.
Andrej Karpathy: From Vibe Coding to Agentic Engineering
Audio streams from Sequoia Capital. Your place is remembered on this device.
From Subvolts
Summary and analysis by Subvolts editorial, AI-assisted.
Andrej Karpathy discusses advancements in AI since he coined "vibe coding." He explains agentic engineering as a more serious discipline built on this foundation. Karpathy likens LLMs to summoned ghosts, requiring new judgment to direct, and touches on Software 3.0, verifiability limits, and the difference between outsourcing thinking and understanding.
Karpathy talks about how AI coding has evolved from "vibe coding" to a more structured approach called agentic engineering. He compares AI models to ghosts that need careful guidance, which is important for anyone curious about how AI is being built and controlled.
This episode offers insights into the evolution of AI development from Karpathy's perspective. It's for AI researchers, developers, and tech leaders interested in the practical application and future direction of large language models. The discussion on agentic engineering and LLM direction connects directly to current efforts by OpenAI, Google Gemini, and Anthropic to build more capable and controllable AI systems.
- HostSequoia Capital
- GuestAndrej KarpathyFounder, Eureka Labs
- Guest: Andrej Karpathy
- Title: Andrej Karpathy: From Vibe Coding to Agentic Engineering
- Show: Training Data
- Length: 30 minutes
- Karpathy's roles: Co-founder of OpenAI, former head of AI at Tesla, founder of Eureka Labs
Andrej Karpathy (co-founder of OpenAI, former head of AI at Tesla, and now founder of Eureka Labs) talks with Sequoia partner Stephanie Zhan at AI Ascent 2026 about what's changed in the year since he coined "vibe coding." He explains why he's never felt more behind as a programmer, why agentic engineering is the more serious discipline taking shape on top of vibe coding, and why we should think of LLMs not as animals but as ghosts: jagged, statistical, summoned entities that require a new kind of taste and judgment to direct. He also touches on Software 3.0, the limits of verifiability, and why you can outsource your thinking but never your understanding.
- vibe coding
- Andrej Karpathy
- An earlier, less structured approach to AI development.
- agentic engineering
- Andrej Karpathy
- A more structured discipline for directing AI systems.
- LLMs
- Andrej Karpathy
- Large Language Models, AI systems that process and generate text.
1 h 08David Silver and Lasse Espeholt of Ineffable Intelligence: A Superlearner for the Age of Experience
WithDavid Silver, Lasse Espeholt
1 h 041 h 0552 minMaking Cities Awesome: Peregrine’s Nick Noone & Ben Rudolph
WithNick Noone, Ben Rudolph
Same guests, other shows
1 h 21Google Changes Search for the First Time in 25 Years
WithAndrej Karpathy
1 h 07Andrej Karpathy on Code Agents, AutoResearch, and the Loopy Era of AI
WithAndrej Karpathy
2 h 25Andrej Karpathy — AGI is still a decade away
WithAndrej Karpathy
38 minWhy AI needs a new kind of supercomputer network - Episode 18
WithMark Handley, Greg Steinbrecher
Questions people ask
- What is "vibe coding"?
- Vibe coding refers to an earlier approach in AI development that Karpathy coined, suggesting a less structured method.
- What is agentic engineering?
- Agentic engineering is presented as a more serious discipline that builds upon "vibe coding" to direct AI systems.
Page generated Oct 19, 2026. Summaries are Subvolts' own; the audio, artwork and notes belong to Sequoia Capital.