EP. 152 · 05.08.2026 · 45:00
BUILDING WITH LLMS: CRAFT, TOOLING AND THE NEW STACK
with Andrej Karpathy
Auto-generated brief
EPISODE BRIEF — EP. 152 · BUILDING WITH LLMS: CRAFT, TOOLING AND THE NEW STACK Guest: Andrej Karpathy · Published: 05.08.2026 · Duration: 45:00 【OVERVIEW】 Andrej Karpathy on what it actually takes to build with large language models — the tooling gaps, the evaluation problem, why so much of the work is unglamorous data engineering, and what the emerging AI-native software stack looks like from the inside. 【KEY TAKEAWAYS】 1. From Tesla Autopilot to LLMs 2. Why evaluation is the hardest unsolved problem 3. The AI-native developer stack 4. Advice for engineers entering the field 【CHAPTERS】 00:00 — From Tesla Autopilot to LLMs 08:00 — Why evaluation is the hardest unsolved problem 22:00 — The AI-native developer stack 35:00 — Advice for engineers entering the field 【TOPICS】LLM · Engineering · OpenAI · Tesla · Developer Tools 【WATCH】https://thedaopod.com/episodes/ep-152-andrej-karpathy-on-building-with-llms
SUBSCRIBE
Subscribe to The DAO
Get every dialogue, roundtable and observatory briefing in your podcast app — or copy the RSS feed and add it manually.
Subscription status unknown
We can't read your YouTube subscription directly — confirm it manually, and redo it anytime.
Follow us
https://thedaopod.com/rss.xmlABOUT THIS EPISODE
THE CONVERSATION
Andrej Karpathy on what it actually takes to build with large language models — the tooling gaps, the evaluation problem, why so much of the work is unglamorous data engineering, and what the emerging AI-native software stack looks like from the inside.
SHARE
Copy link & social preview
thedaopod.com
EP. 152 · BUILDING WITH LLMS: CRAFT, TOOLING AND THE NEW STACK
Andrej Karpathy on what it actually takes to build with large language models — the tooling gaps, the evaluation problem, why so much of the work is unglamorous data engineering, and what the emerging AI-native software stack looks like from the inside.
Pasting this link on X, WeChat or LinkedIn renders the preview card above.
CHAPTERS
TIMELINE
Chapters derived from show notes
GUESTS
ON THE ROUNDTABLE
Founding member, OpenAI · Former Director of AI, Tesla
A founding member of OpenAI and former Director of AI at Tesla, where he led the Autopilot vision team. One of the field's most widely followed educators, his lectures on neural networks and language models have taught a generation of practitioners.
No subtitle track for this video — the timeline below is generated from chapters and follows playback
FULL TRANSCRIPT
Searchable Transcript
Chapter-derived timeline
0:00 · From Tesla Autopilot to LLMs
Key Moments
4 lines
Related videos
Matched by host & keywords
EpisodeEP. 149 · A PRIMER ON LARGE LANGUAGE MODELS
with Andrej Karpathy
EpisodeEP. 125 · SOFTWARE 2.0, LLMS, AND THE FUTURE OF CODING
with Andrej Karpathy
EpisodeEP. 160 · PHYSICAL AI AND THE RISE OF THE AGENT
with Jensen Huang
EpisodeEP. 170 · SOLVING THE HARDEST PROBLEM IN ROBOTICS
with Fei-Fei Li
EpisodeEP. 165 · POWER, POLITICS AND THE RACE TO AGI
with Sam Altman
EpisodeEP. 180 · THE GPU SHORTAGE AND THE AI REVOLUTION
with Lisa Su