Skip to content
Sonic
AI
Sonic
AI
Home
Discover
Ask Sonic
Projects
Use with Claude or ChatGPT
Show me around
Request source or feature
Building AlphaGo from scratch – Eric Jang, Sonic AI
Home
/
Dwarkesh Podcast
/
Building AlphaGo from scratch – Eric Jang
Dwarkesh Podcast
Notify me
•
May 15, 2026
•
2:37:16
Interview
Building AlphaGo from scratch – Eric Jang
Dwarkesh Patel
(Podcast host, analyst, and angel investor in…)
•
Eric Jang
(Guest)
•
Eric Zhang
(Guest)
Get the full transcript next time Dwarkesh Podcast releases an episode
Summary, key quotes, top claims, and the searchable transcript — emailed automatically. No card needed.
Sign up
Executive Summary
The cost to build a superhuman Go AI has plummeted from millions of dollars (DeepMind's AlphaGo) to a few thousand, thanks to open-source projects like Katago and modern development tools.
AlphaGo's success stems from a powerful self-improvement loop combining Monte Carlo Tree Search (MCTS) with deep neural networks (policy and value networks), where search generates better data for the networks, and the networks guide the search.
A profound insight from AlphaGo is that relatively small neural networks can 'amortize' and approximate solutions to intractably large search problems, suggesting that many NP-hard problems have enough structure to be solved efficiently by AI.
The principles of combining search and learned models are a core AI paradigm, but extending them from structured games like Go to open-ended domains like language models presents a major research challenge due to the vast action space.
Continue your research
Keep pulling the thread on Eric Jang.
Democratization of Superhuman AI
The Power of Amortized Computation
9
quotes
Transcript
Key Arguments
Analysis
Quotes & Entities
9
Related
Loading transcript...
Processed May 15, 2026
Daily intelligence brief →
yt-dlp + mlx-whisper + Gemini