Firehose

15 MAY 2026 · Podcast · Dwarkesh Podcast

Eric Jang – Building AlphaGo from scratch

Eric Jang explains how to build AlphaGo from scratch using modern AI tools, detailing the game of Go's rules and the core Monte Carlo Tree Search (MCTS) algorithm. He describes how deep neural networks, specifically value and policy network…

AlphaGo development Go game rules Monte Carlo Tree Search Deep learning Neural networks Reinforcement learning Self-play training Computational complexity Scaling laws Automated AI research LLM training Robotics RL Game theory Off-policy training On-policy training

Browse by tag

Eric Jang – Building AlphaGo from scratch