AlphaZero
Next-generation Go-playing AI that learned through self-play, without human demonstrations.
Common Themes
Videos Mentioning AlphaZero
Is GPT-5.1 Really an Upgrade? But Models Can Auto-Hack Govts, so … there’s that
AI Explained
Next-generation Go-playing AI that learned through self-play, without human demonstrations.
Garry Kasparov: Chess, Deep Blue, AI, and Putin | Lex Fridman Podcast #46
Lex Fridman
A Google DeepMind AI program that achieved superhuman performance in chess, Go, and Shogi by developing its own strategies from self-play, representing a step towards machine-produced knowledge.
Can We Contain Artificial Intelligence?: A Conversation with Mustafa Suleyman (Episode #332)
Sam Harris
An evolution of AlphaGo that learned to play games, including Go, chess, and shogi, entirely through self-play without human data.
Ryan Hall: Solving Martial Arts from First Principles | Lex Fridman Podcast #169
Lex Fridman
An AI program by DeepMind that taught itself to beat Stockfish in four hours, used to illustrate the rapid advancement and potential power of AI.
Q* - Clues to the Puzzle?
AI Explained
A reinforcement learning system credited with inventing new ways to play games and exhibiting creativity, cited as an example of RL's potential.
Sean Kelly: Existentialism, Nihilism, and the Search for Meaning | Lex Fridman Podcast #227
Lex Fridman
A DeepMind AI system that achieved superhuman performance in games like Go and Chess, surprising grandmasters with its creative moves. Discussed for its potential artistry if it were deeply socially embedded and cognizant of its psychological impact.
Peter Woit: Theories of Everything & Why String Theory is Not Even Wrong | Lex Fridman Podcast #246
Lex Fridman
An AI program that learned to play chess and other games without human supervision, mentioned as an example of impressive progress in AI that is inspiring despite fuzzy definitions of 'intelligence'.
Making Sense of Artificial Intelligence
Sam Harris
An AI from DeepMind that used similar architecture to AlphaGo to learn and play chess.
Ben Askren: Wrestling and MMA | Lex Fridman Podcast #242
Lex Fridman
An AI program developed by DeepMind that mastered chess, Shogi, and Go by playing against itself.
Constructing Self and World: A Conversation with Shamil Chandaria (Episode #320)
Sam Harris
A DeepMind AI system that achieved superhuman performance in games like chess, shogi, and Go using self-play.
David Ferrucci: IBM Watson, Jeopardy & Deep Conversations with AI | Lex Fridman Podcast #44
Lex Fridman
Google DeepMind's AI program that mastered chess, shogi, and Go by playing against itself, highlighted for its brilliant bootstrapping data problem solution.
Joscha Bach: Artificial Consciousness and the Nature of Reality | Lex Fridman Podcast #101
Lex Fridman
AI system that learned to play various games through self-play, demonstrating the power of reinforcement learning.
Scaling Test Time Compute to Multi-Agent Civilizations — Noam Brown, OpenAI
Latent Space
Mentioned alongside AlphaGo as an example of AI achieving superhuman performance through pre-training, test-time compute, and self-play.
Rodney Brooks: Robotics | Lex Fridman Podcast #217
Lex Fridman
DeepMind's AI program that mastered chess, shogi, and Go through self-play.
Wojciech Zaremba: OpenAI Codex, GPT-3, Robotics, and the Future of AI | Lex Fridman Podcast #215
Lex Fridman
An AI program that achieved superhuman performance in chess, shogi, and Go, regarded as a fundamental leap in AI.
Max Tegmark: AI and Physics | Lex Fridman Podcast #155
Lex Fridman
DeepMind's AI that defeated world champions in Chess and Go by learning through self-play, demonstrating the ability of AI to develop its own 'intuition' without human programming.
Dmitry Korkin: Evolution of Proteins, Viruses, Life, and AI | Lex Fridman Podcast #153
Lex Fridman
DeepMind's AI for games, which learned by self-play and beat world champions, used as a comparison for AlphaFold 2's impact.
Machines, Creativity & Love | Dr. Lex Fridman
Andrew Huberman
An AI system that achieved superhuman performance in chess and Go through self-play mechanisms, without human supervision.
Ilya Sutskever: Deep Learning | Lex Fridman Podcast #94
Lex Fridman
A more generalized version of AlphaGo, capable of mastering multiple games like chess, shogi, and Go through self-play reinforcement learning, demonstrating advanced reasoning capabilities.
Rob Reid: The Existential Threat of Engineered Viruses and Lab Leaks | Lex Fridman Podcast #193
Lex Fridman
DeepMind's AI program that mastered chess, Go, and shogi, mentioned as an example of AI surpassing human capabilities in games, evoking a sense of sadness for human intellect.
Michael Littman: Reinforcement Learning and the Future of AI | Lex Fridman Podcast #144
Lex Fridman
An extension of AlphaGo Zero that learned to play multiple games (Go, Chess, Shogi) purely through self-play and achieved superhuman performance, with no ceiling yet discovered for its improvement in Go or Chess.
John Danaher: The Path to Mastery in Jiu Jitsu, Grappling, Judo, and MMA | Lex Fridman Podcast #182
Lex Fridman
A machine learning program by Google's DeepMind that learned chess and Go through self-play and quickly surpassed all human and rival AI players, even within hours.
Nick Bostrom: Superintelligence | AI Podcast Clips
Lex Fridman
An AI system developed by DeepMind that demonstrated advanced learning capabilities through self-play, surpassing previous AI models in playing games like Go and Chess.
David Silver: AlphaGo, AlphaZero, and Deep Reinforcement Learning | Lex Fridman Podcast #86
Lex Fridman
A more generalized version of AlphaGo that learns to play Go, chess, and shogi without human expert data, purely through self-play.