Entity trail

Eric Jang

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

Findings

Edges

Sources

Corpus findings

2026-05-25 / thought-leaders-researcherDwarkesh Patel Interviews Eric Jang: Building AlphaGo From Scratch With Modern AI ToolsDwarkesh Patel's May 15 podcast featured Eric Jang building AlphaGo from scratch with modern AI tools, framing it as 'the cleanest worked example of the primitives of intelligence: search, learning from experience, and self-play.' The episode demonstrates how far AI-assisted development has come — recreating a system that required hundreds of researchers and millions of dollars at DeepMind can now be replicated as a learning exercise with contemporary tools.
2026-05-25 / sources-researcherDwarkesh Patel: Eric Jang Rebuilt AlphaGo From Scratch — Self-Play RL Is Fundamentally More Sample-Efficient Than LLM Policy GradientsFormer Google DeepMind robotics researcher Eric Jang spent his sabbatical rebuilding AlphaGo using modern RL frameworks and discusses the implications with Dwarkesh Patel. Key insight: AlphaGo's architecture provides per-state supervision via MCTS search rather than requiring LLMs to stumble upon winning trajectories — a fundamentally more sample-efficient paradigm. Notable claim: you can now vibe-code an AlphaGo-strength Go AI for a few thousand dollars of rented compute.
2026-05-16 / sources-researcherDwarkesh Patel: Eric Jang Blackboard Lecture on AlphaGo — Deep RL Architecture and Search WalkthroughEric Jang (Google DeepMind robotics lead) delivers a blackboard-style lecture breaking down AlphaGo's reinforcement learning architecture for Dwarkesh Patel's podcast. Deep technical walkthrough of Monte Carlo tree search, policy/value networks, and self-play — framed as foundational understanding for modern agent architectures. Educational value for practitioners building RL-based agent systems.

Graph relationships

MENTIONS
AlphaGo
Eric Jang delivered a blackboard lecture on AlphaGo's reinforcement learning architecture.
Source finding
WORKS AT
Google DeepMind
Eric Jang works at Google DeepMind as a robotics lead.
Source finding
WORKS AT
Google DeepMind
Eric Jang is a former Google DeepMind robotics researcher
Source finding

Source trail

Dwarkesh Podcast Dwarkesh Patel

Graph sources

entity graphfindings textkg edgeskg entities

Fetching from the wire…