Alpha Zero's "Immortal Zugzwang Game" against Stockfish

agadmator's Chess Channel · 1.7M views · 2017 · 15:37

Open on YouTube

Chess, board games & puzzlesMachine learning & deep learningexplainer

Why Hacker News recommends it

HN recommends it as a striking, well-explained example of AlphaZero's play and of zugzwang.

What it is

agadmator walks through a game in which DeepMind's AlphaZero beat Stockfish, ending in a famous zugzwang that leaves the engine helpless. He gives commentary on the moves.

Recommended by 2 HN commenters across 2 different months, 2019 to 2025.

What Hacker News said

Strong rec lawrenceyan · 2019-12 · on “Zugzwang”

A great example I love showing people is Alpha Zero's infamous "Immortal Zugzwang Game" against Stockfish [0]. Stockfish gets utterly annihilated in a trap that seemingly springs out of nowhere, though of course the reality is that Alpha Zero was actually really in control the entire time. [0] [this video]

Recommends mrleiter · 2019-10 · on “Multiplayer AlphaZero”

Anyone who's interested to see how brilliant AlphaZero played against the best chess computer (then), with solid explanations: [this video]

Cites yunwal · 2025-11 · on “Gemini 3”

Here’s a chess stackexchange of positions that stump engines [LINK] It basically comes down to “ideas that are rare enough that they were never programmed into a chess engine”. Blockades or positions where no progress is possible are a common theme. Engines will often keep tree searching where a human sees an obvious repeating pattern. Here’s also an example where 2 engines are playing, and deep mind finds a move that I think would be obvious to most grandmasters, yet stockfish misses it [this video] That being said, I’m not sure that this necessarily correlates with brilliancy. There are a few of these that I would probably get in classical time and I’m not a particularly brilliant player.