TAG
#sokoban
0 reviews · 5 essays
Related essays
Where 'Solvable' and 'Fun' Diverge — PuzzleJAX Hands 500+ PuzzleScript Games to the Machines (arXiv, Aug 2025)
One article today: "PuzzleJAX: A Benchmark for Reasoning and Learning" (arXiv preprint, August 2025) by researchers at NYU, the University of Malta, the University of the Witwatersrand (South Africa), and Microsoft (Sam Earle, Graham Todd, Ahmed Khalifa, Julian Togelius and others). They reimplement PuzzleScript — Stephen Lavelle's (increpare) 2013 puzzle-authoring language — on the GPU and hand 500+ human-authored games to tree search, reinforcement learning, and large language models. Read as a designer, the core is one observation: 'solvable by a machine' and 'interesting to a human' are not the same thing. Tree search brute-forces simple games but stalls the moment they get richer; LLMs score 0% on most. The authors even note PuzzleScript's own creator hesitating to embed an auto-solver into the IDE, a caution about measuring difficulty by search.
Can AI Build a Whole Puzzle Game? ScriptDoctor and Its Generate-Playtest-Repair Loop
ScriptDoctor has a large language model write an entire puzzle game — rules, sprites, levels — then lets a compiler and a search-based agent inspect the result and demand revisions. The testbed is PuzzleScript, a language indie developers know well. I walk through the paper in five parts — problem, method, findings, where you can use it, limitations — covering why human-authored examples boost success rates, why reasoning models win, and the distance between 'solvable' and 'fun'.
Ten years of sausage grilling and a shift of perspective — minimal rules, maximal depth, and spatial cognition as puzzle material
Two articles today. First: Thinky Games' 10th anniversary feature on Stephen's Sausage Roll (April 21, 2026) — the sokoban-like praised by puzzle developers as perfectly designed, which birthed the sausage-like subgenre through radical minimalism. Second: Alan Hazelden's Thinky Third Thursday April 2026 (April 16), spotlighting A Little Perspective and He Who Watches — two games that use perspective shifts and spatial cognition as their core puzzle material.
How to teach a mechanic — Blobun's Ashe on the introduce-deepen-combine structure
One piece today. Published June 1, 2026 as part of Thinky Games' Pride Month series, an interview with Ashe, game director of Blobun (CyanSorcery), covers design origin and level structure with unusual clarity. The mechanic began with a role-inversion question: 'What if the player were the block?' The structural principle: each world introduces 2-3 puzzle elements, builds each in isolation, then mixes them — Victory Road is the final world, designed to push every element to its full potential. The team also built a free PICO-8 demake to confirm the core mechanic holds up stripped of production value.
Sokoban (1982) — The 44-Year-Old Prototype of Meta-Puzzles
In 1982, Hiroyuki Imabayashi of Thinking Rabbit released Sokoban. Forty-four years later, walk-and-push is still the bedrock of Baba Is You and Patrick's Parabox. Reading the lineage backward from period context.