TAG
#puzzlescript
0 reviews · 8 essays
Related essays
Fifteen puzzles branch from a single shared part: inside the Thinky Collective's relay-baton co-design
One piece today. I read, in the original English, a Thinky Games news article (by Corey Hardt, published July 24, 2026) from the edited, puzzle-focused outlet. It covers The Snake That Eats Puzzle Game Mechanics, the latest release from the Thinky Collective, a loose community of puzzle developers who take turns building on each other's work. This time, each contributor received just one shared part from the previous game and had to design a brand-new, one-screen puzzle around it — a constrained relay-baton approach that stitched together fifteen-plus miniature games into one collection.
From the same skeleton to a different puzzle: the Thinky Collective's “inherit just one thing” design experiment
One piece today. I read, in the original English, a Thinky Games article (by Corey Hardt, published July 24, 2026) from the edited puzzle-focused outlet. It covers how the Thinky Collective — a loose community of puzzle gamedevs — built the browser game The Snake That Eats Puzzle Game Mechanics. Normally they pass a single large PuzzleScript project around, each adding levels, art, or refinements. This time the method changed: each dev received just one piece of the previous person's game and had to make a miniature, single-level game from that shared element. The result is that adjacent games might share sprites while their mechanics have swapped, or keep the same level shape while a new look and context turn the puzzle into something else entirely. A constraint produced divergence, and a dozen-plus one-screen games were strung together. As an aspiring designer, I carried this home as a design template I want to try.
PuzzleScript (2013) — The One-Line Rule That Mass-Produced the World's “Pushing Games”
In October 2013, indie developer Stephen Lavelle (increpare) released PuzzleScript, a free browser-based puzzle engine whose Sokoban-style push rule fits on a single line of code. Traced forward, it runs through Alan Hazelden's early jam games into A Good Snowman Is Hard to Build, and — by Hempuli's own account — into the block-pushing puzzle revival that fed Baba Is You. Here the lineage is checked against the record.
Letting an LLM build a whole game, and an AI playtest it: ScriptDoctor and the state of automatic game design
One piece today. I read, in the original English, "ScriptDoctor: Automatic Generation of PuzzleScript Games via Large Language Models and Tree Search" by Sam Earle, Julian Togelius and colleagues (arXiv:2506.06524; a short paper submitted to the IEEE Conference on Games). They pick PuzzleScript — the description language for turn-based 2D-grid puzzle games created by increpare (Stephen Lavelle) — as a "model organism," and have an LLM generate a whole game (rules, sprites, levels), iterating on it using compiler errors and the results of a breadth-first-search player agent. Feeding in a few human-authored games as examples clearly raises quality, and reasoning models (o1, o3-mini) beat GPT-4o. But the sharpest lesson is on the failure side: the games that looked most complex were often complex only because of broken mechanics — solvable is not the same as good. A rich read for anyone thinking about automatic game design.
Inside Stephen Lavelle's Philosophy — Making the Refusal to Explain Into the Work
"Nah I don't feel like it." That was how Stephen Lavelle (Increpare) answered a player who asked him to explain his puzzle design. The prolific maker of 500-plus freeware games, the author of the free engine PuzzleScript and of Stephen's Sausage Roll. I read his philosophy, obsessions, failures, dilemmas and influences using only words he himself wrote.
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.
No prizes, clear constraints, real community — the design wisdom behind Thinky Puzzle Game Jam 6
One article today. We cover Corey Hardt’s May 15 announcement of the 6th annual Thinky Puzzle Game Jam (running June 20–28). The jam’s deliberate “no prizes” policy, 48-hour working limit, and PuzzleScript-friendly approach distinguish it from commercially-oriented jams, creating a space for pure design experimentation. Over 150 participants have already joined.
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'.
