Testing Codex Comprehension with PuzzleScript

banteg · x · 2026-07-13

The author asks if anyone has tested models like Fable/Sol to build games using PuzzleScript, noting the language is expressive enough for Sokoban-style mechanics and can combine complex rules.

The attached image tests whether Codex truly understands the boundaries of this constrained language. The focus isn't just "writing code," but whether the model can reason under constraints and generate rule-compliant designs.

Original post →

More from coding & agent

coding & agent channel →