GPT-5.6 Sol powers SQL-based game engine prototype
Peter Gostev used GPT-5.6 Sol to build DOOMQL, a proof-of-concept that replaces traditional game engines with SQLite as the core runtime. The project demonstrates how modern LLMs can tackle unconventional architectural problems: SQL queries now handle collision detection, enemy AI, rendering, and player movement in a playable Doom-like terminal game. This signals a shift in how developers think about LLM-assisted systems design, moving beyond chatbots toward using AI to explore radical reimaginings of foundational software patterns.
Modelwire context
ExplainerThe real story here isn't that Doom got reimplemented again. It's that SQL, a query language built around set operations on tabular data, is being used to express stateful, real-time simulation logic, and an LLM generated that architectural leap rather than a human engineer reaching for it deliberately.
Modelwire has no prior coverage to anchor this to directly. It sits at the intersection of two threads the site hasn't yet tracked: LLM-assisted software architecture exploration, and the growing practice of using constrained or unexpected substrates (databases, spreadsheets, config formats) as general-purpose compute. The closest intellectual neighborhood would be coverage of GPT-5-class models tackling open-ended engineering tasks, but without that archive, this stands alone as an early data point.
Watch whether Gostev or others publish performance benchmarks comparing the SQLite runtime against a minimal C engine on equivalent scene complexity. If query-based collision detection holds acceptable frame rates past trivial map sizes, the architectural argument becomes harder to dismiss as a stunt.
This analysis is generated by Modelwire’s editorial layer from our archive and the summary above. It is not a substitute for the original reporting. How we write it.
MentionsPeter Gostev · GPT-5.6 Sol · DOOMQL · SQLite · Simon Willison
Modelwire Editorial
This synthesis and analysis was prepared by the Modelwire editorial team. We use advanced language models to read, ground, and connect the day’s most significant AI developments, providing original strategic context that helps practitioners and leaders stay ahead of the frontier.
Modelwire summarizes, we don’t republish. Simon Willison originally reported this story as “DOOMQL”. The full content lives on simonwillison.net. If you’re a publisher and want a different summarization policy for your work, see our takedown page.