Usando LLMs para Programar Jogos de Tabuleiro e Varia\c{c}\~oes

TL;DR

This paper evaluates the ability of three large language models to generate code for board games and their variants, aiming to streamline game programming through AI assistance.

Contribution

It introduces a method to assess LLMs' effectiveness in creating board game code and variants, providing insights into their practical utility.

Findings

Claude, DeepSeek, and ChatGPT can generate playable board game code.

LLMs show varying success in creating game variants.

The study highlights potential and limitations of LLMs in game development.

Abstract

Creating programs to represent board games can be a time-consuming task. Large Language Models (LLMs) arise as appealing tools to expedite this process, given their capacity to efficiently generate code from simple contextual information. In this work, we propose a method to test how capable three LLMs (Claude, DeepSeek and ChatGPT) are at creating code for board games, as well as new variants of existing games.