Generative AI in Mafia-like Game Simulation

TL;DR

This study evaluates GPT-4's capabilities in mafia-style game simulations, highlighting its strengths in interaction and decision-making, while noting limitations in bluffing and predicting opponents, with implications for future AI development.

Contribution

The paper demonstrates GPT-4's improved performance over GPT-3.5 in game scenarios and discusses challenges in making AI more human-like in complex social games.

Findings

GPT-4 outperforms GPT-3.5 in relevant questioning and responses

Limitations in bluffing and predicting opponent moves remain

Potential for further AI development in social game contexts

Abstract

In this research, we explore the efficacy and potential of Generative AI models, specifically focusing on their application in role-playing simulations exemplified through Spyfall, a renowned mafia-style game. By leveraging GPT-4's advanced capabilities, the study aimed to showcase the model's potential in understanding, decision-making, and interaction during game scenarios. Comparative analyses between GPT-4 and its predecessor, GPT-3.5-turbo, demonstrated GPT-4's enhanced adaptability to the game environment, with significant improvements in posing relevant questions and forming human-like responses. However, challenges such as the model;s limitations in bluffing and predicting opponent moves emerged. Reflections on game development, financial constraints, and non-verbal limitations of the study were also discussed. The findings suggest that while GPT-4 exhibits promising advancements over earlier models, there remains potential for further development, especially in instilling more human-like attributes in AI.