"Intelligent" Randomness: Can LLMs Make Games More Fun?

BSc Thesis / MSc Thesis.

The goal of this project is to explore the feasibility and impact of replacing traditional random number generators (RNG) in games with large language models (LLMs). For example, in a slot machine game, the outcome is typically determined by a random number generated each time the “spin” button is pressed. In this project, students will investigate using an LLM to generate these numbers instead.

Research questions include:

• Does this approach improve player satisfaction (e.g., by prolonging player interaction with the game)?
• How much context should the LLM receive (e.g., should the prompt include previous spin outcomes or player profiles)?
• Is it technically feasible (e.g., what is the latency of LLM-generated numbers compared to traditional RNGs)?

Project goals include:

• Building a slot machine game that can be played online. The game will use either an RNG or an LLM to generate the next outcome.
• Analyzing game data and conducting and evaluating online user questionnaires to answer the research questions.

This project is ideal for students interested in building and analyzing a functional game. It offers opportunities to explore both technical and user experience aspects of integrating LLMs into software.