"Klinkert embraced the idea and pursued it academically, ultimately earning a Master of Interactive Technology in Digital Game Development from SMU Guildhall. His early passion for interactive media has since evolved into a cutting-edge research focus. Now a PhD student in the Computer Science Department at SMU's Lyle School of Engineering, Klinkert is exploring how large language models (LLMs), such as ChatGPT, can be used to create non-playable characters (NPCs) that act and respond more like real people, with consistent personalities and believable emotional responses."
"In experiments that generated over 50,500 individual data points, Klinkert and his team found that GPT-4 achieved 73.98% accuracy in maintaining consistent personality traits across a range of interactions. This represents a major improvement over earlier AI models, which scored below 18% in comparable tests. The results suggest that advanced language models are capable of capturing and sustaining distinct personality profiles, a capability that could fundamentally change how game developers approach character creation."
A PhD student at SMU investigates using large language models to create non-playable characters (NPCs) with consistent personalities and believable emotional responses. Experiments generated over 50,500 data points and showed GPT-4 achieved 73.98% accuracy in maintaining consistent personality traits across varied interactions, compared with earlier models that scored below 18% in comparable tests. LLM-driven NPCs can adapt behavior dynamically, producing nuanced, context-aware, and emotionally appropriate responses rather than scripted, repetitive reactions. This capability could transform character development and game design by enabling more immersive, emotionally complex, and consistently behaved virtual characters.
Read at App Developer Magazine
Unable to calculate read time
Collection
[
|
...
]