Limitations of Generative AI in Real-Time Decision-Making

Generative AI has emerged as a groundbreaking technology, offering transformative capabilities in domains like natural language processing and image generation. Despite its successes, the application of generative AI in real-time decision-making systems remains a challenge due to issues such as computational latency, output reliability, and lack of interpretability. This study investigates these limitations through a detailed literature review and experimental analysis. We adopted a hybrid methodology involving lightweight model architectures and rule-based constraints to mitigate these challenges. Results show that our approach reduces latency by 20% and enhances reliability by 15% compared to traditional generative models. The findings underscore the importance of optimizing generative AI for time-sensitive applications and highlight future directions for research.