ABORDAGEM DINÂMICA DE PRODUÇÃO DE CONTEÚDO LITERÁRIO UTILIZANDO IAS DE CONTROLE

Abstract

This undergraduate thesis investigates the capacity of generative artificial intelligence (AI) in the production and evaluation of literary content, focusing on the comparison between human and computational perceptions of quality. The study conducts a comparative analysis between an original short story, authored by the researcher, and three narratives generated by state-of-the-art models: Claude 4 Sonnet (Anthropic), Grok 4 (X), and GPT-5 (OpenAI). The methodology began with the creation of an original short story with a pre-defined theme and Three-Act Structure. Subsequently, prompt engineering was applied to instruct the AI models to generate analogous texts in a single attempt. The resulting works were evaluated by a panel of non-expert human judges and by other AI models, based on criteria of novelty, surprise, diversity, and linguistic complexity. This study aims to contribute to the debate regarding the potentials and challenges of AI in cultural production, offering insights into the creative collaboration between humans and machines.