Uncovering Inverse Generativity: An Exploratory Prompt Analysis in LLM Platforms

Extended generativity theory states that while generativity lead to more users, more users also affect product boundaries of a platform. We seek to uncover the complex relationship by turning to large language model (LLM) platforms, such as ChatGPT, Gemini or GPT4. LLM platforms are unique, because they draw from an unbounded supply of complements and are considered as ”generative technologies”. Given a nearly infinite amount of complements, how does a growing user base and increasing user engagement impact the scope of services handled by LLM platforms? We assign over 300,000 prompts to NAICS product categories, analyzing the introduction of new categories over time to perform a quantitative analysis on the data. Our findings indicate that product boundaries tend to stabilize, showing degressive growth of product categories. We also discover that engaged users, whom we term ”complementary explorers”, are the primary drivers of product boundary expansion.