This article examines the need for copyright reform in response to the transformative impact of generative AI. It identifies key legal challenges, including the absence of clear criteria for authorship, and the infringement risks associated with both inputs (training of large language models) and outputs (AI-generated content). The authors contend that two overarching themes will drive the development of copyright law: creativity and fairness. Through a comparative analysis of how three jurisdictions – US, China and Singapore – have addressed these challenges, the article offers practical and forward-looking insights for navigating the complex copyright landscape of the generative AI era.