Abstract: The rapid rise of AI in science presents a paradox. Analyzing 67.9 million research papers across six major fields using a validated language model (F1=0.876), we explore AI's impact on science. Scientists who adopt AI tools publish 67.37% more papers, receive 3.16 times more citations, and become team leaders 4 years earlier than non-adopters. This individual success correlates with concerning on collective effects: AI-augmented research contracts the diameter of scientific topics studied, and diminishes follow-on scientific engagement. Rather than catalyzing the exploration of new fields, AI accelerates work in established, data-rich domains. This pattern suggests that while AI enhances individual scientific productivity, it may simultaneously reduce scientific diversity and broad engagement, highlighting a tension between personal advancement and collective scientific progress.
Loading