Large language models (LLMs) are rapidly being implemented in a wide range of disciplines, with the promise of unlocking new possibilities for scientific exploration. However, while the development of LLMs brings opportunities to science, it also comes with pressing challenges. This Focus discusses the current state of the art, highlights key obstacles, and examines some of the potential pitfalls and biases of implementing and using LLMs across different domains, including healthcare, urban planning, chemistry, linguistics, humanities, and computer science. In addition, the Focus explores emerging technologies – such as neuromorphic engineering – that show promise in enhancing the energy efficiency of LLM deployment on hardware platforms.
