Recent advances in large language models (LLMs) like OpenAI’s GPT-4 and Alphabet’s Bard have captivated people around the world, including cognitive scientists. Recently, Dillion et al. [1] asked whether LLMs can replace human participants in cognitive science research, noting some of the limitations of these models and offering a framework for integrating them into a cognitive science research pipeline. Here, we suggest that alongside asking whether LLMs can replace human participants, we ought to critically consider whether they should. What are we assuming when we explore the possibility of treating LLMs as proxies for human participants? And what are the costs of those assumptions? Examining these questions offers opportunities for us to reflect on our values as a field.