# Philosophy of Technology LLMs **Abstract:** It is sometimes assumed that Large Language Models (LLMs) know language, or that they know that Paris is the capital of France. But what–if anything–do LLMs actually know? In this paper, I argue that LLMs can acquire tacit knowledge as defined by Martin Davies (1990). Whereas Davies himself denies that neural networks can acquire tacit knowledge, I demonstrate that certain architectural features of LLMs satisfy the constraints of semantic descriptions, syntactic structure, and causal systematicity. Notably, identifying and describing tacit knowledge in such systems can render them explainable, allowing us to better describe, predict, and intervene on their behavior.