With Pierre Beckmann.
Argues that the concept of understanding needs to be re-engineered for artificial cognition in a way that is empirically informed by mechanistic interpretability research and theoretically informed by a grasp of the functions of the concept.
AI, conceptual engineering, mechanistic interpretability, understanding, conceptual change, functions
PDF coming soonWith Pierre Beckmann.
Offers a unifying account of understanding by reverse-engineering the function of both the state and the concept. Arges that we care about understanding because it grounds robust competence. Our concept of understanding evolved as an efficient proxy to track this elusive property, allowing us to identify who to trust and learn from. This highlights the sociality of understanding and how it shapes the character of human understanding. Understanding is the result of convergent pressures to predict the world using cognitive models that are not only accurate, but also compressed enough to be stored, demonstrated, and transmitted.
epistemology, AI, understanding, conceptual change, compression, competence
Download PDFPhilosophical Studies. With Pierre Beckmann. doi:10.48550/arXiv.2507.08017
Draws on detailed technical evidence from research on mechanistic interpretability (MI) to argue that while LLMs differ profoundly from human cognition, they do more than tally up word co-occurrences: they form internal structures that are fruitfully compared to different forms of human understanding, such as conceptual, factual, and principled understanding. We synthesize MI’s most relevant findings to date while embedding them within an integrative theoretical framework for thinking about understanding in LLMs. As the phenomenon of “parallel mechanisms” shows, however, the differences between LLMs and human cognition are as philosophically fruitful to consider as the similarities.
explainable AI, LLM, mechanistic interpretability, philosophy of AI, understanding, conceptual change
Download PDF