Are LLMs “just” next-token predictors?

Large language models (LLMs) are often labeled as just next-token predictors devoid of cognitive capacities such as thought or understanding. We argue that these deflationary claims are premature. Drawing on prominent theoretical and philosophical frameworks in cognitive science, we critically evaluate different forms of Justaism that dismiss LLM cognition by labeling LLMs as just simplistic entities without specifying or substantiating the critical capacities they supposedly lack. Our analysis highlights the need for a more nuanced discussion of LLM cognition, aiming to better inform future research and the development of machine intelligence.