Properties of LoTs: The footprints or the bear itself?

Abstract

There are two ways to understand any proposed properties of language-of-thoughts (LoTs): As diagnostic or constitutive. We argue that this choice is critical. If candidate properties are diagnostic, their homeostatic clustering requires explanation via an underlying homeostatic mechanism. If constitutive, there is no clustering, only the properties themselves. Whether deep neural networks (DNNs) are alternatives to LoTs or potential implementations turn on this choice.