The Concept of Representation in ML: Beyond Plato and Aristotle
TL;DR
It is argued that philosophical resources from debates about mental representation in the philosophy of mind can clarify what is at stake in recent claims about the convergence of representational properties across different AI models, and explain why alignment evidence alone is insufficient for strong metaphysical conclusions.
Abstract
Representation is a central concept in modern machine learning, where it usually refers to internal encodings that support learning and generalization. As models scale and their capabilities become increasingly human-level, this representational language sometimes shifts from an engineering context into the more philosophically loaded domain of mental representation. We argue that this is the case for recent claims about the convergence of representational properties across different AI models. In particular, we assess the arguments developed in The Platonic Representation Hypothesis, according to which this convergence is driven by a unified structure of reality. We examine this claim by introducing arguments and ideas from debates about mental representation in the philosophy of mind. We argue that these philosophical resources can clarify what is at stake in such claims, explain why alignment evidence alone is insufficient for strong metaphysical conclusions, and suggest directions for future research.