The Umwelt Representation Hypothesis: Rethinking Universality
For AI and cognitive science researchers, it argues against the universality hypothesis, offering a more nuanced framework for understanding representational alignment.
The paper challenges the claim that all sufficiently capable systems converge on universal representations of reality, proposing instead that representational alignment arises from overlapping ecological constraints. It reviews evidence of systematic, adaptive differences across species and ANNs, reframing model comparison as mapping alignment clusters in constraint space.
Recent studies reveal striking representational alignment between artificial neural networks (ANNs) and biological brains, leading to proposals that all sufficiently capable systems converge on universal representations of reality. Here, we argue that this claim of Universality is premature. We introduce the Umwelt Representation Hypothesis (URH), proposing that alignment arises not from convergence toward a single global optimum, but from overlap in ecological constraints under which systems develop. We review empirical evidence showing that representational differences between species, individuals, and ANNs are systematic and adaptive, which is difficult to reconcile with Universality. Finally, we reframe ANN model comparison as a method for mapping clusters of alignment in ecological constraint space rather than searching for a single optimal world model.