Modelling the Formation of Reality, Step by Step

Abstract

Relational and information-based descriptions of reality have been explored in many domains, from relational readings of quantum mechanics to proposals that physical phenomena arise from the organization of information. This paper approaches the same questions from an unexpected side: sustained interaction with a large language model. In that interaction, a distinctive dynamic is visible in sequence. A space of weighted possibilities, shaped by context, realizes one continuation; the realization immediately feeds back and reshapes the conditions for the next. In other domains, the space of possibilities behind a single event can only be reconstructed across many runs but in a language model, it is visible at every step. And because nothing runs in the model between two realizations, each step can also be replayed. The paper abstracts this loop into a substrate-neutral description of context fields meeting in a shared configuration and lays four systems side by side under the same steps: a human, a language model, a detector, a particle, each described in the vocabulary of its own domain. Based on this, it proposes an examination: a conditioning signature obtained in controlled settings of a large language model and compared with how recorded distributions in physical domains respond to their own experimental knobs, with the criteria for failure stated in advance. The framework is then placed among its relational and informational neighbours: it shares their direction and differs in what it needs to assume and in the instrument it offers. Finally, the paper states the questions the reading changes – wherever a description says "spontaneous", it reads a missing participant – and what the reading forbids. It does not propose a theory but a lens; the checking belongs to the domains it touches.