Perceived AGI: Believability as Dimensional Completeness, Not Capability
Human-Computer InteractionArtificial Intelligence
Summary
The authors suggest that while large language models are good at tasks, they often feel flat in long conversations because they lack what people call "perceived mind"—the impression that the model has an inner life. They propose that this comes from showing four key personal stances related to time, truth, entropy, and love, which humans use to sense others' minds. The paper presents a framework to make these stances appear through behaviors like taking initiative and turn timing in conversation, with some early tests implemented. The authors emphasize this is about creating the appearance of mind, not actual consciousness, and they plan future studies to test these ideas.
Authors
Sebastian Cochinescu
Abstract
Large language models are broadly capable, yet in sustained one-to-one conversation they still read as flat: competent, responsive, and somehow not quite the presence of a mind. We hypothesize that a central missing ingredient is not more capability but dimensional completeness. We propose that the believability of an artificial interlocutor -- the degree to which a user attributes an inner life to it, which we call perceived mind -- is governed by whether the agent expresses a small set of first-person stances that humans use as evidence of mind, and that this is separable from task intelligence. We name four such dimensions -- time, truth, entropy, and love -- each defined as a behavioral stance rather than a benchmark competency, each with a human analog and a concrete emulation path; the time dimension already has an author-reported prototype. We identify an observable behavior layer -- initiative (unprompted action) and cadence (the shape and timing of turns) -- through which the stances surface in conversation, both partially realized as deployed features in a production companion application. We state six falsifiable predictions that a later pre-registered study will test, separating those that are pre-registrable now from those that remain conjectures pending operationalization. This is a conceptual framework: it reports no human-subjects data, and its central comparative claims are predictions, not findings. Throughout we hold a firm boundary -- the object is inferrable interiority, not interiority; this is perception engineering, not a theory of machine consciousness -- and we treat the resulting attachment and manipulation risks as load-bearing rather than incidental.