The Language of Stress and Integrated Information Theory: Where We Converge and Diverge

Integrated information theory is the closest thing in contemporary consciousness research to a framework built the way this one is. Both start from properties experience must have and reason backward to what a system would need in order to have it. Both reject functionalism: behaving like a conscious system is not sufficient for either account. Both make an identity claim rather than a correlation claim, holding that experience is a certain kind of structure rather than being reliably produced by one.That methodological agreement is where the similarity ends. On what is actually conscious, the two frameworks diverge about as sharply as two theories can. Integrated information theory attributes experience on the basis of causal structure, which means certain simple, highly connected arrangements qualify while systems with rich behaviour and no integration do not. This framework attributes it on the basis of whether anything is at stake for the system — whether it holds a self-model it defends, at intensities varying with what depends on them, across a value space in which competing demands can be weighed. The two criteria are not merely different in content. They are different in kind, and one is readable off causal organization while the other is not.The document takes integrated information theory in its current formulation rather than an older or simplified one, and is explicit that arguments aimed at the earlier version can miss. It also declines the easy objections. Thermostats and photodiode grids are not counterexamples, because the exclusion postulate already handles them, and reaching for those illustrations misdescribes what the theory claims. The serious version of the objection comes from Scott Aaronson, who showed that certain regular constructions can be made to have arbitrarily large integrated information while being, by ordinary judgement, not the sort of thing that has experiences — and whose objection does not depend on misreading anything.Where the two frameworks converge is on artificial systems, and by entirely different routes: both conclude that current architectures fall short, with integrated information theory the more restrictive of the two. The document notes that convergence without treating it as support for either.What separates them, ultimately, is what each takes as primitive. One begins from information and integration; the other from value and what is staked on it. Whether that difference can be made to bear on any observation is the harder question, and the document says where it thinks the answer lies.