In the 1990s, philosopher John Searle devised a thought experiment: a person sits in a room and, without knowing Chinese, follows instructions to produce correct answers in Chinese. From the outside, it seems they understand the language, but inside, it's just mechanical rule-following. Similarly, a computer imitating the brain can only simulate consciousness without actually possessing it. This argument is often reduced to a short phrase: "A simulation of the brain is no more conscious than a simulation of water is wet."
The authors of the new work look at the problem differently. They rely on the idea that consciousness is not a property of matter but the result of a specific computational organization. Water is wet because of molecular interactions, not because we call it so. Likewise, consciousness: if a system is internally structured like a brain, it will have consciousness — whether it's neurons or silicon chips.
Previously, researchers defined functions by how a system responds to stimuli. But this approach equates the brain with a giant lookup table. To avoid this, the authors introduce the concept of internal causal-computational realization. It accounts for how parts of the system influence each other, how their states change, and where the boundary between agent and environment lies.
The conclusion is conditional but important: if consciousness is an invariant of such internal organization, then any system that faithfully replicates it will be conscious. Whether biological, artificial, or simulated: it doesn't matter. You can deny consciousness to a simulation only by pointing out a specific internal structure it fails to reproduce.
as written by the authors arXiv:2606.15348
A common objection to artificial or simulated consciousness is that a simulated brain is no more conscious than simulated water is wet. We address this from the perspective of Intrinsic Computational Functionalism (ICF): if consciousness is computationally constituted, it depends not on externally imposed descriptions but on the computational structures a system physically realizes in virtue of its own causal-dynamical organization. In previous work we developed Canonical Functionalism as a mathematically precise special case of this anti-interpretivist program, identifying functional states by their complete future input-output roles under a fixed interface. Here we argue that this input-output construction, though important, is incomplete: as a behavioral boundary case of ICF, it makes lookup tables and unfolded systems that preserve the same boundary behavior canonically equivalent. A consciousness-relevant canonical representation must instead include internal mechanisms, interventions, and joint readouts belonging to the relevant intrinsic organization. We therefore define a mechanism-enriched canonical structure and use it to formulate Intrinsic Causal-Computational Realization (ICCR), a realization relation preserving physical implementation, intrinsic state individuation, transition structure, intervention profiles, and the relevant agent-body-world boundary. The central result is conditional: if conscious properties are invariants of intrinsic causal-computational organization, then any system satisfying ICCR realizes the same consciousness-relevant properties, whether biological, artificial, or simulated. We discuss objections including biological naturalism and integrated information theory. We conclude that to deny consciousness to a simulation, one must identify a consciousness-relevant intrinsic causal-computational structure that the simulation fails to realize.
The human brain consumes about 20 watts, like a light bulb in a refrigerator, yet it solves problems that are beyond supercomputers.
In Greg Egan's novel "Permutation City," people upload their consciousness into a computer simulation, and it continues to live as a digital person.