I'd argue that it's not that complicated. That if something meets the below five criteria, we must accept that it is conscious:
(1) It maintains a persisting internal model of an environment, updated from ongoing input.
(2) It maintains a persisting internal model of its own body or vehicle as bounded and situated in that environment.
(3) It possesses a memory that binds past and present into a single temporally extended self-model.
(4) It uses these models with self-derived agency to generate and evaluate counterfactuals: Predictions of alternative futures under alternative actions. (i.e. a general predictive function.)
(5) It has control channels through which those evaluations shape its future trajectories in ways that are not trivially reducible to a fixed reflex table.
This would also indicate that Boltzmann Brains are not conscious -- so it's no surprise that we're not Boltzmann Brains, which would otherwise be very surprising -- and that P-Zombies are impossible by definition. I've been working on a book about this for the past three years...
If you remove the terms "self", "agency", and "trivially reducible", it seems to me that a classical robot/game AI planning algorithm, which no one thinks is conscious, matches these criteria.
How do you define these terms without begging the question?
If anything has, minimally, a robust spatiotemporal sense of itself, and can project that sense forward to evaluate future outcomes, then it has a robust "self."
What this requires is a persistent internal model of: (A) what counts as its own body/actuators/sensors (a maintained self–world boundary), (B) what counts as its history in time (a sense of temporal continuity), and (C) what actions it can take (degrees of freedom, i.e. the future branch space), all of which are continuously used to regulate behavior under genuine epistemic uncertainty. When (C) is robust, abstraction and generalization fall out naturally. This is, in essence, sapience.
By "not trivially reducible," I don't mean "not representable in principle." I mean that, at the system's own operative state/action abstraction, its behavior is not equivalent to executing a fixed policy or static lookup table. It must actually perform predictive modeling and counterfactual evaluation; collapsing it to a reflex table would destroy the very capacities above. (It's true that with an astronomically large table you can "look up" anything -- but that move makes the notion of explanation vacuous.)
Many robots and AIs implement pieces of this pipeline (state estimation, planning, world models,) but current deployed systems generally lack a robust, continuously updated self-model with temporally deep, globally integrated counterfactual control in this sense.
If you want to simplify it a bit, you could just say that you need a robust and bounded spatial-temporal sense, coupled to the ability to generalize from that sense.
Is there a working title or some way to follow for updates?
> so it's no surprise that we're not Boltzmann Brains
I think I agree you've excluded them from the definition, but I don't see why that has an impact on likelihood.
I don't think any of these need to lead to qualia for any obvious reason. It could be a p-zombie why not.
The zombie intuition comes from treating qualia as an "add-on" rather than as the internal presentation of a self-model.
"P-zombie" is not a coherent leftover possibility once you fix the full physical structure. If a system has the full self-model (temporal-spatial sense) / world-model / memory binding / counterfactual evaluator / control loop, then that structure is what having experience amounts to (no extra ingredient need be added or subtracted).
I hope I don't later get accused of plagiarizing myself, but let's embark on a thought experiment. Imagine a bitter, toxic alkaloid that does not taste bitter. Suppose ingestion produces no distinctive local sensation at all – no taste, no burn, no nausea. The only "response" is some silent parameter in the nervous system adjusting itself, without crossing the threshold of conscious salience. There are such cases: Damaged nociception, anosmia, people congenitally insensitive to pain. In every such case, genetic fitness is slashed. The organism does not reliably avoid harm.
Now imagine a different design. You are a posthuman entity whose organic surface has been gradually replaced. Instead of a tongue, you carry an in‑line sensor which performs a spectral analysis of whatever you take in. When something toxic is detected, a red symbol flashes in your field of vision: “TOXIC -- DO NOT INGEST.” That visual event is a quale. It has a minimally structured phenomenal character -- colored, localized, bound to alarm -- and it stands in for what once was bitterness.
We can push this further. Instead of a visual alert, perhaps your motor system simply locks your arm; perhaps your global workspace is flooded with a gray, oppressive feeling; perhaps a sharp auditory tone sounds in your private inner ear. Each variant is still a mode of felt response to sensory information. Here's what I'm getting at with this: There is no way for a conscious creature to register and use risky input without some structure of "what it is like" coming along for the ride.
I have more or less the same views, although I can’t formulate them half as well as you do. I would have to think more in depth about those conditions that you highlighted in the GP; I’d read a book elaborating on it.
I’ve heard a similar thought experiment to your bitterness one from Keith Frankish: You have the choice between two anesthetics. The first one suppresses your pain quale, meaning that you won’t _feel_ any pain at all. But it won’t suppress your external response: you will scream, kick, shout, and do whatever you would have done without any anesthetic. The second one is the opposite: it suppresses all the external symptoms of pain. You won’t budge, you’ll be sitting quiet and still as some hypothetical highly painful surgical procedure is performed on you. But you will feel the pain quale completely, it will all still be there.
I like it because it highlights the tension in the supposed platonic essence of qualia. We can’t possibly imagine how either of these two drugs could be manufactured, or what it would feel like.
Would you classify your view as some version of materialism? Is it reductionist? I’m still trying to grasp all the terminology, sometimes it feels there’s more labels than actual perspectives.