Causation is a feature of models, not reality. We need only suppose reality is one thing after another (or not even that! reality is just this moment, which for us contains a sensation we call a memory of past moments), and any causal structure is inferred to exist rather than something we directly observe. I make this argument in some detail here: https://www.lesswrong.com/posts/RMBMf85gGYytvYGBv/no-causation-without-reification
I agree that causal structure is inferred to exist, and never directly observable. However, the universe has certain properties that makes it very hard not to infer a causal structure if we want to model it, in particular:
A constant increase in entropy
Deterministic laws relating the past and the future
… which have symmetry across time and space
It seems exponentially hard to account for this without causality.
Formally, we often model causation as the action of one thing implying another, and we might formalize this with mathematical notation like A⟹B to mean some event or thing A causes some other event or thing B to happen.
I immediately disagree here, formally we usually model causality as our observations being generated by some sort of dynamical system. This cannot be specified with a mathematical notation like implication.
Try to imagine what the world is like if you’re not modeling it. Are you picturing atoms? Particles? Wave functions? Strings?
Wrong!
Those are all models we impose on the world to make sense of it. Useful ones, usually, but still models.
Sure, I know, but that doesn’t mean there’s no dynamical process generating the territory, only that we don’t know which one (and maybe can’t know).
The territory, noting that the notion that such a thing exists is itself another model, is a kind of soup of stuff that’s all mixed up and irreducible. You either have everything or nothing, for all time or no time. If you want anything else, you have to draw a map, make distinctions, and make choices.
Those distinctions are hopefully correlated with how the territory works, because that makes them useful for things like predicting what will happen (and we often call this correspondence “truth”), but they are not the territory itself. The territory just is; always has been, always will be.
This means that there’s no aspect of the territory that is causality. There’s no A, there’s no B, there’s no ⟹, there’s just “is”.
A and B are typically high-level features in our models that simplify the territory; as a result, the causality in our models will also be simplifications of the causality in the territory.
But without causality, I don’t see how you’d get thermodynamics. That seems like a “just is” that is best accounted for causally, even if we don’t have the exact causal theory underlying it. (Somehow, thermodynamics has managed to hold even as we’ve repeatedly updated our models, because it doesn’t depend on the exact causal model, but instead follows from deep aspects of the causal structure of reality.)
But if it’s not in the territory, why is causality so useful that it’s largely invisible to us, and why is it so hard for us to wrap our minds around what the world would be like if we didn’t perceive its presence?
Well, there clearly is some feature of the territory we’re carving out, making into a thing (“reifying”), and calling causality. But, we often forget, almost the instant we’ve done this, that we were the ones who did the carving, and then imagine that our perception of the world is how it really is.
This is important because it can lead us to making mistakes by thinking we understand something we don’t. We fail to notice how confused we are about the aspect of reality we call causality because it’s so close to our faces we don’t realize it’s a lens through which we are looking all the time.
But if causality is describing some feature of reality, and the feature it is describing is not itself causal, then what is the feature it is describing?
Causation is a feature of models, not reality. We need only suppose reality is one thing after another (or not even that! reality is just this moment, which for us contains a sensation we call a memory of past moments), and any causal structure is inferred to exist rather than something we directly observe. I make this argument in some detail here: https://www.lesswrong.com/posts/RMBMf85gGYytvYGBv/no-causation-without-reification
I feel a bit confused.
I agree that causal structure is inferred to exist, and never directly observable. However, the universe has certain properties that makes it very hard not to infer a causal structure if we want to model it, in particular:
A constant increase in entropy
Deterministic laws relating the past and the future
… which have symmetry across time and space
It seems exponentially hard to account for this without causality.
When opening the post:
I immediately disagree here, formally we usually model causality as our observations being generated by some sort of dynamical system. This cannot be specified with a mathematical notation like implication.
Sure, I know, but that doesn’t mean there’s no dynamical process generating the territory, only that we don’t know which one (and maybe can’t know).
A and B are typically high-level features in our models that simplify the territory; as a result, the causality in our models will also be simplifications of the causality in the territory.
But without causality, I don’t see how you’d get thermodynamics. That seems like a “just is” that is best accounted for causally, even if we don’t have the exact causal theory underlying it. (Somehow, thermodynamics has managed to hold even as we’ve repeatedly updated our models, because it doesn’t depend on the exact causal model, but instead follows from deep aspects of the causal structure of reality.)
But if causality is describing some feature of reality, and the feature it is describing is not itself causal, then what is the feature it is describing?