↑ comment by dxu ·
2019-07-10T23:54:05.616Z · LW(p) · GW(p)
It's a common belief, but it appears to me quite unfounded, since it hasn't happened in millennia of trying. So, a direct observation speaks against this model.
It's another common belief, though separate from the belief of reality. It is a belief that this reality is efficiently knowable, a bold prediction that is not supported by evidence and has hints to the contrary from the complexity theory.
General Relativity plus the standard model of the particle physics have stood unchanged and unchallenged for decades, the magic numbers they require remaining unexplained since the Higgs mass was predicted a long time ago. While this suggests that, yes, we will probably never stop being surprised by the
universe observations, I make no such claims.
I think at this stage we have finally hit upon a point of concrete disagreement. If I'm interpreting you correctly, you seem to be suggesting that because humans have not yet converged on a "Theory of Everything" after millennia of trying, this is evidence against the existence of such a theory.
It seems to me, on the other hand, that our theories have steadily improved over those millennia (in terms of objectively verifiable metrics like their ability to predict the results of increasingly esoteric experiments), and that this is evidence in favor of an eventual theory of everything. That we haven't converged on such a theory yet is simply a consequence, in my view, of the fact that the correct theory is in some sense hard to find. But to postulate that no such theory exists is, I think, not only unsupported by the evidence, but actually contradicted by it--unless you're interpreting the state of scientific progress quite differently than I am.*
That's the argument from empirical evidence, which (hopefully) allows for a more productive disagreement than the relatively abstract subject matter we've discussed so far. However, I think one of those abstract subjects still deserves some attention--in particular, you expressed further confusion about my use of the word "coincidence":
I am still unsure what you mean by coincidence here. The dictionary defines it as "A remarkable concurrence of events or circumstances without apparent causal connection." and that open a whole new can of worms about what "apparent" and "causal" mean in the situation we are describing, and we soon will be back to a circular argument of implying some underlying reality to explain why we need to postulate reality.
I had previously provided a Tabooed version [LW(p) · GW(p)] of my statement, but perhaps even that was insufficiently clear. (If so, I apologize.) This time, instead of attempting to make my statement even more abstract, I'll try taking a different tack and making things more concrete:
I don't think that, if our observations really were impossible to model completely accurately, we would be able to achieve the level of predictive success we have. The fact that we have managed to achieve some level of predictive accuracy (not 100%, but some!) strongly suggests to me that our observations are not impossible to model--and I say this for a very simple reason:
How can it be possible to achieve even partial accuracy at predicting something that is purportedly impossible to model? We can't have done it by actually modeling the thing, of course, because we're assuming that the thing cannot be modeled by hypothesis. So our seeming success at predicting the thing, must not actually be due to any kind of successful modeling of said thing. Then how is it that our model is producing seemingly accurate predictions? It seems as though we are in a similar position to a lazy student who, upon being presented with a test they didn't study for, is forced to guess the right answers--except that in our case, the student somehow gets lucky enough to choose the correct answer every time, despite the fact that they are merely guessing, rather than working out the answer the way they should.
I think that the word "coincidence" is a decent way of describing the student's situation in this case, even if it doesn't fully accord with your dictionary's definition (after all, whoever said the dictionary editors determine have the sole power to determine a word's usage?)--and analogously, our model of the thing must also only be making correct predictions by coincidence, since we've ruled out the possibility, a priori, that it might actually be correctly modeling the way the thing works.
I find it implausible that our models are actually behaving this way with respect to the "thing"/the universe, in precisely the same way I would find it implausible that a student who scored 95% on a test had simply guessed on all of the questions. I hope that helps clarify what I meant by "coincidence" in this context.
*You did say, of course, that you weren't making any claims or postulates to that effect. But it certainly seems to me that you're not completely agnostic on the issue--after all, your initial claim was "it's models all the way down", and you've fairly consistently stuck to defending that claim throughout not just this thread, but your entire tenure on LW. So I think it's fair to treat you as holding that position, at least for the sake of a discussion like this.
Replies from: shminux
↑ comment by shminux ·
2019-07-24T04:33:42.604Z · LW(p) · GW(p)
Sadly, I don't think we are converging at all.
It seems to me, on the other hand, that our theories have steadily improved over those millennia (in terms of objectively verifiable metrics like their ability to predict the results of increasingly esoteric experiments)
and that this is evidence in favor of an eventual theory of everything.
I don't see why it would be. Just because one one is able to march forward doesn't mean that there is a destination. There are many possible alternatives. One is that we will keep making more accurate models (in a sense of making more detailed confirmed predictions in more areas) without ever ending anywhere. Another is that we will stall in our predictive abilities and stop making measurable progress, get stuck in a swamp, so to speak. This could happen, for example, if the computational power required to make better predictions grows exponentially with accuracy. Yet another alternative is that the act of making a better model actually creates new observations (in your language, changes the laws of the universe). After all, if you believe that we are agents embedded in the universe, then our actions change the universe, and who is to say that at some point they won't change even what we think are the fundamental laws. There is an amusing novel about the universe protecting itself from overly inquisitive humans: https://en.wikipedia.org/wiki/Definitely_Maybe_(novel)
How can it be possible to achieve even partial accuracy at predicting something that is purportedly impossible to model?
I don't believe I have said anything of the sort. Of course we are able to build models. Without predictability life, let alone consciousness would be impossible, and that was one of my original statements. I don't know what is it I said that gave you the impression that abandoning the concept of objective reality means we ought to lose predictability in any way.
But to postulate that no such theory exists is, I think, not only unsupported by the evidence, but actually contradicted by it--unless you're interpreting the state of scientific progress quite differently than I am.*
I don't postulate it. You postulate that there is something at the bottom. I'm simply saying that there is no need for this postulate, and, given what we see so far, every prediction of absolute knowledge in a given area turned out to be wrong, so, odds are, whether or not there is something at the bottom or not, at this point this postulate is harmful, rather than useful, and is wholly unnecessary. Our current experience suggests that it is all models, and if this ever changes, that would be a surprise.