Posts
Comments
"I would let the five die and not feel guilty about it, because I am not the cause of their deaths."
A more charitable way of phrasing the consequentialist PoV here is that we care more about stopping the deaths than avoiding feelings of guilt. Yes, it's true that on certain accounts of morality you can't be held responsible for the deaths of five people in a Trolley Problem-esque scenario but the people will still be dead and consequentialism is the view that consequences trump all other considerations, like adherence to a deontological moral code, acting as a virtuous person would act, acting in a way that is perfecting of one's teleological nature etc.
Whether or not to hold people responsible for certain actions, like everything else on consequentialism, is, for us, a matter of determining whether that would lead to the best consequences.
Now, having said that, in practice consequentialists will behave like deontologists, virtue ethicists etc. quite a lot of the time. The reason for this is that having everyone go around making individual act utilitarian calculations for every potentially moral decision would likely be catastrophic and consequentialists are committed to avoiding terrible consequences whenever possible. It is usually better to have rules that are held to be exceptionless (but which can be changed to some degree, as is exactly the case with law) and teach people to have certain virtuous qualities so that they won't be constantly looking for loopholes in the rules and so on.
Does this mean that deontology, virtue ethics etc. are correct after all? No! Because it's still all being justified on consequentialist grounds, which is how we decide which rules to have and what counts as a virtue etc. in the first place. They will be the rules and virtues that lead to the best real world consequences. Because the kind of philosophical scenarios under which it is morally correct to push a fat man off a bridge are carefully constructed to be as inconvenient as possible the rules and virtues that we use in practice will probably forbid pushing people off bridges or raising the kind of person who would do that. This will mean that once in a blue moon someone really will find themselves in such a scenario and that person will likely make the wrong decision. It will also mean that the majority of the time, people will be making the right decisions and the consequences, overall, will be better than they would be if we let people decide for themselves on a case-by-case basis whether murdering someone maximised utility or not.
Consequentialism will still have counter-intuitive results. It should! There's no reason to think that our intuitions are an infallible guide to what's right. However, the kind of consequentialism attacked in a lot of philosophical arguments is a pretty naive version and it would be much more productive for everyone if we focussed on the stronger versions.
I'm like a third of the way through that Tegmark paper and I agree with it so far as I understand it but I don't see how it contradicts my view here. He claims that consciousness is a state of matter, i.e. a pattern of information. You can make a table out of a variety of materials, what matters is how the materials are arranged (and obviously brains are a lot more complicated than tables but it's what they can do by virtue of their arrangement in terms of the computations they can perform etc. that matters). To Tegmark (and I think to me, as well) consciousness is what certain kinds of information processing feel like from the inside. Which is is pretty much exactly what I'm saying here (that is equivalent to the story in my Moby Dick analogy). If the information processing is indistinguishable from the inside and internally forward-flowing in the sense that the resulting observer slice is a continuation of a previous one to same degree as meat-based humans, then mission accomplished. The upload was successful.
Aging? Don't see the connection. You seem to argue that information patterns are identity, but information patterns change greatly as you age. Mark at age 12, the troubled teenager, is very different than Mark at age 29, the responsible father of two. But I think most people would argue they are the same person, just at two separate points in time. Why?
I hold that Mark at age 29 is a legitimate continuation of Mark at age 12 but I also hold that this is true of Mark the upload, age 29. Neither are made of the same particles nor do they have the same mental states, as Mark, age 12. so I don't see why one is privileged with respect to the other. I actually make this same point, with almost the same example, in support of my position that non-meat based future observer slices are just as valid as meat based ones.
As for comatose patients, some possible objections that someone could make to my view are that it doesn't constitute a legitimate continuation of someone's conscious narrative if there is a significant interruption to that narrative, if significant time has passed between observer slices or if the later observer slice is running on a significantly different substrate. However, someone revived from a coma after ten years, say, ought to still be regarded as the same person even though there has been a massive discontinuity in their conscious narrative, ten years have passed between observer slices and, even on classical physics, every single one of the particles of which they were composed prior to the coma has now been replaced, meaning they are now literally running on a different substrate.
I'm not conflating them, I'm distinguishing between them. It's because they're already conflated that we're having this problem. I'm explicitly saying that the substrate is not what it's important here.
But this works both ways: what is the non-question begging argument that observer slices can only be regarded as older versions of previous slices in the case that the latter and the former are both running on meat-based substrates? As far as I can see, you have to just presuppose that view to say that an upload's observer slice doesn't count as a legitimate continuation.
I don't want to get drawn into a game of burden of proof tennis because I don''t think that we disagree on any relevant physical facts. It's more that my definition of identity just is something like an internally-forward-flowing, indistinguishable-from-the-inside sequence of observer slices and the definition that other people are pushing just...isn't.
All I can say, really, is that I think that Error and Mark et al are demanding an overly strong moment-to-moment connection between observer slices for their conception of identity. My view is easier to reconcile with things like quantum physics, ageing, revived comatose patients etc. and that is the sort of thing I appeal to by way of support.
It does if the the underlying issue is not actually an issue unless you choose certain, in my opinion inadequate, definitions of the key terms. I can't force you not to do that. I can point out that it has implications for things like going to sleep that you probably wouldn't like, I can try my best to help resolve the confusions that I believe have generated those definitions in the first place and I can try to flesh out, with tools like analogy, what I consider to be a more useful way of thinking about identity. Unfortunately, all of these things could potentially open me up to the charge of changing definitions but if that's the case I can only plead guilty because that's the appropriate response in situations where the debate happens to turn on the definitions of the relevant terms.
Error wrote that, in the case of non-destructive copying, he doesn't consider the upload to be a legitimate continuation of the copied entity but he does consider the flesh-and-blood, 'meat' version still walking around to be exactly that. I guess the intuition here is that this case effectively settles the question of identity because you would have a flesh-and-blood human who would have first-hand knowledge that it was the real one ("How can he be me? I'm here!")
I totally get that intuition. I can see how to most people it would be just obvious that the Machine-Version of Error is not the Meat-Version of Error. It's because it's not!
The problem is that neither of those entities are the thing that was copied. What was copied was Error as he was at a particular moment. The Meat-Version isn't that. The Meat-Version is not made of the same particles, nor does he have the same mental states. The Meat Version is a legitimate continuation of the old Meat Version but so is the Machine Version.
I remember having my photograph taken at the seaside when I was a child. When I look at the child in that photograph now I regard myself as the same person. I know we're not made of the same particles, I know that I have memories of events that he hasn't experienced yet, knowledge that he doesn't have, a completely different personality...On my definition of identity, however, I get to call him 'me.' I can consistently point at this photograph and say, 'that was me, when I was a child.'
What I want to know is, how can someone who rejects this view of identity point at a picture of himself as a child and say the same thing without opening the door for a future upload to look at a photograph of him right now (i.e. before the upload) and say, 'that was me, when I was made of meat'?
It's not the book, it's the story.
Moby Dick is not a single physical manuscript somewhere. If I buy Moby Dick I'm buying one of millions of copies of it that have been printed out over the years. It's still Moby Dick because Moby Dick is the words, characters, events etc. of the story and that is all preserved via copying.
A slight difference with this analogy is that Moby Dick isn't constantly changing as it ages, gaining new memories and whatnot. So imagine that Melville got half way through his epic and then ran out of space in the notebook that I want you to also imagine he was writing it in. So we have a notebook that contains the first half of Moby Dick (presumably, this is a pretty big notebook). Then he finishes it off in a second notebook.
Some time later he pulls a George Lucas and completely changes his mind about where his story was going ("Kill off Ahab? What was I thinking?") and writes a new version of the story where they go into a profitable, if ethically dubious, whaling business with rather more success than in the first version. This is then written up in a third notebook. Now we have three notebooks, the last two of which are both legitimate continuations of the first, carrying on from the exact same point at which the first notebook was ended.
There is no interesting sense in which one of these is some privileged original, as Eliezer puts it. If you can't get your head around that and want to say that, no, the published (in real life) version is the 'real' one imagine that the published version was actually the third notebook. There is no equivalent of publication for identity that could confer 'realness' onto a copy. In real life, neither or them are notebook 1 but they're both continuations of that story.
If Will Riker discovers that he was non-destructively copied by the Transporter and that there's another version of him running around, he will likely think, 'I don't acknowledge this guy as 'me' in any meaningful sense.' The other guy will think the same thing. Neither of them are the same person they were before they stepped into the Transporter. In fact, you are not the same person you were a few seconds ago, either.
Identify yourself as the book and your concept of identity has big problems with or without uploading. Start by reconciling that notion with things like quantum physics or even simple human ageing and you will find enough challenges to be getting on with without bringing future technology into it.
But you are not some collection of particles somewhere. You are the story, not the book. It's just that you are a story that is still in the process of being written. Uploading is no different that putting Moby Dick on a Kindle. If there's still a meat version of you running around then that is also a copy, also divergent from the original. The 'original' is (or was) you as you were when the copy was made.
I had noticed it and mistakenly attributed it to the sunk cost fallacy but on reflection it's quite different from sunk costs. However, it was discovering and (as it turns out, incorrectly) generalising the sunk cost fallacy that alerted me to the effect and that genuinely helped me improve myself, so it's a happy mistake.
One thing that helped me was learning to fear the words 'might as well,' as in, 'I've already wasted most of the day so I might as well waste the rest of it,' or 'she'll never go out with me so I might as well not bother asking her,' and countless other examples. My way of dealing it is to mock my own thought processes ('Yeah, things are really bad so let's make them even worse. Nice plan, genius') and switch to a more utilitarian way of thinking ('A small chance of success is better than none,' 'Let's try and squeeze as much utility out of this as possible' etc.).
I hadn't fully grasped the extent to which I was sabotaging my own life with that one, pernicious little error.
Yes, I agree.
I agree with your first paragraph, though in the interests of authorial intent, I'd like to stress that I don't think that Dawkins subscribes to Bayesianism and I don't think that The God Delusion has anything to do with Bayes. I was saying, 'this is about as close as he gets to Bayesianism and he's not quite there, which is a pity because he would have made for a good advocate. The best you could say is that he's tacitly using similar logic in certain places, one example being the seven point scale.'
I don't think that Dawkins or Tyson explicitly think of themselves as Bayesians. I would guess that they know the theorem and consider it useful in certain contexts without fully grasping its broader implications for science and epistemology. Or possibly they disagree that it has those implications, as many people do. Try introducing Tyson to some of Eliezer's views on MWI and see how he responds. My guess would be that he's missing a lot of the context necessary to appreciate that position even if he accepts that plausibility comes in degrees.
Dawkins is the more interesting case.
In the God Delusion, Dawkins proposes a seven point scale to measure one's degree of belief in theism with, I think, 0 being someone who was absolutely certain of its truth and 7 someone who was equally certain of its falsehood (placing himself at a 6.9). This probably maps onto probability theory pretty well but if he identified as a Bayesian I'd expect him to just use the conventions of probability theory (i.e. 0 and 1). In fact, that would have been an excellent opportunity to introduce Bayesianism. A straight forward introduction to Bayesianism from one of the best popular science writers published in a hugely successful book would have been extremely welcome but he doesn't go there. And I don't see why he wouldn't. He has a discussion of game theory in later additions of the Selfish Gene, for example, and I think he would do a good job of presenting something like that to a broader audience. I think it would have gone some way towards improving the quality of a lot of typical atheist reasoning, as well. I know I said and believed a lot of regrettably stupid things about theism and religion prior to catching the bug.
I do think that Dawkins would be sympathetic to Bayesian Epistemology if it was presented to him in the right way and you could make a good case that he tacitly presupposes some of the main assumptions but I just don't think he realises that he's doing it. It's possible to accept quite a lot of Bayesianism - both knowingly and unknowingly - without having that click.