LESSWRONG
LW

Comment Permalink

I find this an immensely valuable insight: continuity, or "haecceity", is the critical element of self which naive uploading scenarios dismiss. Our current rational situation of self as concept-in-brain has no need for continuity, which is counterintuitive.

We know a good deal about the universe, but we do not yet know it in its entirety. If there were an observer outside of physics, we might suspect they care great deal about continuity, or their laws might. Depending on your priors, and willingness to accept that current observational techniques cannot access all-that-there-is, it might be worth embedding some value to haecceity near your value of self.

Contrast grow-and-prune uploading with slice-and-scan uploading: the latter will be anathema to the vast majority of humanity; they may "get over it", but it'll be a long battle. And slice-and-scan will probably be much slower to market. Start with Glass and EEGs: we'll get there in our lifetime using grow-and-prune, and our AIs will grow up with mentors they can respect.

See in context

6 Continuity in Uploading

by Error

17th Jan 2014

2 min read

6

I don't acknowledge an upload as "me" in any meaningful sense of the term; if I copied my brain to a computer and then my body was destroyed, I still think of that as death and would try to avoid it.

A thought struck me a few minutes ago that seems like it might get around that, though. Suppose that rather than copying my brain, I adjoined it to some external computer in a kind of reverse-Ebborian act; electrically connecting my synapses to a big block of computrons that I can consciously perform I/O to. Over the course of life and improved tech, that block expands until, as a percentage, most of my thought processes are going on in the machine-part of me. Eventually my meat brain dies -- but the silicon part of me lives on. I think I would probably still consider that "me" in a meaningful sense. Intuitively I feel like I should treat it as the equivalent of minor brain damage.

Obviously, one could shorten the period of dual-life arbitrarily and I can't point to a specific line where expanded-then-contracted-consciousness turns into copying-then-death. The line that immediately comes to mind is "whenever I start to feel like the technological expansion of my mind is no longer an external module, but the main component," but that feels like unjustified punting.

I'm curious what other people think, particularly those that share my position on destructive uploads.

---

Edited to add:

Solipsist asked me for the reasoning behind my position on destructive uploads, which led to this additional train of thought:

Compare a destructive upload to non-destructive. Copy my mind to a machine non-destructively, and I still identify with meat-me. You could let machine-me run for a day, or a week, or a year, and only then kill off meat-me. I don't like that option and would be confused by someone who did. Destructive uploads feel like the limit of that case, where the time interval approaches zero and I am killed and copied in the same moment. As with the case outlined above, I don't see a crossed line where it stops being death and starts being transition.

An expand-contract with interval zero is effectively a destructive upload. So is a copy-kill with interval zero. So the two appear to be mirror images, with a discontinuity at the limit. Approach destructive uploads from the copy-then-kill side, and it feels clearly like death. Approach them from the expand-then-contract side, and it feels like continuous identity. Yet at the limit between them they turn into the same operation.

Whole Brain Emulation

Personal Blog

6

Continuity in Uploading

New Comment

88 comments, sorted by

top scoring

Click to highlight new comments since: Today at 6:37 PM

Some comments are truncated due to high volume. (⌘F to expand all)Change truncation settings

[-]scientism11y60

I agree that uploading is copying-then-death. I think you're basically correct with your thought experiment, but your worries about vagueness are unfounded. The appropriate question is what counts as death? Consider the following two scenarios: 1. A copy of you is stored on a supercomputer and you're then obliterated in a furnace. 2. A procedure is being performed on your brain, you're awake the entire time, and you remain coherent throughout. In scenario 1 we have a paradigmatic example of death: obliteration in a furnace. In scenario 2 we have a paradigm... (read more)

2Jonathan Paulson11y

You are dodging the question by appealing to the dictionary. The dictionary will not prove for you that identity is tied to your body, which is the issue at hand (not "whether your body dies as the result of copying-then-death", which as you point out is trivial)

2torekp11y

All true, but it just strengthens the case for what you call "stipulating a new meaning for the words 'survival', 'death', etc". Or perhaps, making up new words to replace those. Contemplating cases like these makes me realize that I have stopped caring about 'death' in its old exact meaning. In some scenarios "this will kill you" becomes a mere technicality.

1scientism11y

Mere stipulation secures very little though. Consider the following scenario: I start wearing a medallion around my neck and stipulate that, so long as these medallion survives intact, I am to be considered alive, regardless of what befalls me. This is essentially equivalent to what you'd be doing in stipulating survival in the uploading scenario. You'd secure 'survival', perhaps, but the would-be uploader has a lot more work to do. You need also to stipulate that when the upload says "On my 6th birthday..." he's referring to your 6th birthday, etc. I think this project will prove much more difficult. In general, these sort of uploading scenarios are relying on the notion of something being "transferred" from the person to the upload, and it's this that secures identity and hence reference. But if you're willing to concede that nothing is transferred - that identity isn't transferrable - then you've got a lot of work to do in order to make the uploading scenario consistent. You've got to introduce revised versions of concepts of identity, memory, self-reference, etc. Doing so consistently is likely a formidable task. I should have said this about the artificial brain transplant scenario too. While I think the scenario makes sense, it doesn't secure all the traditional science fiction consequences. So having an artificial brain doesn't automatically imply you can be "resleeved" if your body is destroyed, etc. Such scenarios tend to involve transferrable identity, which I'm denying. You can't migrate to a server and live a purely software existence; you're not now "in" the software. You can see the problems of reference in this scenario. For example, say you had a robot on Mars with an artificial brain with the same specifications as your own. You want to visit Mars, so you figure you'll just transfer the software running on your artificial brain to the robot and wake up on Mars. But again, this assumes identity is transferrable in some sense, which it is not. But yo

0torekp11y

No, and that is the point. There are serious drawbacks of the usual notions of welfare, at least in the high-tech future we are discussing, and they need serious correcting. Although, as I mentioned earlier, coining new words for the new concepts would probably facilitate communication better, especially when revisionaries and conservatives converse. So maybe "Yi" could be the pronoun for "miy" branching future, in which Yi go to Mars as well as staying home, to be merged later. There is no contradiction, either: my welfare is what I thought I cared about in a certain constellation of cares, but now Yi realize that was a mistake. Misconceptions of what we truly desire or like are, of course, par for the course for human beings; and so are corrections of those conceptions.

[-]mwengler11y50

Upload shmupload.

Lets remove unnecessary complications and consider the more essential question. You are knocked out. While unconscious, a particle-for-particle copy of you is made with all identical energy levels, momenta, spins, colors, flavors, and any other quantum states associated with any of the particles in your body. The only differences are all the particles in the new copy are 3 m to the east of the particles in the original. The unconscious copies are placed someplace nice and revived approximately simultaneously.

Pretty obviously, neit... (read more)

3[anonymous]11y

Yes, it is of importance to the me right here, right now, in the present. Under one interpretation I wake up in the other room. In the other I do not - it is some other doppelgänger which shares my memories but whose experiences I do not get to have. If I somehow find myself in the room with my clone, it's true that there's no way short of checking external evidence like security footage or somesuch to determine which is the real me. That is true. But that is a statement about my knowledge, not the world as it exists. The map is not the territory. If I were to wake up in the other room with the clone nearby, it no longer matters which one of us is the original or not. He isn't me. He is a separate person that just happens to share all of the same memories and motivations that I have. I want to say that I wouldn't even give this copy of me the time of day, but that would be rhetorical. In some ventures he would be my greatest friend, in others my worst enemy. (Interestingly I could accuratly tell which right now by application of decision theory to the variants of the prisoner's delima.) But even when I choose to interfere in his affairs, it is not for directly self-serving reasons - I help him for the same reason I'd help a really close friend, I hurt him for the same reason I'd hinder a competitor. The truth has real implications for the me that does exist, in the here and now. Do I spend not-insignificant sums of money on life insurance to cover cryonic preservation for me and my family, thereby foregoing other opportunities? Do I consider assisted suicide and cryonic preservation when I am diagnosed with a terminal or dibilitating disese of the brain? Do I stipulate revival instead of uploading in my cryonics contract, knowing that it might mean never being revived if the technology can not be developed before my brain deteriorates too much? Do I continue to spend time debating this philosophical point with other people on the Internet, in the hope that they t

1Jonathan Paulson11y

I don't understand how to distinguish "the clone is you" from "the clone is a copy of you". Those seem like identical statements, in that the worlds where yon continue living and the world where the clone replaces you are identical, atom for atom. Do you disagree? Or do you think there can be a distinction between identical worlds? If so, what is it? In the same sense, future-you isn't you either. But you are willing to expend resources for future-you. What is the distinction?

0[anonymous]11y

Yes, to the universe as witnessed by an outside observer, and to the law. The important difference is haecceity, which to an naive inside view is currently meaningless, but to any intuitive observer or reflective agent becomes relevant. Objective history exists, it's just that we humans-within-universe simply cannot access it. There are countless unknowns about the universe that we know about. There are also almost certainly unknown unknowns. Haecceity currently lies essential to sense of self, but in a more broadly aware context perhaps its value could be concretized and rationalized.

[-]PDH11y40

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 y... (read more)

3randallsquared11y

"Moby Dick" can refer either to a specific object, or to a set. Your argument is that people are like a set, and Error's argument is that they are like an object (or a process, possibly; that's my own view). Conflating sets and objects assumes the conclusion.

0PDH11y

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.

0randallsquared11y

Hm. Does "internally-forward-flowing" mean that stateA is a (primary? major? efficient? not sure if there's a technical term, here) cause of stateB, or does it mean only that internally, stateB remembers "being" stateA? If the former, then I think you and I actually agree.

-1[anonymous]11y

Details please. Quantum physics? Max Tengmark does this subject better than I have the time to. And btw, he's on our side. 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? Comatose patients? Connection please? I am not aware what objective data you are pointing to on this.

0PDH11y

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. 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

-1[anonymous]11y

Changing the definition doesn't resolve the underling issue...

5PDH11y

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 pa

-2[anonymous]11y

Just because the machine version remembers what the meat version did, doesn't mean the conscious meat version didn't die in the uploading process. Nothing you have said negates the death + birth interpretation. Your definitions are still missing the point.

-3Leonhart11y

Sure, something particular happens to the meat version. But (it is asserted) that thing happens to you all the time anyway and nobody cares. So the objection is to you wasting the nice short code "death" on such an unimportant process. This is a way in which words can be wrong.

-6[anonymous]11y

[-]jaime200011y30

How do you feel about the continuous uploading procedure described in "Staring into the Singularity"?

[-]Shmi11y30

I don't acknowledge an upload as "me" in any meaningful sense of the term

What about if your mind is uploaded, then downloaded into your clone previously grown without any brain functions? Would you consider the new meat you as "you"?

-1[anonymous]11y

Why would he? I predict he clearly would not, since he was already dead. What point are you trying to make?

1Error11y

Upvoted for correct prediction.

1Shmi11y

My next question would have been about what Error feels about star trek-style transporters (which temporarily convert a person into a plasma beam).

-1Aleksander11y

And he in turn might respond by asking how you feel about thinking like a dinosaur.

1Error11y

I would not be enthusiastic about Star Trek transporters, no. And yes, I would like to know how shminux feels about thinking like a dinosaur; that does seem to capture my intuitions rather well.

0Shmi11y

First, I would like to acknowledge that ready access to a cloning tech would require a significant reevaluation of metaethics. Second, dealing with lost ACKs is the least of the worries, and the show's premise resulted from a poorly constructed communication protocol. So this particular issue can be solved technologically. For example: mandatory induced unconsciousness similar to general anesthesia, for the duration of transport and success confirmation process, to prevent the subject from anxiously waiting for positive confirmation if the initial ACK is lost. Just to have a taste of the real ethical issues of cloning, note that many forms of utilitarianism mandate immediately creating as many clones as possible as long as their lives are at least "barely worth celebrating", in Eliezer's words. Another issue is cloning the most useful individuals at the expense of the quality of life of the least useful. Refer to your favorite transhumanist sci-fi for more details and examples. I recall a humorous one of the Lem's Ijon Tichy stories (can't find a link ATM), where on one of the planets under constant heavy meteorite bombardment the mandatory logging and cloning tech was used as a routine way to revive the victims, replacing fatalities with minor inconveniences. Finally, yours and Mark_Friedenbach's aversion to radical versions of suspended animation is so foreign to me, I have trouble steelmanning your position.

4Aleksander11y

I recall a humorous one of the Lem's Ijion Tichy stories (can't find a link ATM), where on one of the planets under constant heavy meteorite bombardment the mandatory logging and cloning tech was used as a routine way to revive the victims, replacing fatalities with minor inconveniences. It's the Twenty-Third Voyage in Star Diaries.

[-]trist11y30

I find the whole question less confusing when viewed from the other direction. After the upload, the uploaded you will view the current you as it's past. If the upload is nondestructive, the non-uploaded you will also.

1[anonymous]11y

What if I rewire your neurons so you think you're Donald Trump? Would that make you Donald Trump? If Mr. Trump died in a tragic boating accident tomorrow, could his family rest easy knowing that he didn't actually experience death, but lives on in you?

3trist11y

If you rewrite my nuerons such that I have all of Donald Trump's memories (or connections) and none of my own, yes. If you only rewrite my name, no, for I would still identify with the memories. There's lots of space between those where I'm partially me and partially him, and I would hazard to forward-identify with beings in proportion to how much of my current memories they retain, possibly diluted by their additional memories.

1[anonymous]11y

Ok, what if - like Eternal Sunshine of the Spotless Mind - I slowly over a period of time eliminate your memories. Then maybe - like Dark City - I go in and insert new memories, maybe generic, maybe taken from someone else. This can be done either fast or slowly if it matters. This future continuation of your current self will have nothing other than a causal & computational connection to your current identity. No common memories whatsoever. Would you expect to experience what this future person experiences?

0TheOtherDave11y

Based on your other comments, I infer that you consider this question entirely different from the question "Are you willing to consider this future person you?" Confirm?

0[anonymous]11y

Correct.

-1TheOtherDave11y

Cool, thanks. Given that, and answering for my own part: I'm not sure what any person at any time would possibly ever observe differentially in one case or the other, so I honestly have no idea what I'd be expecting or not expecting in this case. That is, I don't know what the question means, and I'm not sure it means anything at all.

0[anonymous]11y

That's fair enough. You got the point with your first comment, which was to point out that issues of memory-identity and continuous-experience-identity are / could be separate.

-1TheOtherDave11y

Perhaps I understand more than I think I do, then. It seems to me that what I'm saying here is precisely that those issues can't be separated, because they predict the same sets of observations. The world in which identity is a function of memory is in all observable ways indistinguishable from the world in which identity is a function of continuous experience. Or, for that matter, of cell lineages or geographical location or numerological equivalence.

1[anonymous]11y

And I'm saying that external observations are not all that matters. Indeed it feels odd to me to hold that view when the phenomenon under consideration is subjective experience itself.

-1TheOtherDave11y

I didn't say "external observations". I said "observations." If you engage with what I actually said, does it feel any less odd?

0[anonymous]11y

You said "predict the same set of observations" which I implicitly took to mean "tell me something I can witness to update my beliefs about which theory is correct," to which the answer is: there is nothing you - necessarily external - can witness to know whether my upload is death-and-creation or continuation. I alone am privy to that experience (continuation or oblivion), although the recorded memory is the same in either case so there's no way clone could tell you after. You could use a model of consciousness and a record of events to infer which outcome occurred. And that's the root issue here, we have different models of consciousness and therefore make different inferences.

-1TheOtherDave11y

You keep insisting on inserting that "external" into my comment, just as if I had said it, when I didn't. So let me back up a little and try to be clearer. Suppose the future continuation you describe of my current self (let's label him "D" for convenience) comes to exist in the year 2034. Suppose D reads this exchange in the archives of LessWrong, and happens to idly wonder whether they, themselves, are in fact the same person who participated in LessWrong under the username TheOtherDave back in January of 2014, but subsequently went through the process you describe. "Am I the same person as TheOtherDave?" D asks. "Is TheOtherDave having my experiences?" What ought D expect to differentially observe if the answer were "yes" vs. "no"? This is not a question about external observations, as there's no external observer to make any such observations. It's simply a question about observations. And as I said initially, it seems clear to me that no such differentially expected observations exist... not just no external observations, but no observations period. As you say, it's just a question about models -- specifically, what model of identity D uses. Similarly, whether I expect to be the same person experiencing what D experiences is a question about what model of identity I use. And if D and I disagree on the matter, neither of us is wrong, because it's not the sort of question we can be wrong about. We're "not even wrong," as the saying goes. We simply have different models of identity, and there's no actual territory for those models to refer to. There's no fact of the matter. Similarly, if I decide that you and I are really the same person, even though I know we don't share any memories or physical cells or etc., because I have a model of identity that doesn't depend on any of that stuff... well, I'm not even wrong about that.

0[anonymous]11y

When TheOtherDave walks into the destructive uploader, either he wakes up in a computer or he ceases to exist experiences no more. Not being able to experimentally determine what happened afterwards doesn't change that fact that one of those descriptions matches what you experience and the other does not.

0TheOtherDave11y

What do I experience in the first case that fails to match what I experience in the other? That is, if TheOtherDave walks into the destructive uploader and X wakes up in a computer, how does X answer the question "Am I TheOtherDave?" Again, I'm not talking about experimental determination. I'm talking about experience. You say that one description matches my experience and the other doesn't... awesome! What experiences should I expect X to have in each case? It sounds like your answer is that X will reliably have exactly the same experiences in each case, and so will every other experience-haver in the universe, but in one case they're wrong and in the other they're right. Which, OK, if that's your answer, I'll drop the subject there, because you're invoking an understanding of what it means to be wrong and right about which I am profoundly indifferent. Is that your answer?

0[anonymous]11y

This is so completely unrelated to what I am talking about. Completely out of left field. How the upload/clone answers or fails to answer the question "Am I TheOtherDave?" is irrelevant to the question at hand: what did TheOtherDave experience when he walked into the destructive uploader. I've rephrased this as many times as I know how, but apparently I'm not getting through. I give up; this is my last reply.

0TheOtherDave11y

OK.

0TheOtherDave11y

Of course not. But what does thinking you're Donald Trump have to do with it? The question at hand is not about who I think I am, but what properties I have.

0[anonymous]11y

No, the question at issue here is continuity of experience, and the subjective experience (or rather lack thereof) when it is terminated - death.

2TheOtherDave11y

Ah, OK. You confused me by bringing up trist thinking they were Donald Trump, which seemed unrelated. For my own part, I'm not sure why I should care about the nominal difference between two things with identical properties, regardless of how continuous their subjective experience is/has been, and regardless of whether one of them is me. But I acknowledge that some people do care about that. And not just for subjective experience... some people care about the difference between an original artwork and a perfectly identical copy of it, for example, because the continuity of the original's existence is important to them, even though they don't posit the artwork has subjective experiences. That's fine... people value what they value. For my own part, I don't value continuity in that sense very much at all.

0Leonhart11y

Taboo "think". If you rewire my neurons* to give me the false propositional belief that I am Donald Trump, then no. If you rewire my neurons to an exact copy of Donald Trump's, then yes. And, yes, they could, to the exact same degree that they would accept a miraculously-resuscitated Trump who was amnesiac about the previous day leading up to the boating accident, and also looked totally different now. But this is a looser requirement. There could be a whole bunch of threshold people who would be recognised by my family as a valid continuation of me, but who I could not have anticipated becoming. *and any other skull-stuff that bears on the problem

[-]RowanE11y20

I think the expansion and contraction model, as you've described it, would probably also result in my death. The being that includes the computer and myself would be a new being, of which I am now a component. When the meaty component dies, this is my death, even though there is now a being who perceives itself to be a continuation of me. This being is, in many ways, a continuation of me, just not in the way that I care about most.

I'm not completely sure of this, of course, but anywhere I'm not sure whether I'll die or not I prefer to lean heavily towards not dying.

[-]CAE_Jones11y20

What's the point of uploading if we have an AI with all the skills and knowledge of everyone not information-theoretically dead at the time of its creation?

I have no idea how to argue with the ideas about consciousness/identity/experience/whatever that make uploading seem like it could qualify as avoiding death. It occurs to me, though, that those same ideas sorta make uploading individuals pointless. If strong AI doesn't happen, why not just upload the most useful bits of people's brainstates and work out how to combine them into some collective that is n... (read more)

5Jonathan Paulson11y

Because I want to be alive. I don't just want humanity to have the benefit of my skills and knowledge.

0CAE_Jones11y

When I read this in the recent comments list, I at first thought it was a position against uploading. Then I read the other recent comments and realized it was probably a reply to me. I get the impression that no one has a functional definition of what continuity of identity means, yet destructive copies (uploads, teleports, etc) appear to be overwhelmingly considered as preserving it at least as much as sleep. I find this confusing, but the only argument that seemed to support it that I've found is Eliezer's "Identity is not in individual atoms", which is a bit disingenuous, in that uploads are almost certainly not going to be precise quantum state replicators. (I'd make a pole, here, but my last attempt went poorly and it doesn't appear to be standard markup, so I don't know where I'd test it.) What probability would you assign to each of these as continuing personal identity? 1. Sleep. 2. puberty 3. The typical human experience over 1-5 years. 4. Gradual replacement of biological brain matter with artificial substitutes. 5. Brain-state copying (uploads, teleportation) 6. Brain-state melding (Brain Omega = Brain A | Brain B | Brain n )

0Jonathan Paulson11y

1) 1.0 2) 1.0 3) 1.0 4) It depends on the artificial substitutes :) If they faithfully replicate brain function (whatever that means), 1.0 5) Again, if the process is faithful, 1.0 6) It really depends. For example, if you drop all my memories, 0.0. If you keep an electronic copy of my brain on the same network as several other brains, 1.0. in-between: in-between (Yes, I know 1.0 probabilities are silly. I don't have enough sig-figs of accuracy for the true value :)

3RowanE11y

I don't think most people who believe uploading qualifies as avoiding death would also agree that adding a fraction of a person's brainstate to an overmind would also qualify as avoiding death.

[-]Thomas11y10

The simplest way to understand all this, is to look others as your coincarnations.

All the paradoxes go away. What remains, is a memmetic hazard, though.

[-]Leonhart11y10

Copy my mind to a machine non-destructively, and I still identify with meat-me. You could let machine-me run for a day, or a week, or a year, and only then kill off meat-me. I don't like that option and would be confused by someone who did.

This is just bizarre. If the point is to preserve continuity, why on earth would you let the copy run independently and diverge? Of course it won't then represent a continuation of experience from the point at which meat-you was later killed.

The point of the destructive upload is precisely so that you-now can antici... (read more)

5Error11y

Except I don't anticipate continuing only as the upload; I anticipate being dead. Uploaded-me will remember incorrectly anticipating the same, but uploaded-me was not the one doing the anticipating. I am an instance of a class, not the class itself. Actually, tabooing "I", since it seems to be getting in the way: This instance of the class anticipates that this instance will be dead, and has a problem with that even if other instance(s) of the class remain.

1DanielLC11y

That's the same as "I". There is one instance. It forks. There are two instances. If you claim that one of them was the original instance, you are using "I". I'd say that past!you, upload!you, and meat!you are three distinct instances of the class you. Thinking you're going to die means that past!you does not believe that there is a future!you.

1Error11y

Well, yes. What I was trying to do was avert a confusion where "I" might refer to an instance (meat brain, silicon RAM copy #224) or might refer to a class (the abstract computation they're both running), by specifying the intended meaning. That is the point of tabooing, right? Thanks; this seems to be the source of disagreement. I see two instances, not three, the second forking at the moment of upload and running the same program with a new PID. I don't think we'll find common ground here, and I'm not sure I'm up to defending my position on the subject. I just found the consequences of that position interesting to explore.

1Leonhart11y

Fine, but we're still talking past each other, because I think there is no sense in which dead meat-you "was" the one doing the anticipating that is not also true of live upload-you. So the whole point of this, as I understood it, was that the universe doesn't support persistent instances in the way you want it to. You could follow e.g. Mitchell Porter (as far as I understood him) and claim that there's a particular quantum doohickey that does support real fundamental continuity of stuff. Do you? Or am I wildly misinterpreting you?

0Dentin11y

For the record, (this instance of this class) has no problems with the destruction of (other instances of this class or itself), so long as at least one instance remains and is viable, and a handful of similarity conditions are met. Seriously. We can talk about it on lw chat some time if you're bored.

0TheOtherDave11y

Wait, what? Are you regularly having the experience "dammit, I'm still the meat one" now?

0Leonhart11y

Well, no, because I don't remember recently non-destructively uploading myself. Am I missing your point?

1TheOtherDave11y

Perhaps I'm missing yours. Say P1 = my continued existence in a meat body, and P2 = my continued existence in an uploaded body. It seems clear to me that I prefer P1 to NOT P1... that's why I don't kill myself, for example. So why would I prefer P2 to (P2 AND P1)?

4Leonhart11y

Ah. But I'm not making an argument, just reporting current preferences. If P2 can happen, that changes my preference for P1 over NOT P1, except in the case where P1 can also extend indefinitely; due to e.g. advances in anti-aging science, or alicornication science. I strongly disvalue any me dying without being able to legitimately (by the lights of my model) anticipate then waking up as an upload. The best way to avoid this scenario is with a destructive upload. Obviously, my enthusiasm for this in any real situation involves a tradeoff between my confidence in the upload process, what I expect life as an upload to be like, and my remaining expected QUALYs. I can imagine creating multiple P2s via non-destructive uploads before that point, but there will always be one meat-me left over. What I want is that he have no further experiences after whatever turns out to be his last save point, in which time to have the possibly silly, but inevitable and emotionally compelling thought, "I've missed the boat." There's no reason that this should be compelling to you, but do you think it's actually inconsistent?

1Error11y

I found this enlightening, in that I'd never really understood the point of deliberate destructive uploading until now. A preference report in return: I would strongly prefer P1 over P2, mildly prefer P2 & P1 over just P1, and moderately prefer P2 over nothing (call nothing P0). I think of destructive-upload as death, but I think I value the algorithm I'm running somewhat, even in the absence of the hardware currently running it. Given the opportunity to do a non-destructive upload, I would certainly take it. Given the opportunity to do a destructive upload, I would....well, I might take it anyway. Not because it wouldn't be death, but because not taking it would eventually result in P0. I would prefer such an upload to take place as late in life as possible, assuming the possibility of early death by accident is ignored. (I am not certain which way I would go if it was not ignored)

0TheOtherDave11y

Fair enough. Sure, if you happen to have both the desire to not die and the independent desire to stop living in your meat body once you've been uploaded, then a destructive upload gives you more of what you want than a nondestructive one.

[-]ShardPhoenix11y10

I think we have to give up on uniqueness of identity in order to remain consistent in these kind of sci-fi scenarios.

edit: And I guess "identity" has to have a continuous value to - similar to the anthropic principle - being x% certain you are in a particular world is like being x% certain you are a particular person.

0[anonymous]11y

What do you mean by "uniqueness of identity"?

1DanielLC11y

The idea that, after a non-destructive upload, only one of the people can be you.

[-]Ander11y10

I think that your position on destructive uploads doesn't make sense, and you did a great job of showing why with your thought experiment.

The fact that you can transition yourself over time to the machine, and you still consider it 'you', and you cant actually tell at what specific line you crossed in order to become a 'machine', means that your original state (human brain) and final state (upload) are essentially the same.

[-]solipsist11y210

I don't like the structure of this argument. If I morph into a coffee table, I can't mark a specific line at which I become a piece of furniture. This doesn't imply that I'm essentially a coffee table. No hard boundary does not imply no transition.

0MrCogmor11y

Error isn't implying that the final state is different. Just that the destructive copy process is a form of death and the wired brain process isn't. I get where he is coming from, a copy is distinct from the original and can have different experiences. In the destructive copy scenario a person is killed and a person is born, In the wired brain scenario the person is not copied they merely change over time and nobody dies. My view is that if I die to make a upload (which is identical to me except for greater intelligence & other benefits) then I think the gain outweighs the loss.

[-]Richard_Kennaway11y00

Suppose that rather than copying my brain, I adjoined it to some external computer in a kind of reverse-Ebborian act; electrically connecting my synapses to a big block of computrons that I can consciously perform I/O to. Over the course of life and improved tech, that block expands until, as a percentage, most of my thought processes are going on in the machine-part of me. Eventually my meat brain dies -- but the silicon part of me lives on.

This is very similar to the premise of Greg Egan's short story, "Learning to be me".

[-]polarix11y00

[-]Lalartu11y00

Speaking of uploading procedures, I think the most brute-force, simple in concept and hard in implementation is described in
Transhuman by Yuri Nikitin. Just replace neurons one by one with nanorobots that have identical functionality, then as whole brain is transformed increase working speed.

[-]kilobug11y-10

But what's the difference between "non-destructive upload" and "making a copy of the upload" or "making a copy of your biological body" ?

The intuition behind "Copy my mind to a machine non-destructively, and I still identify with meat-me." is flawed and non-coherent IMHO. What if you can't even tell apart "meat you" and the other one, like the other one is put in a robotic body that looks, feels, ... exactly like the flesh body ? You fall asleep, you awake, there are two "you", one flesh the othe... (read more)

-2[anonymous]11y

You are misunderstanding the argument.

0kilobug11y

More exactly I don't really understand it, because it relies on presumptions/intuitions that I don't have. My point was mostly to try to get those made more explicit so I can better understand (and then accept or refute) the argument. Sorry if that wasn't clear enough.

[-]solipsist11y-20

Why do you have your position on destructive uploads? It could be that when you go to sleep, you die, and a new person who thinks they're you wakes up. The world is inhabited by day-old people who are deluded by their memories and believe they've lived decades-old lives. Everyone will cease to exist as a person the next time they go to sleep.

If you believe that, I can't prove you wrong. But it's not a productive worldview.

In a world where everyone is uploaded or Star Trek transported each day, you could believe that the world is inhabited by day-old people who will cease to exist on their next transport. I couldn't prove you wrong. But it wouldn't be a productive worldview.

8Error11y

Mostly by comparison to non-destructive uploads. Copy my mind to a machine non-destructively, and I still identify with meat-me. You could let machine-me run for a day, and only then kill off meat-me. I don't like that option and would be confused by someone who did. Destructive uploads feel like the limit of that case where the time interval approaches zero. As with the case outlined in the post, I don't see a crossed line where it stops being death and starts being transition. Now that I've written that, I wish I'd thought of it before you asked; the two are really mirror images. Approach destructive uploads from the copy-then-kill side, and it feels like death. Approach them from the expand-then-contract side, and it feels like continuous identity. Yet at the midpoint between them they turn into the same operation.

-3[anonymous]11y

Who cares? Don't appeal to social norms. For the person about to step into teleporter, there's a true difference, even if it not observable from the outside.

3TheOtherDave11y

Sure. For every person about to go to bed, there's also a true difference between the way they are as they go to bed, and the way they are as they wake up. That there is a true difference doesn't really matter much; a more useful question is whether we value the difference... which is a psychological and social question. When you insist on ignoring social norms, the effect is simply to insist that a particular set of social norms (the ones having to do with continuous existence in a single body being important) be given unexamined primacy. Which is fine for you, since you embrace that set. For those of us who reject it, it just seems like a goofy thing to insist on.

1solipsist11y

I can't justify believing that I will continue to exist 5 seconds from now -- that I am more than this thought, right now -- without appealing to social norms and practicality.

Moderation Log