Re: [sl4] Re: Uploads coming first would be good, right?

From: Charles Hixson (charleshixsn@earthlink.net)
Date: Wed Feb 25 2009 - 14:32:39 MST


Johnicholas Hines wrote:
> On Tue, Feb 24, 2009 at 1:47 PM, Charles Hixson
> <charleshixsn@earthlink.net> wrote:
>
>>> On Mon, 23 Feb 2009 "Johnicholas Hines"
>>> <johnicholas.hines@gmail.com> said:
>>>
>>>> My claim is I think we should consider the expert
>>>> opinion that "there's no weather underneath" as relevant
>>>>
>> This isn't clear. If it models how clouds change accurately enough I would
>> assert that temperature is implicitly encoded into the model. And if it's
>> accurate *enough*, then it might be a good local model of weather. And if
>> it's accurate ENOUGH, then it might be a reasonable datafeed for your World
>> Weather Watch.
>>
>> Think of neural nets. They don't have separate variables for separate
>> measures, and they don't have intelligible internal workings. But if you
>> train one well enough, it produces reasonable results without having the
>> separate variables that we have decided are good descriptors. Like
>> temperature.
>>
>> Personally, I want to be able to understand my models, but I don't think of
>> intelligibility as an essential property of a model.
>>
>
> Yes, an expert could extract an implicitly encoded temperature from
> only images of clouds. Forrest Mims seems capable:
> http://sunandsky.org/
>
> Yes, it is possible to build faithful models that have confusingly
> different internal workings. (Of course, there is some explanation for
> why the model is faithful. If we knew that explanation, then they
> would be intelligible internal workings.)
>
> Lest we get confused, let me recap. We're talking about criteria for
> how one might determine that an emulation is a faithful emulation.
>
> Dr. Mahoney pointed out that it might be possible to build a computer
> program from only the public record that emulates a person
> sufficiently well to convince their friends and family. My worry was
> the claim that "good enough to fool your friends and family" was the
> only, or primary, criterion for fidelity.
>
> The weather metaphor goes like this:
>
> wet weather : emulated weather :: wetware humans : emulated humans
>
> The point of making the weather metaphor was to claim that we wouldn't
> use the "friends and family criterion" as the only, or primary,
> criterion for whether to trust a weather simulation. We would also use
> experts. If we're interested in simulating never-before-seen
> situations such as extreme global warming, then the experts (at least
> in the near term) need to see the construction in order to argue that
> the results of the simulation are correct by construction.
>
> Johnicholas
>
> P.S.
>
> Though it might be possible to build a faithful emulation of a human
> from only the public record, I don't think it's likely to happen soon.
> Let me try to convince you of that, using two points:
> 1. A faithful emulation should act correctly even in quite extreme,
> never-before-encountered situations. Your friends and family haven't
> seen you in these situations, and lots of different behaviors would be
> plausible.
> 2. A faithful emulation should enact firm plans and intentions that
> you made immediately before uploading. Guessing those plans and
> intentions based on the public record might be possible, but I think
> it would be quite difficult.
>
>
The problem is, basically, that the public record isn't complete
enough. E.g., it's quite possible that model based on clouds appearance
would need to model the internal appearance of the clouds to allow
accurate projections. And it's quite probable that any such model would
be a lot more computation intensive than one based on a higher level
understanding, and explicitly including such things as temperature.

The problem with your analogy is: What is the equivalent of looking at
the model and deciding that one needs to turn up the thermostat this
evening? I.e., if it's a good weather model, then there is an
isomorphism between levels.

I suppose the question is, basically, are two things which are
canonically isomorphic not actually the same thing? If they are, then
the upload IS the person. Though in that case it becomes a question
as to exactly how much of a person needs to be captured. E.g., is a
structure isomorphic to the retina required, or merely something that
will appropriately stimulate a simulation of the optic nerves? But how
much can you peel off in the name of efficiency and still have the same
valid person?

I tend to believe that canonically isomorphic entities are merely
different views of the same underlying entity. But canonically
isomorphic is a very high barrier, and one that's probably unreachable
in practice. So the question becomes "How great a deviation is
allowable without considering the entity to be a new person?"



This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:01:04 MDT