Re: Domain Protection

From: Sebastian Hagen (
Date: Mon May 09 2005 - 14:11:41 MDT

Russell Wallace wrote:
> *shrug* If I were dictator of Earth, I wouldn't make biological age
> the sole metric. I'm not, and the fact is that biological age has been
> made the critical metric for most things, including when you're
> allowed leave your parents. Don't blame me, wasn't my decision.
This design for Friendliness content is based on your decisions,
however. And in a lot of similar cases (the basic design, but also some
parameters; see your responses to my example questions) you are
obviously willing to assume the role of 'dictator of Earth' (Eliezer
called it 'taking over the world' in the CV document on the sl4-wiki) -
that is, you are specifying basic rules that, if implemented by a RPOP,
could not later be overridden under any circumstances.
Is the suggestion to decide whether individual humans are capable of
making this choice based on their age an attempt to make your model more
acceptable to individuals used to current society?

> That's something that needs to be decided; I offered merely a few suggestions.
Naturally; the question is who gets to decide it.

>>How are the available
>>ressources divided between them?
> My suggestion would be: find out at the start who wants to live in
> which domain, then whatever percentage of humanity picked a particular
> domain, it gets allocated that percentage of the available resources.
> (Should be plenty to go around, we're looking at galaxies per person
> (plus descendents).)
So all people insisting that they want a domain exclusively for
themselves (and any other entities they create) would get one?

>>How is interdomain communication
> Some would allow it, some wouldn't. (The Amish domain isn't going to
> want TV broadcasts from the Transcend, for example.)
Are these limits always fixed at domain creation, are they always
subject to later revision, is their later modifiability determined at
domain creation, or use it completely different rules?

>>Do 'sentient beings' only get to choose their domain once,
>>are they free to move between them at any time, or are parameters of the
>>individual domains responsible for deciding who is allowed to enter or
> The latter. I'd advocate giving every domain an exit that in principle
> anyone is allowed to use at any time, but in practice there are going
> to be issues like:
> - In the distant future, the domain you want to emigrate to may not
> have the resources left to take more immigrants.
> - If you're from the Transcend, for example, you're not going to be
> allowed into the Amish domain anyway.
Does this apply to all sentiences that have ever had any kind of contact
with a transhuman intelligence, even if they themselves are plain
'human' in capabilities and appearance? There are a lot of possibilities
for memetic 'corruption', as perceived by the Amish, here. If the Sysop
explains this to them, it is quite possible that they will end up
blocking all incoming data (including visitors) from the vast majority
of other domains.

> - Someone in a domain where lots of computing power is available to
> individuals could simulate a bunch of sentient beings and not allow
> them access to the exit.
That's a valid concern. There's also the possibility that physically
existing individuals (or individuals existing on the lowest level
available in the domain) could be denied the possibility to use the exit
by other entities existing inside it; how exactly this would be possible
depends on the implementation. If the exit is linked to spatial
coordinates, one could prevent access to them. If it required a specific
information one could eliminate the knowledge - etc.

>>If you allow unupgraded humans to make final decisions about these
> If I allow...? Supposing I wanted to prevent them, how do you propose
> I go about it, and who or what should make the decisions instead?
Eliezer's Collective Volition is an example for a Friendliness content
model that defers this kind of decision to an instance that doesn't
consist of plain humans. I don't know if it's actually workable in
practice; though if it isn't it should fail safely. Of course this only
means that it won't destroy the world directly - the setback dealt to
the project by pursuing an incorrect Friendliness content model may
still cause sufficient delays to allow a parallel development to destroy it.

> Catastrophic? There's no guaranteed way to avoid that, but I think
> domain protection offers the best hope that it will be restricted to
> individual domains rather than wiping out _all_ sentient life.
What about the possibility of domains that use a significant part of the
available resources developing into "hell worlds" with a significant
negative utility under most common value systems?
It is possible that those domains would drag the total utility
(according to the mentioned value systems) of the entire system below zero.

>>Do you have a better method of determining these parameters?
> The rules for individual domains? Get a bunch of intelligent,
> responsible humans who are representative of humanity's various
> cultures and acceptable to the political process to draw them up. Use
Making that selection would be quite difficult by itself.

> Friendly AI for error checking (i.e. have it try to point out where
> the humans' decisions would have unintended consequences, though the
> final decision has to be made by humans).
The conventional assumption would be to assume that even a RPOP couldn't
predict all of the possible consequences in detail; after all you
probably don't want to spend more resources (units of computation) for
initial simulations than for the actual implementation.

Sebastian Hagen

This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:51 MDT