So, it looks like to really create any kind of system like this, a black-box seperate programming ability in some sort must be created, wherin we can create the program to 'hard-wire' in the reward system, seperate from the main AI unit, where they cannot in any way change it to reward itself. The
Although I understand, in vague terms, what ideaRichard is
attempting to express, I don't seewhy having"massive numbers of weak
constraints" or "large numbers of connections from [the]motivational
system to [the]thinking system." gives any more reason to believe it is
reliably Friendly
I disagree that humans really have a "stable motivational system" or would have to have a much more strict interpretation of that phrase. Overall humans as a society have in general a stable system (discounting war and etc) But as individuals, too many humans are unstable in many small if not
This is why I finished my essay with a request for comments based on an
understanding of what I wrote.
This is not a comment on my proposal, only a series of unsupported
assertions that don't seem to hang together into any kind of argument.
Richard Loosemore.
Matt Mahoney wrote:
My
- Original Message From: James Ratcliff [EMAIL PROTECTED]To: agi@v2.listbox.comSent: Saturday, October 28, 2006 10:23:58 AMSubject: Re: [agi] Motivational Systems that are stableI disagree that humans really have a "stable motivational system" or would have to have a much more strict
PROTECTED]
To: agi@v2.listbox.comSent: Saturday, October 28, 2006 10:23:58 AMSubject: Re: [agi] Motivational Systems that are stable
I disagree that humans really have a stable motivational system or would have to have a much more strict interpretation of that phrase. Overall humans as a society have
Hank Conn wrote:
Although I understand, in vague terms, what idea Richard is attempting
to express, I don't see why having massive numbers of weak constraints
or large numbers of connections from [the] motivational system to
[the] thinking system. gives any more reason to believe it is
Richard, The problem with the entire presentation is that it is just too hopeful, there is NO guarentee whatsoever that the AI will respond in a nice fashion, through any given set of interactions.First, you say a rather large amount (how many needed?) of motivations all competing at once for the
I'm sure you guys have heard this before but... If AI will inevitably be created, is it not also inevitable that we will "enslave" the AI to do our bidding?And if both of these events are inevitable it seems that we must accept that the Robot Rebellion and enslavement of humanity is ALSO
My comment on Richard Loosemore's proposal: we should not be confident in our ability to produce a stable motivational system. We observe that motivational systems are highly stable in animals (including humans). This is only because if an animal can manipulate its motivations in any way, then it
Richard,
As I see it, in this long message you have given a conceptual sketch
of an AI design including a motivational subsystem and a cognitive
subsystem, connected via a complex network of continually adapting
connections. You've discussed the way such a system can potentially
build up a
Ben Goertzel wrote:
Loosemore wrote:
The motivational system of some types of AI (the types you would
classify as tainted by complexity) can be made so reliable that the
likelihood of them becoming unfriendly would be similar to the
likelihood of the molecules of an Ideal Gas suddenly
12 matches
Mail list logo