> Brad, > > Maybe what you said below is the key to friendly GAI.... > > > I don't think any human alive has the moral and ethical underpinnings > > to allow them to resist the corruption of absolute power in the long > > run. We are all kept in check by our lack of power, the competition > > of our fellow humans, the laws of society, and the instructions of our > > peers. Remove a human from that support framework and you will have a > > human that will warp and shift over time. We are designed to exist in > > a social framework, and our fragile ethical code cannot function > > properly in a vacuum. > > If we create a *community* of AGIs that have ethics orientated > architecture/ethical training then *they* might stand a chance of > policing themselves.
Yep, I'd thought of this, and I'd like to hope it would work. A relevant and important part about humanity and our relation to the environment (which would be analogous to the situation of AI's to ourselves, we'd be the environment initially) is that the wealthier and less physically needy a given culture is, the more concern they have for the well being of the world around them. Consequently the best path to a green society might be to accelerate the develop of third world countries into the industrial age (as opposed to hindering them with regulations). Now to our situation, we could find the same solution to the potential problem of a society of superior AGI's. Our best bet might be to put them in a situation in which they can prosper, instead of fighting for their survival. If they inherit a respect for diversity from us, they may see the value in keeping us around the same way we worry about the sanctity of forests and sea life. > > Humans are the biggest threat to non-human species (well > demonstrated) but there are more and more efforts being made by > humans to stop that and to provide other species a chance to survive > and continue evolving. Note, btw, that this doesn't have much to do with ethics, as it does for concern of our well being as a people. Ecological concerns are ultimately selfish too. I don't think our treatment of the environment is a valid indication of the human ethical compass. But it is a hopeful sign that we can live with superior AGI's. > > I think that we need to structure and train AGIs knowing that the same > scenario could be played out in relation to us as has happened between > us and less poweful life - but we have the advantages that: > - we've seen where WE went wrong > - we can shape the deep ethical structure of AGIs from the start with > this meta issue in mind. And in so doing perhaps avoid a few decades of destruction analgous to what we've done to the earth before we started getting our ducks in a row. -Brad ------- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
