David Clark wrote:
> I agree that an AGI fundamentally will be created by a combination of data (databases) and procedures (programs) but how large and by who the programs will be created has yet to be determined. Why do you assume that all AGI programs will be created by humans? Why couldn't an initial set of programs be created by AGI researchers that will when complete start creating programs on it's own? Why would you have to start out with the minimal data and set of algorithms that humans do?
I'm not sure how many lines of code will G0 require, but a minimalist implementation may take ~30K lines only (just a wild guess) -- ignoring vision and various forms of learning.
Since G0 can reason about programming when it has acquired the appropriate knowledge, it can be self-modifying. Therefore it satisfies the criteria for being a "seed AI".
At least it seems to me that the G0 route is a very economic way to build a seed AI. The only alternative I can think of is the evolutionary programming approach, which may be even messier, harder to predict, and harder to design.
As for "friendliness" it is the problem of modeling human values and robust "safe" planning (ie planning with safety considerations).
YKY
This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/[EMAIL PROTECTED]
