> -----Original Message----- > From: Matt Mahoney [mailto:[email protected]] > > How would a p-conscious AGI behave differently than a p-zombie AGI? > What test are you using to distinguish them? >
A p-conscious agent could predict other p-conscious agents thoughts and actions more accurately. This is an extension of the normal channels of agents distributed communication/computation. How would a swarm of p-zombies behave in reality? How synergistic would a team of p-zombies be? What would the mathematical model of teamwork be for non-p-conscious agents verses p-conscious agents? > > Experimentally we have a lot of p-zombie AI but not a single instance of p- > conscious AI (or at least AI that we would attribute p-consciousness to > because it behaves like a human). So it seems like a zombie would be easier > to build, not harder. > An approximation might be easier to build. A simple chat-bot is easy to build it appears conscious. How close though are the existing approximations that you refer. Even if Turing test is passed how close can you feasibly get? Functional approaches like GWT oriented implementations are the way to go as they are operational. There are other operational models too that don't seek to merely store, catalog and imitate behavioral information. > My approach is described in http://mattmahoney.net/agi2.html We need an > economic model that rewards collection and publication of human > knowledge on a global scale. There is no feasible way to do this without > decades of global effort. The work and the ownership needs to be > distributed. The approach is not to build human minds, because humans > make lousy workers. The approach is to build billions of specialists and a > network that routes messages to the right experts competing for attention > and reputation in a hostile environment. I wrote this proposal in 2008, before > social networking became popular, and we are already seeing this type of > interaction between websites, except using more complex and ad-hoc > protocols. > Distributed systems related to what you describe are happening self-oganizingly. People may not realize it but when they use social networking systems they are actually performing work for the company in exchange for a small benefit. Essentially this could be included in your description of a global effort it's just happening differently on a volunteer oriented financial model. Your distributed design is interesting but really just a general overview that dips into specifics. The protocol description is kind of brief. Similar models like you describe though still have potential IMO for something new to happen but the protocol and computational structure need to be more elaborate... John ------------------------------------------- AGI Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-f452e424 Modify Your Subscription: https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-58d57657 Powered by Listbox: http://www.listbox.com
