Ben: as discussed already ad nauseum, I do not think that robust perception/action is necessarily the best place to start in making an AGI. However, our current work on embodying Novamente and OpenCog does involve 3D virtual worlds ... and, of course, my planned work with Xiamen University using OpenCog to help control a Nao robot also involves our 3D visual world...
In terms of P.R. - communicating what you're doing - about through which channels your AGI's or other AGI's will try to learn about which dimensions of which worlds, this is all a little confusing. And I suspect everybody, including you, is a little confused here - especially about the different limitations/advantages of the different approaches. Hey, you seem to be in a highly experimental/exploratory stage, which is fine. But the "ad nauseum" comment seems to be aimed at stifling rather than encouraging further analysis, and covering over the confusion.. There's actually an awful lot to discuss here - it hasn't all been covered. ------------------------------------------- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244&id_secret=111637683-c8fa51 Powered by Listbox: http://www.listbox.com
