> Of course you have to specify exactly what an engineered set of dynamics > do, including the dynamics that make up what is, from our perspective, a > mind. Who ever said otherwise? Well, me. But I now fully > acknowledge my > ancient position to have been incredibly, suicidally stupid. ... > Eliezer S. Yudkowsky http://singinst.org/ > Research Fellow, Singularity Institute for Artificial Intelligence
Hmmm.... Due to vagaries of natural langauge, I'm not entirely sure if I agree with your new or your ancient position. It seems to me that, in a self-organizing computational system, -- "specifying exactly what a set of dynamics do" (as I interpret that phrase) is not the same as -- "being able to predict exactly what consequences a set of dynamics will lead to in various environmental circumstances" The former is feasible, the latter is generally not. In fact I suspect that, for any system complex enough to deserve the name "mind," the latter will be *profoundly* infeasible. Some software programs are deterministic enough that one can predict their reactions to various environmental interactions and their evolution over time; minds are not that kind. -- Ben ------- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]