Coherency is one of those things about which we should be optimistic rather than pessimistic. What is a machine intelligence if it is not a machine capable of coherent reasoning?
An AGI will be capable of coherent reasoning in situations up to a certain complexity ceiling. However, some real-world situations will exceed that complexity ceiling. Since the point seems clear to me, and Eliezer and Pei and Jef (whose all have considerable knowledge on the topic) agree with me, and since you have not posed any cogent counterargument, I remain confident that my earlier statement is correct: an AGI with modest computational resources cannot be probabilistically coherent/consistent except in regard to a relatively small subset of the statements with which it must deal. But, frankly, I am tired of repetitively arguing this point with you, and will stop now... ;-) -- Ben ----- 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/?list_id=303
