On 1/11/03 9:39 PM, "Ben Goertzel" <[EMAIL PROTECTED]> wrote:
> But you can't escape the halting problem on the lower level. > > Using randomness you can escape the halting problem, in a sense. But, you > can't get true randomness in your virtual machine, only simulated > randomness. So you are not really escaping the halting problem, you're only > simulating escaping the halting problem, in a way that is indistinguishable > from escaping the halting problem based on observations with a certain > degree of coarseness... There isn't any randomness to the behavior; I could work out how it would terminate if I wanted to. Hence why standard computational theory applies. The truth is that there is no such thing as an "iteration" or loop in a conventional computer science sense on our machinery. All quasi-iterative behaviors are inherently bounded. The absolute worst case scenario is that I run out of working/short-term memory (e.g. if you ran a clever algorithm designed not to halt on our machinery), which will halt the computation essentially by exception leaving you with the intermediate results. This actually seems fairly analogous to how humans do computation anyway. Obviously this is something of an oversimplification; I think I see your point. There is still a halting problem, just not a practical halting problem for most intents and purposes. Or at least it has been pushed to a level of abstraction where we don't really worry about it too much. No practical result will emerge from infinite computation, and our machinery doesn't like to do infinite computation anyway (but will happily make approximations). On the other hand, I have personally demonstrated that conventional computer architectures will quite happily do infinite computation, much to my embarrassment. ;-) Cheers, -James Rogers [EMAIL PROTECTED] ------- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
