On Sat, Aug 10, 2019 at 11:14 AM Ben Goertzel <[email protected]> wrote: > > The point is, Matt, you can't copy my quantum predictor without me > knowing you were copying it. Basic principle of quantum > cryptography. > > This is irrelevant to AGI though, just a sorta fun thought experiment...
Actually it is relevant. For every learner, there is a sequence with about the same complexity that it can't learn. It doesn't depend on my ability to make a copy of your program or on whether you know that I did. The sequence still exists. The paper goes beyond my proof. Powerful predictors exist, but they are necessarily highly complex. https://arxiv.org/abs/cs/0606070 -- -- Matt Mahoney, [email protected] ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T1ff21f8b11c8c9ae-M1dfe2f79d166eff464f37fe5 Delivery options: https://agi.topicbox.com/groups/agi/subscription
