Matt,
“Internet” is comprised of data (like encyclopedias) and algorithms for processing it (google search, wolframalpha). Data itself is passive and does not have any intelligence, it is the search algorithms which are likely to become self-improving and intelligent. Most likely the first version of such an algorithm will be developed and tested in a lab somewhere in Google, at that point utilization of safety measures would be a good idea. Sample chapter available on the book’s website talks about specific safety measures I propose. It would be great to get your feedback on it. In any case, I really appreciate your interest in the project and would love any help in spreading the word via social networks. Thank you in advance for your support. Best, Roman On Thu, May 30, 2013 at 10:06 PM, Matt Mahoney <[email protected]>wrote: > On Thu, May 30, 2013 at 8:11 PM, Roman Yampolskiy <[email protected]> > wrote: > > 9) Artificial Intelligence Confinement Problem (and Solution). > > Given that the internet is the most intelligent system on the planet > (measured either in knowledge x computing power or in dollars per > hour), and already self-improving exponentially, how do you plan to > confine it? > > -- > -- Matt Mahoney, [email protected] > > > ------------------------------------------- > AGI > Archives: https://www.listbox.com/member/archive/303/=now > RSS Feed: https://www.listbox.com/member/archive/rss/303/23680555-4d4e3f67 > Modify Your Subscription: > https://www.listbox.com/member/?&; > Powered by Listbox: http://www.listbox.com > ------------------------------------------- AGI Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-f452e424 Modify Your Subscription: https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-58d57657 Powered by Listbox: http://www.listbox.com
