My own view is that our state of knowledge about AGI is far too weak for us to make detailed plans about how to **ensure** AGI safety, at this point
What we can do is conduct experiments designed to gather data about AGI goal systems and AGI dynamics, which can lead us to more robust AGI theories, which can lead us to detailed plans about how to ensure AGI safety (or, pessimistically, detailed knowledge as to why this is not possible) However, it must of course be our intuition that guides these experiments. My intuition tells me that a system with probabilistic-logic-based goal-achievement at its core is much more likely to ultimately lead to a safe AI than a system with neural net dynamics at its core. But vague statements like the one in the previous sentence are of limited use; their main use is in leading to more precise formulations and experiments... -- Ben G On Sun, May 25, 2008 at 6:26 AM, Panu Horsmalahti <[EMAIL PROTECTED]> wrote: > What is your approach on ensuring AGI safety/Friendliness on this project? > ________________________________ > agi | Archives | Modify Your Subscription -- Ben Goertzel, PhD CEO, Novamente LLC and Biomind LLC Director of Research, SIAI [EMAIL PROTECTED] "If men cease to believe that they will one day become gods then they will surely become worms." -- Henry Miller ------------------------------------------- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244&id_secret=103754539-40ed26 Powered by Listbox: http://www.listbox.com
