> > We can prove that good solutions must have high algorithmic complexity.
Could you give a sketch for such a proof? Why does the complexity have to initially reside in the algorithm, rather than in the environment? Why can't a simple system build algorithms dynamically by incorporating information extracted from the environment? Is this not the same principle that allowed evolution to create us, and us to create science and technology? On Tue, Feb 17, 2015 at 3:06 PM, Matt Mahoney via AGI <[email protected]> wrote: > On Tue, Feb 17, 2015 at 9:25 AM, martin biehl via AGI <[email protected]> > wrote: > > > > What is wrong with the Legg and Hutter definition of intelligence? I > think that is it. > > For proving theorems, there is nothing wrong with it. For example, we > can prove that a general solution is not computable. We can prove that > good solutions must have high algorithmic complexity. It puts to rest > the "neat" vs. "scruffy" debate. AGI is not like physics. It's long, > hard, slow, expensive work, not an equation. > > For practical purposes, "intelligence" is not really the problem we > want to solve. The problem we want to solve is automating human labor. > It requires solving hard problems like vision, natural language, > robotics, art, and modeling human behavior. We want machines to > understand what we want and do it, not to outsmart us. > > -- > -- Matt Mahoney, [email protected] > > > ------------------------------------------- > AGI > Archives: https://www.listbox.com/member/archive/303/=now > RSS Feed: https://www.listbox.com/member/archive/rss/303/23050605-2da819ff > 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
