On Tue, Dec 20, 2011 at 10:50:36AM -0800, Steve Dekorte wrote:

> Could you describe how more compute power helps you write the app I described 
> faster? 

It is a really narrow problem space I'm not familiar with. I presume
this isn't about scheduling, but about UI and usability?

Anything people-centric will become the bottleneck, so apart from
automatic program generation you can only use systems observe users
in action (machine vision) and find something that maximizes
some observable metric. Of course extracting metrics from behaving
people is a hard problem on its own right, but it if solved it
*will* make things happen faster, and it will have considerable
applicability elsewhere.

But this is really a pathological case. Most problems are computationally
bound, especially if you consider problem specification and implementation.
People just want solutions, and an interactive way to refine the problem until
a good enough solution emerges would work for them.

I would also like machines to become persons. It's not everything always
about us primates.

_______________________________________________
fonc mailing list
[email protected]
http://vpri.org/mailman/listinfo/fonc

Reply via email to