On 24/12/2012 21:07, Matt Mahoney wrote:
On Mon, Dec 24, 2012 at 5:10 PM, Ben Goertzel <[email protected]> wrote:
"Why is evaluating partial progress toward human-level AGI so hard?"
http://multiverseaccordingtoben.blogspot.com/2011/06/why-is-evaluating-partial-progress.html
I don't buy it. [...]
Me neither. Maybe we can't score some things - but we can measure ability at
inductive inference - which is what the brain spends maybe 80% of its time
doing.
We have a selection of reasonable tests, that is no longer the problem we face.
IMO, our main problem is poor test performance - not that we can't test.
--
__________
|im |yler http://timtyler.org/ [email protected] Remove lock to reply.
-------------------------------------------
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
