On Sun, Sep 21, 2014 at 5:31 AM, John Rose via AGI <[email protected]> wrote:
>> You don't need to design consciousness into AGI. You just need to design
>> human behavior. When people see that it behaves like a human, they will
>> just assume that it is conscious. What other test could they do?
>>
>
> Agreed. You can make a p-zombie AGI. But would it understand really who we 
> are if it doesn't have phenomenal consciousness? And might that not be 
> dangerous to us?

Are you saying that a p-zombie AGI would behave differently than a
conscious AGI? Now we're getting somewhere. Exactly how would you test
if an AGI really "understands" us?


-- 
-- Matt Mahoney, [email protected]


-------------------------------------------
AGI
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-f452e424
Modify Your Subscription: 
https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-58d57657
Powered by Listbox: http://www.listbox.com

Reply via email to