From: Michael Wilson (firstname.lastname@example.org)
Date: Mon Oct 17 2005 - 15:15:22 MDT
Chris Capel wrote:
> I'm a bit puzzled why you quoted me, but no matter.
Sorry Chris, I was just trying to establish some continuity so that it
was obvious what my post applied to. I'm fairly sure you have a decent
understanding of this, I just wanted to remind everyone of the depth
of the issue, to stave off any uselessly oversimplified 'embodiment is
necessary - no it isn't - yes it is' arguments.
> But for the record, I was referring in the quoted text to the
>> assumption that "strictly humanoid intelligence would not likely be
>> Friendly ...[etc.]"
> which seems to be an issue apart from embodiment, and more amenable to
> limited generalization.
Unfortunately I've found that those kind of generalisations often
assume a consistency to the opposing position that doesn't in fact
exist. It is a seperate issue and in theory a simpler question, but
we're already seen 'can intelligences with humanoid embodiment be
Friendly?' get confused with 'can intelligences with human like
cognitive architecture be Friendly?'. As you can probably guess, I'd
say that physical form and available I/O channels is a pretty
superficial issue for FAI purposes, whereas goal system architecture
is absolutely critical.
* Michael Wilson
How much free photo storage do you get? Store your holiday
snaps for FREE with Yahoo! Photos http://uk.photos.yahoo.com
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:52 MDT