Re: How would a computer know if it were conscious?

From: Brent Meeker <>
Date: Mon, 04 Jun 2007 09:28:23 -0700 wrote:
> On Jun 3, 11:11 pm, "Stathis Papaioannou" <> wrote:
>> Determining the motivational states of others does not necessarily involve
>> feelings or empathy. It has been historically very easy to assume that other
>> species or certain members of our own species either lack feelings or, if
>> they have them, it doesn't matter. Moreover, this hasn't prevented people
>> from determining the motivations of inferior beings in order to exploit
>> them. So although having feelings may be necessary for ethical behaviour, it
>> is not sufficient.
> You are ignoring the distinction I made between three different kinds
> of general intelligence. I gave there different definitions remember:
> *Pattern Recognition Intelligence
> *Symbolic Reasoning Intelligence
> *Reflective Intelligence
> A mere 'determination of the motivational states of self and others'
> does not by itself constitute *reflective intelligence* according my
> definitions. Not only must the motivational states of self/others by
> determined and represented (this process by itself does not require
> ethics or sentience), these representations must be *reflected* upon.
> Only this final step, I'm saying, leads to ethical behaviour. Once
> you have a system performing *full* reflection correctly, you get
> feelings. And, I maintain, there is no real difference between
> feeling and motivation.

But what feeling? You assume that the AI has the same values to reflect on as a normal human. Even normal humans have feelings of competitivness, they value domination and security. An AI, however reflective, might conclude the world would be better without humans, leaving more resources for copies of itself. Of course you could define this away as "not bad", but then we're left to wonder what counts as "bad behavoir" and what doesn't.

Brent Meeker

You received this message because you are subscribed to the Google Groups "Everything List" group.
To post to this group, send email to
To unsubscribe from this group, send email to
For more options, visit this group at
Received on Mon Jun 04 2007 - 12:28:27 PDT

This archive was generated by hypermail 2.3.0 : Fri Feb 16 2018 - 13:20:14 PST