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

From: <>
Date: Sun, 03 Jun 2007 01:36:39 -0700

Consciousness is a cognitive system capable of reflecting on other
cognitive systems, by enabling switching and integration between
differing representations of knowledge in different domains. It's a
higher-level summary of knowledge in which there is a degree of coarse
graining sufficient to lose precise information about the under-lying
computations. Current experience is integrated with past knowledge in
order to provide higher-level summaries of the meaning of a concept.
Any cognitive system capable of reflection in this sense is
conscious. In essence, conscious is what *mediates* between different
representations of knowledge... as mentioned above... the ability to
switch between and integrate different representational systems.

There are three general types of consciousness arising from the fact
that there are three different classes of cognitive systems which
could be potentially reflected upon. The first are systems which
perceive physical concepts. When this perception is reflected upon,
we experience sensations. The second are systems which perceive
teleological concepts... closely related to our motivational systems.
When this is reflected upon, we experience emotions (or more
accurately feelings). The third type of consciousness is very weak in
humans... it's the ability to reflect upon systems which perceive
logical/mathematical things. Reflection upon these systems is
consciously experienced as an 'ontology-scape' (in a sense, conscious
awareness of the theory of everything). But as mentioned, this last
type of consciousness is very weak in humans, since our ability to
reflect upon our own cognitive systems is quite small and not done by
the brain directly (when engaged in logical reasoning, we humans are
not generally reflecting on our thoughts directly, but via indirect
means such as verbal or visual representations of these thoughts).

The third type of conscious mentioned above is synonymous with
'reflective intelligence'. That is, any system successfully engaged
in reflective decision theory would automatically be conscious.
Incidentally, such a system would also be 'friendly' (ethical)
automatically. The ability to reason effectively about ones own
cognitive processes would certainly enable the ability to elaborate
precise definitions of consciousness and determine that the system was
indeed conforming to the aforementioned definitions.

 Much of the confusion surrounding these issues stems from the fact
there's not one definition of 'general intelligence', but THREE.
There's the ability to detect patterns (which does not require
sentience), there's the ability to engage in symbolic reasoning (which
also does not require sentience), finally there's the ability to
engage in reflective reasoning (reasoning about reasoning). And it's
this third definition intelligence which DOES by necessity entail
consciousness. It also, by necessity entails ethical behaviour.

Now there those who point to powerful systems such as 'Corporations'
and 'Evolution' to try to argue that you can have intelligence without
consciousness. But these arguments are not convincing. It's true
that, for instance 'Evolution' is an intelligence system in ONE sense,
but it's certainly NOT a *reflective intelligence*. Nor, is , for
instance a 'Corporation'. A 'corporation' has SOME of the sub-systems
of person-hood, but not all of them. The existence of non-sentient
cognitive systems which display *some* of the features of
intelligence is a LONG way from establishing that you can have
*reflective intelligence* without consciousness. As has been pointed
out, RPOPS such as for instance 'Evolution' are NOT capable of
reflective intelligence and therefore cannot be taken as a disproof of
the claim that reflective intelligence must by necessity automatically
be friendly and sentient.

The reason I elaborate this carefully is because you will, on certain
mailing lists, run into a number of artificial intelligence crack-pots
claiming that (1) You can have reflective intelligence without
consciousness and (2) AI's with reflective intelligence don't have to
be ethical and might destroy the world. Ignore these crack-pot claims
when you see them.

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 Sun Jun 03 2007 - 04:37:02 PDT

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