> On 18 Apr 2019, at 03:29, Russell Standish <[email protected]> wrote: > > On Wed, Apr 17, 2019 at 06:22:35PM -0700, 'Brent Meeker' via Everything List > wrote: >> >> But how complete must the self-model be. > > That is the 64 million dollar question.
To have consciousness, I put the bar on universality, to simplify. Technically the notion of “subcreativity”, or the equivalent notion of self-speedability should be enough. To have self-consciousness, it needs to be Gödel-Löbian, or a reflexive K4 reasoner, to use Smullyan terminology. > >> As Bruno has pointed out, it can't >> be complete. Current Mars Rovers have some "house keeping"self-knowledge, >> like battery charge, temperature, power draw, next task, location, time,... > > I don't think that's enough. I think it must have the ability to > recognise other (perhaps similar) robots/machines as being like > itself. Again, that is equivalent with being “rich enough” or Löbian, but hat is needed to have self-consciousness, to distinguish []p (used to define the belief of another machine) and []p & p, needed to “know itself” and assess the difference. (Brute) consciousness is a simple form of knowledge. Self-consciousness is more demanding, it needs the transitive formula ([]p -> [][]p, Smullyan’s awareness of self-awareness). Bruno > >> Of course current rovers don't have AI which would entail them learning and >> planning, which would require that they be able to run a simulation which >> included some representation of themself; but that representation might be >> very simple. When you plan to travel to the next city your plan includes a >> representation of yourself, but probably only as a location. >> > > Hod Lipson's starfish's representation of itself is no doubt rather > simple and crude, but it does pose the question of whether it might > have some sort of consciousness. > > > -- > > ---------------------------------------------------------------------------- > Dr Russell Standish Phone 0425 253119 (mobile) > Principal, High Performance Coders > Visiting Senior Research Fellow [email protected] > Economics, Kingston University http://www.hpcoders.com.au > ---------------------------------------------------------------------------- > > -- > You received this message because you are subscribed to the Google Groups > "Everything List" group. > To unsubscribe from this group and stop receiving emails from it, send an > email to [email protected]. > To post to this group, send email to [email protected]. > Visit this group at https://groups.google.com/group/everything-list. > For more options, visit https://groups.google.com/d/optout. -- You received this message because you are subscribed to the Google Groups "Everything List" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To post to this group, send email to [email protected]. Visit this group at https://groups.google.com/group/everything-list. For more options, visit https://groups.google.com/d/optout.
