[ExI] Echoes of the Invincible

Samantha Atkins sjatkins at mac.com
Wed Jun 26 22:40:05 UTC 2013


On Wed 26 Jun 2013 01:59:09 AM PDT, Eugen Leitl wrote:
> On Tue, Jun 25, 2013 at 08:39:48PM -0700, Samantha Atkins wrote:
>
>> Why conflate explicit codifying with being able to build an AGI at all?  It is much more likely to be a hybrid of symbolic and sub-symbolic techniques.  Significant parts of an AGI need to self unfold/develop from the "seed" which is about the best we can likely come up with as human programmers and system designers.   I don't think that any godhood is required.
>
> I'm willing to bet that we're barely smart enough to crib
> off biology, or create boundary conditions for emergence.
> Both result in evolutionary systems.
>
> I think the naturally inspired and expecially naturally
> derived intelligences have the best story and track
> record so far.
>

They do within the environment or close enough to it that they evolved 
fitness for.  It remains to be seen how adaptable they are to radically 
different environments that may or may not be conducive to creating 
enough of the natural environment within.

Personally I think when we can program enough somewhat sloppy 
interconnected highly parallel artificial circuits into a system that 
we will see intelligence quite similar to what we see in biological 
systems.  Whether it turns out to be much better than biology produces 
it any time soon is of course an open question.

>> Why is a stable goal system being mixed up with a stably non-evolving society?
>
> How would you implement a stable goal system in an animal?

We probably should clarify, or I should get clarity on, exactly what is 
meant by "stable goal system" in this conversation.   Does it mean?

a) concisely described;
b) easy to evaluate and reason about;
c) unable to drive unexpected actions;
d) having an invariant core (supergoal[s]);
e) having invariant subgoals..

??? Or some mixture of the above and other elements?  Until there is 
mutual agreement on this the discussion is not likely to be fruitful.

- samantha



More information about the extropy-chat mailing list