Phil Sutton wrote:
***
I think if an ethical goal is general and
highly important then we should make sure we find ways to hard wire it - ie we
shouldn't launch AGIs into the world until we have worked out how to hardwire
the really critical ethical goals/contraints.
...
I
think it is possible to lodge very abstract concepts into an entity, and use
hard wiring to assist the AGI to rapidly and easily recognise examples of the 'hard' abstract concepts - thus
giving some life to each abstract concept
. ..
Making sure that the
AGI has the perceptual mechanisms to know and experience the critical early
examples would be a key part of the values development process. Training
and self directed learning would then add many many more examples to the core
abstract concept thus allowing it to become more and more general over time,
informed by the extensive and subtle experiential database that the AGI builds
up over time.
***
Phil, this is not really a disagreement about AI
ethics, it's a fundamental disagreement about AI theory and the complexity of AI
dynamics
I am not bullish on the possiblity of reliably
hard-wiring any specific content into a real AGI system....
It seems to me that you can *reliably* insert
content into an AGI system's mind-brain ONLY insofar as you
understand the meaning that a specific "insertion" is going to have in terms of
the overall dynamics of the system's mind/brain....
You can certain put content in there, and see what it
leads to.. This may be a valuable thing to do, in many cases and for many
reasons.
But I tend to think that the dynamics of a true AGI is
going to be pretty complicated and pretty hard to predict in
detail...
I agree with the interactive teaching approach, for
teaching an AGI ethics and other things too. I think that if you do the
interactive teaching approach, the initial "lodging of abstract concepts" you've
suggested will become basically irrelevant. What it learns thru being
taught will be the critical thing...
-- Ben
