For instance, if someone built a robotic dog that was as good as a real
dog
> at perception,
> cognition and action, I would consider that a big step toward powerful
AGI.
> But dogs really
> suck at compression. (Yeah, their brains may carry out compression
> operations internally.
> But, if you give a dog an explicit compression problem to solve, it will
not
> give a very
> useful or impressive answer...)
How will you develop and test the vision and hearing systems? Does your
system extract the right features? If so, your reconstructed inputs
should be
perceptually indistinguishable (at least to a real dog).
But who says the system will be able to reconstruct its inputs?
Can a dog reconstruct its inputs?
I don't think either of my dogs can.... I just asked my 2 year old Golden
Retriever to do so,
and she gave me a cute but quite uncomprehending look...
What you are talking about seems to be NOT
-- AGI systems that are compressors
but rather
-- the ability of smart engineers to use the internal mechanisms of some AGI
system to make a compressor
Then your intelligence test gets complex, and becomes something like "a
system is an AGI if a suitably smart engineer can use its internals to make
a great compressor, without having to add on too much"
-- Ben g
-----
This list is sponsored by AGIRI: http://www.agiri.org/email
To unsubscribe or change your options, please go to:
http://v2.listbox.com/member/?member_id=231415&user_secret=fabd7936
