From: sam kayley (thedeepervoid@btinternet.com)
Date: Fri Nov 18 2005 - 10:27:08 MST
From: "Michael Wilson" <mwdestinystar@yahoo.co.uk>
> > a theory gap (proprietary or simply advanced software theory
> > that is difficult to discern by untrained, or
> > reverse-engineers(also possible)),
>
> IMHO this is highly likely for any AGI design that actually
> works on current hardware. AGI is very hard to understand,
> extremely difficult to explain, and I'm willing to bet damn
> near impossible to reverse engineer without the full source
> and development documentation (and pretty difficult and time
> consuming even then).
Looking at the code, sure, but running the code on lots of examples in a
debugger should shed some light for someone with experience of cracking and
bayes/AIT. Several people can do this simultaneously, of course, and AGI is
easier to explain when working within a team where members are not stripping
details to avoid giving too much away.
I suspect any deliberate attempts at code obfuscation, if they are to be
more than a nuisance to an experienced cracker would have a performance
penalty.
This archive was generated by hypermail 2.1.5 : Tue Feb 21 2006 - 04:23:19 MST