[extropy-chat] Re: Structure of AI

[Adrian Tymes]

--- Eliezer Yudkowsky <sentience at pobox.com> wrote:
> scerir wrote:
> > Is a simulation 'detailed enough' the same as a
> simulation
> > 'deterministic enough'?

No.  Details refer to what can be detected in the
present, but says little about future states - save
that they comply with whatever rules of physics have
been set up.  It allows for completely random events
to trigger different specific future paths.

> > Because, in this case, the
> simulation
> > would be too strong, that is to say no 'free will'
> (whatever 
> > it means) would be allowed.
> 
> This is where Adrian's rule comes in handy; until
> you can give me an 
> experimental test for the presence or absence of
> free will, you're not 
> allowed to talk about it.  :)

You're allowed to talk about it.  One has to have a
way to find out that the test is lacking.  Just don't
continue to obssess over it once you discover the
impossibility of testing.