Re: Building a friendly AI from a "just do what I tell you" AI

From: Joshua Fox (joshua@joshuafox.com)
Date: Tue Dec 04 2007 - 11:33:50 MST


Eliezer,

I didn't quite understand your message, which is a bit funny given the
context.

Did you mean that
1. I said Tim's article was clearly written because I thought I understood
it, but really I might not have?
2. That Tim might think he understands my email, but really he might not
have?
3. That despite what I said about formal and informal styles, Tim's article
should be less formal?

Joshua

2007/12/4, Eliezer S. Yudkowsky <sentience@pobox.com>:
>
> Joshua Fox wrote:
> > 2007/11/21, Tim Freeman <tim@fungible.com <mailto:tim@fungible.com> >:
> >
> > ... http://www.fungible.com/respect/index.html. Unfortunately the
> paper
> > needs revision and hasn't yet made sense to someone who I didn't
> > explain it to personally. Maybe I'll be able to make it readable
> > over Thanksgiving.
> >
> > Tim,
> >
> > The paper is, in fact, very clearly written. Its style achieves a nice
> > balance between the heavy formalism of academic papers and the informal
> > exposition in many transhumanist items, even the better ones. Each style
> > has its place, but your article's is just right for what it is aiming
> at.
>
> Tim, I'd verify that praise if I were you:
>
> http://www.overcomingbias.com/2007/10/illusion-of-tra.html
> http://www.overcomingbias.com/2007/10/double-illusion.html
>
> --
> Eliezer S. Yudkowsky http://intelligence.org/
> Research Fellow, Singularity Institute for Artificial Intelligence
>
>



This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:01:01 MDT