Philip,
Unfortunately, I don't have time to maintain a Web record of the key
points I make in an e-mail dialogue -- frankly, I don't *really* even have
time for as much e-mailing as I've been doing this last week
!!
Hopefully Eliezer will write up a brief paper on his observations about
AIXI and AIXItl. If he does that, I'll be happy to write a brief
commentary on his paper expressing any differences of interpretation I have, and
giving my own perspective on his points.
Actually, I imagine the discussion of AIXI Friendliness will be shorter
and smoother than this last discussion. By now I've read the Hutter
paper more carefully, and I've also gotten used to the language Eliezer uses to
talk about AIXI/AIXItl. I reckon the next part of the discussion will have
a lot less misunderstanding (though perhaps more genuine disagreement, we'll
see ...)
--
Ben
-----Original Message-----
From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED]]On Behalf Of Philip Sutton
Sent: Sunday, February 16, 2003 7:17 PM
To: [EMAIL PROTECTED]
Subject: Re: [agi] Breaking AIXI-tl - AGI friendliness - how to move onHi Eliezer/Ben/all,Well if the Breaking AIXI-tl discussion was the warm up then the discussion of the hard stuff on AGI friendliness is going to be really something! Bring it on! :)----Just a couple of suggestions about the methodology of the discussion - could we complement email based discussion with the use of the web? What I find in these very long (and at times highly technical) discussions is that the conclusions get lost along the way.I was a member of Government commission on the timber industry some years back and the commission members were chosen to represent the various sides in the industry/conservation conflict. The parties had been engaged in almost total warfare for the last 20 years and the idea was to see if we could find any common ground on which to build a new win-win strategic direction for the industry.One of the techniques we used informally was to let each side record what they saw the issues as, including commenting on each other's positions, and then recording consensus as it emerged.What this meant was that each 'side' kept an updated summary of the key 'facts', arguments and conclusions - as they saw them. Then the facilitator worked with the group to collect key 'facts', arguments and conclusions that both sides could agree on.At the end of the process we developed strategies for taking action on the areas of agreement and we developed a process for continuing to grapple with the on-going areas of disagreement.So in our case with the discussion of how to ensure AGI friendliness or community-mindedness, we could let any party to the discussion who feels they have a distinct point of view that is not well represented by anyone else to keep a rolling summary of the key 'facts', arguments and conclusions as they see them. These summaries could be kept on separate webpages, maintained by each party to the discussion. Everyone would have access to the summaries and the discussion would be carried out via email through the list.At some stage when the discussion has taken form on at least some key issue we might try to see if the group as a whole can agree on anything - and someone needs to write thouse outputs up in a rolling consolidated form on another web page.This might sound like a lot of work and excess structure but I think it helps to draw something solid out of the swirl of discussion and allows us to move on when a solid foundation has been built....And on another issue, if people are using highly technical arguments, and if those arguments are meant to have higher order implications could each person include a commentary in plain English along with their technical discussion, so that everyone can follow at least the higher order aspects of the discussion as it unfolds.Right at the end of the AIXI-tl debate Eliezer started using the 'magician in the cavern' analogy and all of a sudden I felt as if I was understanding what he was driving at. That use of analogy is a wonderful way to keep everyone in the loop of the conversion. If that sort of thing could be done more often that would be very helpful.What do you reckon?Cheers, Philip