Re: Friendliness successfully IMPLEMENTED!

From: Thomas McCabe (pphysics141@gmail.com)
Date: Wed Mar 19 2008 - 16:28:13 MDT


On Wed, Mar 19, 2008 at 5:35 PM, <mwaser@cox.net> wrote:
> > 1). Your email's subject line is obviously misleading. The primary
> > concern is how to make Friendly AIs, not Friendly humans.
>
> Oh, come on . . . . given that *no one* has an AI nor expects to have one this year, you have absolutely no excuse for being mislead by the title. The *only* intelligent machine that I possibly could have implemented Friendliness on is a human being. This is an intelligent first step to implementing it on a future AI.

Humans and AIs have radically different cognitive structures. Trying
to implement Friendliness on both at the same time isn't going to
work.

> How am I not addressing the/*your* primary concern?
>
> How is the subject line misleading -- given that it is already longer than the visible field of my webmail page?

My initial thought was that you had actually written out a technical
specification and tested it on working software.

> Me thinks thou doth protest far too much. Why does this bother you so much? Are you afraid of being infected with a meme that enforces ethics?

I'm afraid of this list being infected with impossible Friendliness
architectures.

>
> > 2). Please provide some evidence to the list that you haven't
> > committed any immoral acts since declaring Friendliness, which is a
> > rather audacious claim.
>
> First, I have never made any claims about morals. I do not agree with most proclamations that most people make when they start using the word morals. The term is *ethics* -- many people might believe that they are synonymous but they have radically different connotations for many others.

Point taken.

> Second, about the only proof that I can provide is to declare that I have not *knowingly* performed any unethical acts since being fully infected and challenge everyone to prove any evidence to the contrary.

Since none of us have any idea who you are or where you live, this
would be rather difficult.

> The problem with this "proof" is that I'd also say that I'm not sure that you could provide any evidence of me knowingly performing unethical acts in the last several *YEARS* -- so Friendliness hasn't visibly changed my personal *willingness* to act ethically AT ALL. I was previously willing to act ethically and pretty much always did so (to the extent that I can't remember not doing so in the past several years) and I remain that way.

One of Christianity's main principles is that everyone acts
unethically all the time. This isn't quite true, but it's plausible
enough, given most people's understanding of human cognitive
architecture. What makes you different from everyone else?

> Third, I can't think of any other evidence I could provide. Do you have any suggestions to help me?

If you're intelligent enough to rewrite human architecture to that
extent, without the benefit of ultratechnology, you should be
intelligent enough to figure out how to provide evidence for it.

> > 3). The fragility of this type of cooperative Friendliness has been
> > long since established in evolutionary biology.
>
> What cooperative Friendliness? I'm not seeing any cooperation here at all. I asked for assistance. I said "If you believe that this is incorrect, *PLEASE* free me by showing me where this meme is harmful and rid me of my infection." You came back and attacked me for being misleading and then demanded proof that I was a good person.

It only becomes cooperative when it spreads to a large group of
people, which (if I understand correctly) is what you're assuming.

>
> > The system is
> > vulnerable to anyone who wants to disrupt it. Mitigating this requires
> > a huge technological or power advantage, which we don't currently
> > have.
>
> Prove your statement by freeing me of the meme or making me willingly perform an unethical act.

I don't have to. If I'm powerful enough, I can simply *shoot you*.
Poof, there goes Friendliness.

> Mark
>

-- 
 - Tom
http://www.acceleratingfuture.com/tom


This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:01:02 MDT