Re: SIAI's flawed friendliness analysis

From: Christian Szegedy (szegedy@or.uni-bonn.de)
Date: Fri May 30 2003 - 07:01:38 MDT


Eliezer S. Yudkowsky wrote:

>
>> As a parent, I would interfere with my child's self-determination if
>> they were going to do something sufficiently destructive. I'd also try
>> to change them so that they no longer *wanted* to do the destructive
>> thing.
>
>
> Angels and ministers of grace preserve us, Ben, I hope you were
> talking about an AI and not a human child! Just reach into a human
> mind and tamper like that? Thank Belldandy my own parents didn't have
> that capability or I'd be a nice, normal, Orthodox Jew right now.

You must be joking!

> What about the kids' values for themselves? Parents don't own children.

It is not about owning. People are trying to influence each other
all the time, and parents try to educate their children, which is
quite right.

>> But we presumably don't want a Friendly AI to take on this kind of
>> parental role to humans -- because it's simply too dangerous??
>
>
> Because I think it's wrong. Direct nonconsensual mind modification
> seems unambiguously wrong.

Nonconsensual? It's too black and white. I don't think there is a clear
border between consensual and nonconsesual mind modification.
Would you ask your child: "Are you agree that I modify your mind in
order to prevent you from leaving the pathway?"

And even if the other mind agrees to be modified, was not this
decision the result of some kind of external manipulation?

Best Regards, Christian



This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:42 MDT