Re: Volitional Morality and Action Judgement

From: Randall Randall (
Date: Mon May 24 2004 - 12:40:26 MDT

On May 24, 2004, at 1:08 PM, John K Clark wrote:

> On Sun, 23 May 2004 "Eliezer Yudkowsky" <> said:
>> I think it might literally take considerably more caution to
>> tweak yourself than it would take to build a Friendly AI
> Why wouldn’t your seed AI run into the same problem when it tries to
> improve itself?

For the same reason that it's easier to predict the
consequences of changing something in the Linux
kernel than the consequences of making changes to
a bacterial genome, in general.

Randall Randall <>
'I say we put up a huge sign next to the Sun that says
"You must be at least this big (insert huge red line) to ride this 
ride".' --

This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:47 MDT