Re: Volitional Morality and Action Judgement

From: Eliezer Yudkowsky (
Date: Wed May 26 2004 - 19:34:42 MDT

Mark Waser wrote:

> The
> best way to ensure that an AI is truly friendly is to make it social, make
> it realize that it is imperfect and capable of mistakes and bad decisions,
> and have it realize that the best way to avoid mistakes is to consult (and
> work with) others. Of course, since you don't exhibit these behaviors . . .

Thank you, I'll file that with the other thousand brilliantly insightful
solutions to FAI I've heard over the last three years, with stickers that
say "Heartwarming", "Nontechnical", "Anthropomorphic", "No Walkthrough
Given", and "Fits on a T-Shirt".

> Wow. That's REALLY arrogant.

I don't think so. I'm too modest to be REALLY arrogant. My compassion and
pity prevents me from mocking fools with the audacity to disagree with me;
it is not their fault that they are less gifted than I. But thank you for
the compliment, and I'll try harder in the future.

Eliezer S. Yudkowsky                
Research Fellow, Singularity Institute for Artificial Intelligence

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