Re: [sl4] Simple friendliness: plan B for AI

From: Vladimir Nesov (
Date: Tue Nov 09 2010 - 12:39:51 MST

On Tue, Nov 9, 2010 at 10:07 PM, Alexei Turchin <> wrote:
> I roughly figured, what principles could form the basis of a simple friendliness:
> (0..7)

Burdensome detail. Why these rules? An actual FAI won't satisfy them
(for example, "AI must comply with all existing CRIMINAL an CIVIL
laws" is ridiculous and in all CAPS).

> Simple friendliness is plan B if mathematical FAI fails.

What is the intended meaning behind "mathematical" here, and hence the
distinction? Mathematics is proxy for clear understanding. Human value
is complex, hence you can't stumble on it blindly, which is the
limitation where clear understanding is absent.

Vladimir Nesov

This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:01:05 MDT