Re: Mind Reading - Approach to Friendliness

From: Charles D Hixson (
Date: Sun Jun 18 2006 - 21:59:01 MDT

H C wrote:
> Concept is pretty simple. You develop really powerful
> analytical/debugging applications that can display the entire contents
> of the AI mind in tractable and useful visual representations and
> extrapolations into future states of the mind.
> Strategy:
> Let the AI 'sleep' (i.e. down-time) long enough to periodically
> analyze the entire contents of the mind. The point in the analysis is
> to isolate areas of potential risk/danger and either directly
> modify/secure these areas, or to instruct the AI via it's
> communication channel with the programmers (and obviously check up on
> the AI's obediance).
> Theoertically, the only window for danger would be in the period it is
> awake and thinking. It would need to come to several conclusions
> simultaneously that all affirmed some non-Friendly behavior, and
> develop that intention into a non-Friendly action before it went to
> sleep.
> A strategy to combat this possibility would be to develop dynamic
> diaognostic software, that could actively monitor the entire range of
> the AI's mental and external actions. A comprehensive security system
> would need to be developed to set alerts, automatic shut downs,
> security warnings, and anything abnormal or potentially remarkeable.
> The point of implementing this strategy is to allow a non-verifiably
> Friendly AGI to help the programmers and mathematicians developing
> Friendliness theory in a relatively safe and reliable manner.
> -Hank
Centers of power are attractive to people who desire to control.
Allowing the programmers this kind of access to a working AI seems to me
suicidally wrong. It's all very well when what's available is the
ability to engage in a lot of hard work for dubious rewards. When it
becomes a center of power an entirely different crew of people will be
attracted...and you only need one bad apple.

How many centuries are proposing that this setup should endure? It's

This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:56 MDT