From: H C (firstname.lastname@example.org)
Date: Sun Jun 18 2006 - 18:48:47 MDT
>From: Keith Henson <email@example.com>
>Subject: Re: Mind Reading - Approach to Friendliness
>Date: Sun, 18 Jun 2006 19:43:24 -0400
>At 08:21 PM 6/18/2006 +0000, you 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.
>This *might* work, but my feeling is it would be harder, maybe a *lot*
>harder than designing the AI in the first place.
It might be pretty easy, too.
It's definitely easier than a technical specification of CEV. And it's
universal. It wouldn't be safe for a full blown take-off, but it would be
safe (concievably) to help (in some way) the team designing the AI that
would be safe for take-off.
>>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.
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:56 MDT