From: James Higgins (jameshiggins@earthlink.net)
Date: Sat Jul 27 2002 - 16:28:08 MDT
Gordon Worley wrote:
> The random person on the street has the same kind of brain an AI
> researcher has: a human one. When it comes to SI, it won't be a matter
First, the Box problem doesn't apply to an SI. I believe most people
(at least on SL4) agree that once you have an SI there is no way to keep
it in prision, period. Thus the box tests can only apply to
infra-human, human level or trans-human AIs.
> of just convincing (though that will be one likely mode of attack), but
> of using various techniques to attack the human brain: hypnosis,
> sensory confusion, magic words (you never know), and more ways that we
> haven't thought up yet. The only case in which the AI researcher has an
It is, in my personal opinion, unlikely that an infra-human or human
level AI could effectively control a human via a TTY with the safeguards
previously discussed on this list. This type of thing only starts to
become practicle with trans-human AI.
> advantage is if the AI is infrahuman or human level and if the
> researcher is someone like Eliezer who knows what an unFriendly
> infrahuman or human level AI might try to do to escape and can watch for
> these and stop himself if he sees what he's doing. Unfortunately, this
> advantage is very slight and only really applies to mind attacks, not
> brain attacks (hence the advantage only existing against infrahuman and
> human level AI).
>
> All humans look the same to SIs, even the ones that created ver.
In any case, none of this is at all relevant to the box tests conducted
and report here on SL4. It can't be because neither Eliezer nor Justin
are SIs and, thus, can't employ brain attacks. So the argument that all
humans are equivelant to an SI using brain attacks is irrelevant here.
Since is is unlikely that random people will be conversing with AIs in
boxes, and even if they are they won't have the power to release them, I
maintain that the experiments conducted by Justing are not relevant and
can not be used as the basis for any decision making.
James Higgins
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:40 MDT