📄 Extracted Text (1,457 words)
From: Jeffrey Epstein <[email protected]>
To: Ben Goertzel
Subject: Re: why not have the machine take iq tests
Date: Mon, 11 Feb 2013 17:35:51 +0000
put toghetr a proposal
On Mon, Feb 11, 2013 at 12:38 PM, Ben Goertzel > wrote:
Yeah... the child IQ tests would be a reasonable research focus.... I
can see that making an AGI pass these tests would be
attention-grabbing in the media, and also scientifically compelling
to a certain subset of the community.
I'd have to find a child psychologist willing to actually share some
specific test questions; they are cagey about supplying them online or
in books for some reason... I guess they don't want parents to coach
their tots on the specific questions ;p .... But that wouldn't be too
hard.
Selmer Bringsjord, at RPI, has done some work making robots pass
vision and movement oriented IQ tests
http://wwwspi.edu/dept/NewsComm/Magazine/dec02/atrensselaer/atrensselaer5.html
[Selmer is an interesting guy btw.... He is a rather good Al
researcher, mathematician and cognitive scientist -- yet also a pretty
hard-core Christian, who believes human-level AGI is impossible
because computers and robots don't have souls !! The capability of
the human mind to maintain fundamental contradictions, yet still
reason logically in closely related areas, is pretty impressive...]
But Selmer is taking an approach of especially engineering and tuning
a system just to pass each specific test.... To me, that is not very
interesting.... It's like taking a really dumb kid and spending
hundreds of hours coaching the kid on specific sorts of IQ questions
that you know he is going to be asked. The child IQ tests could be a
good objective for an AGI research project, but only if pursued in the
right spirit...
Well ... let me know if you want to fund me and David Hanson to work
on making one of his robots pass the child IQ tests ;-/ .... We
could put together a brief proposal in this direction fairly quickly I
would suppose. Robot-wise, this would actually just require a torso
with hands/arms and a head with eyes & ears; we wouldn't need to worry
about locomotion. AI-wise, it's basically the same stuff I'm trying
to get done anyway, just a slightly different focus and a clearer
evaluation mechanism...
BTW I am back in the US again right now, due to a family emergency....
I could possibly come up to NY again later in the week if you want to
EFTA00953909
seriously pursue this possibility.... I'll probably be back in Hong
Kong by the weekend.
thx ;)
ben
On Mon, Feb II, 2013 at 11:00 AM, Jeffrey Epstein <[email protected]> wrote:
> it seems to me to be a more explicit well defined goal , you always ask
> what can i show you or others. I thinkg the abiliity to pass a number of iq
> tests for children, would provide focus if not insight
> On Mon, Feb 11, 2013 at 10:15 AM, Ben Goertzel wrote:
»Yeah, I have looked at this test before:
>>
>> http://en.wikipedia.org/wiki/Wechsler_Preschool_and_Primary_Scale_of Intelligence
>>
>> Note that the test items often involve vision and action, not just
» abstract puzzle solving...
» Making an OpenCog system do well on this test would be a great
» objective for a research project....
>> Or, even if that's not the explicit objective of the research, I would
>> imagine that after some more development is done, it will be able to
» pass those tests automatically...
» If an Al system first deals with these preschool/primary IQ problems,
>> and then moves on to the more advanced IQ problems -- THEN it will
>> probably be able to deal with the more advanced IQ problems in a more
>> human-like, AGI-ish way, rather than just solving them using very
>> specialized techniques...
» -- Ben
>>
>>
>> On Mon, Feb 11, 2013 at 9:08 AM, Jeffrey Epstein <jeevacation®gmail.com>
» wrote:
»> even iq tests for children. there are enough diffemt types of tests
>» making
>» the sytem robust
» >
>> > On Mon, Feb 11, 2013 at 9:59 AM, Ben Goertzel wrote:
>>>>
>>» Hi,
»»
»» That's certainly a natural question to ask...
»»
»» I think one could engineer a system to do really well on current
»» written IQ tests, with a couple years' focused work by a small team...
EFTA00953910
»»
»» IQ tests are hard for people, because people do them using the same
»» abilities they use to do other, more complex and useful tasks.... But
»» just as folks have engineered specialized systems for chess and
»» Jeopardy, one could engineer a special system for IQ tests...
»»
»» For example, with rather modest effort, this group engineered a system
»» that does well on specific portions of the standard IQ test
»»
»» http://www.kurzweilai.net/computer-programs-that-ace-iq-tests
»»
»» I believe a similar approach could be taken to each of the other
»» portions of the IQ test.... Putting them together, one would then
»» have a high-IQ AI system -- without much capability to do anything
»» else...
»»
»» The tests used to measure intelligence of preschoolers are a bit more
»» interesting to me, in the sense that they tend to involve intelligent
»» engagement in the world, which is harder to "fake" ...
»»
»» The bottom line is, though, IQ tests are moderately effective for
»» humans because they are designed to exploit particular features of the
»» human mind. It's hard for humans to pass IQ questions without being
»» pretty generally intelligent, but the same wouldn't necessarily be
»» true for Al minds...
»»
»» -- Ben
»»
»»
»»
»» On Mon, Feb 11, 2013 at 6:53 AM, Jeffrey Epstein
»» <[email protected]>
»» wrote:
»» > https://www.youtube.corrilwatch?v=229ehewjdUlt
»»>
»»>--
» >>>. ******a****************************************************
>> >> > The information contained in this communication is
>> >> > confidential, may be attorney-client privileged, may
>> >> > constitute inside information, and is intended only for
»>» the use of the addressee. It is the property of
>> >» Jeffrey Epstein
>> >> > Unauthorized use, disclosure or copying of this
»» > communication or any part thereof is strictly prohibited
>> >> > and may be unlawful. If you have received this
>> >> > communication in error, please notify us immediately by
>> >> > return e-mail or by e-mail to jeevacation®gmail.com, and
>> >> > destroy this communication and all copies thereof,
»»> including all attachments. copyright -all rights reserved
»»
»»
»»
»» --
»» Ben Goertzel, PhD
EFTA00953911
»» http://goertzel.org
»»
»» "My humanity is a constant self-overcoming" -- Friedrich Nietzsche
>> >
>> >
» >
» >
» >
• > ***********************************************************
>> > The information contained in this communication is
>> > confidential, may be attorney-client privileged, may
>> > constitute inside information, and is intended only for
>» the use of the addressee. It is the property of
>> > Jeffrey Epstein
>> > Unauthorized use, disclosure or copying of this
>> > communication or any part thereof is strictly prohibited
>> > and may be unlawful. If you have received this
>> > communication in error, please notify us immediately by
>> > return e-mail or by e-mail to [email protected], and
>> > destroy this communication and all copies thereof,
>> > including all attachments. copyright -all rights reserved
» --
» Ben Goertzel, PhD
» http://goertzel.org
>>
>> "My humanity is a constant self-overcoming" -- Friedrich Nietzsche
>
> **************** ********** ****** ********** *****************
> The information contained in this communication is
> confidential, may be attorney-client privileged, may
> constitute inside information, and is intended only for
> the use of the addressee. It is the property of
> Jeffrey Epstein
> Unauthorized use, disclosure or copying of this
> communication or any part thereof is strictly prohibited
> and may be unlawful. If you have received this
> communication in error, please notify us immediately by
> return e-mail or by e-mail to [email protected], and
> destroy this communication and all copies thereof,
> including all attachments. copyright -all rights reserved
Ben Goertzel, PhD
http://g g
EFTA00953912
"My humanity is a constant self-overcoming" -- Friedrich Nietzsche
The information contained in this communication is
confidential, may be attorney-client privileged, may
constitute inside information, and is intended only for
the use of the addressee. It is the property of
Jeffrey Epstein
Unauthorized use, disclosure or copying of this
communication or any part thereof is strictly prohibited
and may be unlawful. If you have received this
communication in error, please notify us immediately by
return e-mail or by e-mail to [email protected], and
destroy this communication and all copies thereof,
including all attachments. copyright -all rights reserved
EFTA00953913
ℹ️ Document Details
SHA-256
71b08e0e3467b00134aa69fe2ab56da37e7db92a2e6e66be35387f839c77ce7a
Bates Number
EFTA00953909
Dataset
DataSet-9
Document Type
document
Pages
5
Comments 0