EFTA02565964

From: on behalf of Ben Goertzel Sent: Monday, February 11, 2013 6:03 PM To: Jeffrey Epstein Subject: Re: why not have the machine take iq tests Sure thing -- will do tomorrow or Wednesday, thanks ;) On Mon, Feb 11, 2013 at 12:35 PM, Jeffrey Epstein <[email protected]> wrote: > 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://www.rpi.eduidept/NewsComm/Magazine/dec02/atrensselaer/atrensse » laer5.html » [Selmer is an interesting guy btw.... He is a rather good AI » 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... >> EFTA_R1_01730876 EFTA02565964 » 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. Al-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 seriously pursue this possibility.... I'll probably be back in » Hong Kong by the weekend. » thx ;) » ben >> » On Mon, Feb 11, 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 10:1S AM, Ben Goertzel » » » » 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 wrote: 2 EFTA_R1_01730877 EFTA02565965 » » solving them using very specialized techniques... » » » » -- Ben » » » » » » On Mon, Feb 11, 2013 at 9:08 AM, Jeffrey Epstein » » <[email protected]> » » wrote: » >» even iq tests for children. there are enough differnt 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... » » » » » » 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 » » » 3 EFTA_R1_01730878 EFTA02565966 » » » » » » » » » On Mon, Feb 11, 2013 at 6:53 AM, Jeffrey Epstein » » » <[email protected]> » » » wrote: » » >» https://www.youtube.com/watch?v=229ehewjdUk » » » > » » » > — » » » > » » >» 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, disdosure 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, induding all attachments. copyright -all » » >» rights reserved » » » » » » » » » » » » -- >>» » Ben Goertzel, PhD »»>> >> >> >> >> >> » "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 » » » » 4 EFTA_R1_0 1730879 EFTA02565967 » » "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 » "My humanity is a constant self-overcoming" -- Friedrich Nietzsche > > ********** i YYYYYYY ***** ***** ***** ********•******** ********* > 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 "My humanity is a constant self-overcoming" -- Friedrich Nietzsche <?xml version="1.0" encoding="UTF-8"?> <!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd"> <plist version="1.0"> <dict> <key>conversation-id</key> 5 EFTA_R1_01730880 EFTA02565968 <I nteger>245372</i nteger> <key>date-last-viewed</key> <integer>0</integer> <key>date-received</key> <integer>1360605800</integer> <key>flags</key> <integer>8590195713</integer> <key>gmail-label-ids</key> <array> <integer>6</integer> <integer>2</integer> </array> <key>remote-id</key> <string>275521</string> </dict> </plist> 6 EFTA_R1_01730881 EFTA02565969