This is more along the lines of what I have been trying to say as well, How and can we enumerate the type of stepping stone tasks we need an AGI to perform, rate the complexity of them, and then look thru and see which ones we really want to concentrate as teh more important matters, with the first three being the most important
*navigation, *manipulation, *communication/ languages James Ratcliff Mike Tintner <[EMAIL PROTECTED]> wrote: I feel very confident that this - a simple physical navigation test - is the way to go. But you are raising a good point - which I had more or less reached in a related exchange wth Ben - which is that it is clearly necessary to have some kind of evolutionary table of adaptivity, so that people understand how a simple navigation test will lead onwards and upwards.. In other words, you need to illustrate how, in a general way, the ability to understand language and master, say, relatively abstract subjects of formal knowledge (which is where most people's minds are currently Turing-fixated) have evolved from and are dependent on basic physical skills, through evolution. Just a couple of thoughts to begin with here. If anyone wants to develop them, I'll definitely respond with further ideas - You need to show that the ability to master physics and chemistry, depends on the physical ability to move objects around. Ditto the ability to master maths depends on the ability to count, physically divide and separate objects. (Interesting aside - infinity was a taboo subject in maths. until as McLuhan pointed out, the printing press (with its capacity to go on for ever) made it a realistic subject to conjure with). You need to show that the ability to master language - with its combinatorial qualities - constantly producing new combinations of subject, verb and object, is dependent on and evolved from the ability to manipulate and combine complex sets of tools. You need a progressive table of *navigation, *manipulation, *communication/ languages (starting with things like bees' dances and nothing so sophisticated as verbal language), *hunting, *sexual exchange/ copulation, *games of play (which starts fairly on in evolution), *building structures (enormous numbers of animals right down to worms are architects of some kind)...... As I said, just some odd thoughts. ----- Original Message ----- From: "DEREK ZAHN" To: Sent: Wednesday, April 25, 2007 3:57 PM Subject: Re: [agi] The University of Phoenix Test [was: Why do you think your AGI design will work?] > > Mike Tintner writes: > >>Let's call it the Neo-Maze Test. > > I think this type of test is pretty interesting; the objection > if any is whether the capabilities of this robot are really > getting toward what we would like to consider general > intelligence. > > For example, moving from the simple maze to navigating > an office building involves new reasoning abilities such as > understanding how to work an elevator. If that ability > is programmed explicitly it is suspicious, but if it is somehow > learned, that's certainly more interesting. > > In some ways this idea is similar to another easy-to-define > approach to AGI with tangible intermediate goals: recapitulating > phylogeny: Start with a fruitfly simulator and build a "brain" > capable of passing the Turing-fruitfly test (well, not fooling > the other fruitflies so much, but being able to flourish in the > fruitfly's world by controlling a fruitfly's body). Then move > on to the Turing-mouse test, the Turing-dog test, and > the Turing-monkey test. > > The reason such an approach is distasteful to most AGI > researchers is the opinion that it puts a lot of work into > doing things that seem completely unrelated to the core > task, and even once you have a simulated monkey, are > you really very close to AGI? > > I don't know the answer. > > > ----- > This list is sponsored by AGIRI: http://www.agiri.org/email > To unsubscribe or change your options, please go to: > http://v2.listbox.com/member/?&; > > > > -- > Internal Virus Database is out-of-date. > Checked by AVG Free Edition. Version: 7.5.463 / Virus Database: 0.0.0/0 - > Release Date: 00:00 > > ----- This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?&; _______________________________________ James Ratcliff - http://falazar.com Looking for something... --------------------------------- Ahhh...imagining that irresistible "new car" smell? Check outnew cars at Yahoo! Autos. ----- This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=231415&user_secret=fabd7936
