Messages

that is a good idea for a service to provide.
You could imagine a server delivering on demand, informations , in a particular format for AI (XML ?).
the info would be classified in several categories (history, news, facts and so on) so you could get a exactly what you are looking for.
you should even be able to ask for simple query like AFRICA+PETROL.
I think Wikipedia could be a good source for this, since they store all the info.
historical or technical info would be for free, while latest news would be paid on per request basis.

Hello
thanks for the reply.
If fact, there is more into the database than just what described.
The absence of data will be as important as data itself.
I do not describe the search engine, since it is not very clear to me either, but it will be based on comparing data statistically.
if we can not find a color for glass, this will trigger some question from the AI , IF NEEDED. And this is the question. Do you always ask yourself what is the color of glass ? probably not. So why bother until it is necessary. And if you discuss this with people, did you ever find a clear answer agreed by everebody ? probably not. So will be the AI, and that is why i think it could be more human than system
that are build to know or answer everything or find a logic in everything. At the extreme, we can look for all objects that are made of glass in the DB and make a statistic about color of them (if exist), then take decision (or not take)
The same for the big cow. If you define it like big , why bother for other (and possibly different) opinions until it happens.
If we really need to confront that BIG to real world (like purchasing a car to transport the cow. We will probably not rely on that information (we will ask for the real size). Or if we do,  we will order a BIG car, and there will be no trouble.
There are many things we believe as true until experience proves the contrary. And there are many thing we believe as true that are false, and we never need to change this opinion, because life does not ask for. So will be the AI, based on statistical result when no data is available. The AI has anyway no way to check for things, so if you say it is big, it can either believe it, reject it, or store.
if we make a statistic off all object described by john and found that 75% of them are described as big, but on the other hand, some other people said they are not, we can infere that john sees everything bigger than it is, especially when it belongs to him.
If we ask john how many feet we need into the truck to put his cow and discover that this size is the one of a small cow, we can start discussing it.
i think that what make a dialogue interesting is when what you have said yesterday, conflict a bit with what i learned today. It give you the need to learn more. The goal will not be to define everything, just to store and sort in a way you can find it back later.
The same as our brain does.

Hello

Here are some ideas about building an AI.
Probably most of it has already been realized in some way , but for me it looks pretty interesting.
If you get the courage to read all, what do you think of ?

'this is the first step to build an AI, that should not emulate a human brain, but
'be some kind of curious mind, able to ask question, learn thing,
'make statement or inference and build a personality by himself.
'The AI should recognize the value of a conversation by the quantity of new data discovered,
'the percentage of contradiction discovered, number of object covered.
'The AI should be logic, but tolerant and be able to use fuzzy concept or accept
'value (like EVERYWHERE, SOMETIME) and accept to make choice based on probability.
'The AI should not look for logic in what is said. we want it free to discuss
'about lies or false opinion. But we want some wisdom in it, so it does not
'accept anything for being true or false, but can accept something being
'a different point of view and respecting it.
'=======================================================================
'The first approach is close from LISP, in a manner we build lists.
'first db is object description for short memory.
'this mean, we will build each object during conversation to grab data from
'what said by the user. to help conversation, some data (the obvious ones) can be taken from
'the 2nd database (same structure), but usually the goal would be to generate questions and
'have specific answers.
'for example it is obvious that a car has 4 wheel(most of time) and an engine.
'This should be found in the 2nd DB, called Knowledge and containing only
'proven(usual) facts or cultural information and being READ-ONLY DB.
'The knowledge DB will also contain the point to clarify.
'More important, the knwledge DB will contain for each object all the properties
'that it would be nice to know, indicated by a question mark.(kind of template for creating
'child objects from generic objects).
'For example the object NA(name)=car will have the propertie CO (color)=?
'indicating that color is something that could be asked for such object.
'We could build some code for expressing urgency level like CO=?! meaning
'that this is possibly something higly important to know.
'For the object "Jim's car" we would like to know the color, the maker etc...
'The knowledge DB cannot be modified by regular conversation (must be in training mode).
'but if a child object (john's car) has new properties created that were not in the
'generic template, we could have a log that warns the programmer that such object
'likely needs to be updated. On long term, this could be automatic.
'Such modification could be tagged (L for learned) for eventual management.
'This should allow to manage contradiction like john saying sky is red.
'the knowledge DB will indicate the sky is blue (on earth), so we can create
'an new object is short memory called NA=john'sky OW=John and set CO=red and GG=sky
'In further discussion with John, we will know that John think that the sky is red,
'contrary to the general opinion.
'(or the AI could infer that John is probably not living on earth and ask)

'This is far from PROLOG, where everything is an attempt to verify/prove things
'as true or false. Here we do not really care, we just try to build a meaning from
'things.
'Structure:
'we got 3 fields. object ID (number incremented), value definition and value.
'each time we find a new object, we start to define it.
'for example a new object will receive immediately at least one record.
'12934 , NA, john
'here object 12934 has NAME=John
'the list of properties is defined, but can be expanded as needed
'Properties should answer to simple questions like WHO, WHEN, WHAT, HOW
'WHO or WHAT
'The goal being to be able to get useful info and create links between object.
'Each propertie will have a table with standard questions.
'for example NA can trigger "What is your name ?" or "How did you call it ?"
'or "Has it a name ?" and so on...
'This is slightly different than AIML, because the AI will be able to choose what
'to ask and how to ask, without having to write script. We still can use AIML, but
'main of it should be generated by the AI itself, not by the programmer.
'the choice factor would be something like "what answer is currently most important or urgent to have to continue dialog".
'this can be easily based on statistic.
'this can make use of pre-recorded TTS more efficient, since we do not need to
'convert standard question to .ogg on the fly.
'In the same time we need a tool that can log the way the AI uses links between
'object to find is something new must be created (new property or new keyword).
'Ideally the develloper interface would include a box to show the objects created,
'the number of positive hit (request fullfiled) to other object
', negative hit (object or information not found) and the number of direct and indirect
'link created.
'===========
'NA , FN, LN, MO, FA, SI, BR, SO, DA, OW
'NA=name of object (usually the word used in conversation, but we can create
'object with special names (codes, acronyms) to cover special needs.
'FN,LN firstname, lastname obviously for people only
'MO=mother, can be a simple name, a pointer to another object, or a key word
'indicating special propertie (for example NONE)
'same for FA(father), SI(sister), BR(brother),SO(son), DA(daugther)
'OW=owner. usually point to another object.
'We do not need more since we can reconstruct the whole family geology from
'these info. We could even simplify using only PA (parent) and CH(child) and
'determine parent function from sex propertie of each member, but this would lead
'to more calculation without benefit.
'GG=genre. Here we probably start our first list of keyword.
'I can propose HUMAN, ANIMAL, MACHINE, OBJECT, EVENT, OPINION ,FEELING, LAW, CONCEPT.
'GE=subtype genre (like dog), usually a pointer to another object. (object dog from the knowledge DB)
'=====================

'WHEN
'=====
'some keyword will be needed NEVER, ALWAYS, SOMETIME, EVERYTIME but basically time
'should be value HH:MM or DD/MM/YYYY or both.
'When possible, relative indicators (like tomorrow or after Xmas)must be converted to "hard" value.
'Object could have few values like
'BI= birthdate (age means nothing, so it will calculated as birth date).
'This apply to every object (start of an event for example)
'DU =duration

'HOW
'======
'this should describe specifically on object, or be in the generic definition of object
'for example:
'NA = Lily
'GG = ANIMAL
'GE = cow
'OW = john987
'usually cow have an averag size that can be described under object=cow.
'in this case, if we want to express that Lily is a big cow, we will add
'SZ=BIG
'This will allow to define the object "Lily" by its own properties with eventual fallback to the
'properties of the generic object "cow".
'possibly, the generic object does not contains the requested info, or only a pointer to another
'object (like SZ of cow is specified as same as "horse", or smaller than "elephant").
'once one size is known, every relative value will be recalculated to prevent having to chase for a value
'from object to object
'ST=status, with our second list of keyword.
'for living creatures DEAD,ALIVE,BROKEN, ASLEEP
'for object GAZ, LIQUID, SOLID, BROKEN
'for machine, ON, OFF, BROKEN
'for event, idea, feeling, GOOD, BAD ?????
'for law and concept ????

'WHERE
'=========
'LO=location, can be anything like Africa, New-York, map coordinates or keyword
'like NOWHERE (somewhere is implicite if LO not specified), EVERYWHERE, or pointer to
'another object (to express the concept WITH ME).

'MISC
'=====
'there will be a set of physical properties like
'LE(length) WI (width), TP(temperature) WT (weight)
'SH (shape) , HU (humidity) SK (skin with values like SOFT, HARD, ROUGH etc.)
'MO (mood), VA(value)
End Sub

you have to set it as default voice for your system.
Possibly too, your version of loquendo is limited to work with the application it is delivered with.
(give more details how you get this voice, it is interesting me).

to get back to the original question.
Life is made from rules (few of them).
There is no way to learn faster than knowing directly the rules.
On the other hand, you do not always need to follow the rules (at your own risks)
for me, a proper AI would work with vectors.
Vectors have direction and length and can be multidimensional.
This way you could build a vector (in real life an intention) made from many many parameters (the dimensions) and somewhat limited by the rules (length in a particular dimension, or what is possible).
For playing some game,like chess, for sure there is no other way than knowing the rules. Guessing them would take too much time.
But once you get the vector created (to win the game, for example) you can play with the AI and let it be self creative about how it will reach the goal.
The interest of goal is you can compare two vector and see if they are opposed, divergent, convergent or parallel.
Some vectors could exist with more dimension than other, but you could still compare them on the dimension they have in common.
With such AI, you could just plug in the idea (getting rich) and let the engine find is own way how to do it (working hard, stealing money and so on...) depending on what it knows from life.
For sure you can make it a Saint by implementing lots of rules and allow no escape, or making it evil, by allowing to skip every rules he want (except physical rules), or make it mad (allowing to ignore all the rules).
The dimensions could be sadness,time,weight,pain and several dimension could be merged into another one (2 othogonal dimensions expressing length, will give the surface. 2 othogonal dimensions, 1 for length , 1 for time, give speed.) the advantage of this is you can create new concept (pain versus position or time) on the fly and let the AI to choose if this goes in the wanted direction or not.
For example, the dimension LIFE can have a scale and a rule could say, no human can exceed the life> than 1 (nobody is immortal)
or a rule that say no operation should multiply dimension life by 0 (killing somebody).
you will get too, a vector created from dimension LIFE and TIME, so each subject could have a different length of life allowed (or simply tracked).

This way you could get a HAL that is less depending of the code being written, than the structures and choices he could made.
for instance, to play chess, such system should know how to move the pieces and have the feeling to play chess (because he knows it is fun, or because it feels forced to do it or he needs to).
Then it will probably find his own way to get the input and the output (creating a graphical interface, or just typing the moves into notepad), depends the tools he could find.

to Art:
not to open a discussion, but just to show that arguing is silly.

quote:My daughter's are both going to have babies around May. Explain how this is a bad idea?

Simple observation shows that human kind fast paced reproduction tends to be negative. You could like the idea to self destruct yourself, but it is still a bad idea from my point of view.
Got 2 kids, very happy of having them, since it will not bring anything to the solution.

quote:If I buy a gun I will probably shoot someone? Not hardly! One person can't speak for the actions of others.

the only final action you could do with a gun, is to shoot with.
This include good probability on shooting on somebody, including you.
Whatever the intent you have in mind when buying it, guns are made for no other uses.

quote:The current operating systems you're using to type this posting is full of bugs, patches, glitches and security holes, yet we all use them every day knowing that they are far from perfect. Ever hear of any cars or other products getting a recall because something was defective? Perfection is a pipe dream...the unreachable plateau that we strive for yet always seem to fall somewhat short of reaching. It's a human condition.
Ever see a duckbilled platypus? If ever a chain of events got screwed up in the creation process that one did. There is a place for everything on this earth.

I agree, there is a place for everything on earth (unfortunately).
Aids virus, serial killer, president Bush included.
That does not mean it is good.
For software and car, yes many of them are far from perfect (because designed by man), but none of them have the status of living creature.
Nature does not like failure. they tend to disappear by themselves.

quote :We need to define living creature as opposed to living or self aware entity. Our programs did not take centuries to evolve. The computer / processing power, according to Murphy's Law is "evolving" exponentially. That is, doubling every 6 months.

Mouse and flies and bacteria reproduced even faster (in minutes for some) , this means nothing, they are not better doing so. Seems time is a factor for improvement only when things are going slow.

currently, bringing anything to life is a bad idea.
first, your only motivation to do this would probably be to "use it" or make it useful.
pretty bad start for a living creature to be considered as a thing or tool.
Second, the only way to build specie is patience and time.
whatever you could pop up from your hat, it will be an alpha version, then a beta... and so on, so you would never stop until it is perfect.
So either it will be considered as "defective, bugged, incomplete" or "finalized, perfect". both states have no future, since no creature on earth rely on such criteria.
The only status that a living creature can have , is to hope to find a place (a niche) and hope it will evolve slow enough so it can follow with the developpement.
This , again require lots of time, and the risk to be destroyed on the long path of evolution, something you wouldn't probably accept for you "child".
I think the biggest problem with popping out of mud a living creature, is not the creature. It is the creator.

try emule...

i wrote to haptek and get in return their price list, so obviously
they sell it (it is 100$ not really expensive).
then i will order it and see what happens.

sorry , my fault , i often forget to close the bottom of my messages.
so
thanks anyway

I know this already, so unless you are able to produce lipsynched ogg files or phn files on the fly your information does not really help.
i want to be able to produce answer in several languages on-line.
the goal is to provide thousand of sentences by swapping synonyms on a model, so if you ask something, you never get exactly the same answer.
you can also introduce variation in sentence (like punctuation, silences etc...)

I am currently trying to bring together components to generate voice with lipsync for the haptek characters (web use).
I purchased the 12 voices from ATT (best ratio price/quality).
http://www.naturalvoices.att.com/demos/
The best would be loquendo, but i receive a phone call from the representative and he his asking 4000$ pervoice and per year ?!!.
Cepstral are bout same price than ATT but, in my opinion less good, but i could eventually purchase them also.
I will use a cheap and nice
product called ActiveTTS (http://www.guangmingsoft.net/activetts/ )
that lets you write a Text to wav files in almost any language.
The last step is the Hap Ogg factory that is supposed to convert the wav to ogg with lip sync.
does anybody has this converter so i can test it (before purchase) to make such this workflow is ok.
We could even share the effort and cost, so i can provide a simple form that anybody can use.
the form would include a field for text to convert, language needed, eventually the format (mp3, wav ogg, ogg+lips, lipsync only) and the voice (male/female)
and return the link the file, so you can have your character speaks.

my findings are the following.
You can have people putty for cheap and edit efficiently heads.
that is almost 80 percent of the job, since heads are the most important part of the body (because the motion of the mouth, eyes).
The problem is that haptek stop his effort there.
Ok they sell what they call half-body and some tools to (almost) manage them at in incredible high price. (3500$ for 2 half-body).
The bad news is even if you got the money to buy the kit, it is pretty useless, because body and half body are not made from haptek, but build from a 3d application (maya, 3ds, animation master), so you still need to spend a lot of $ and time to get one of these product work for you.
This is a pity, since  i realize after few search on google, that there is a lot of torso and body available on the web.
You just need to find a page displaying an haptek character, view the html code, and get the url for the .htr file and save it on your disk.
At the same time, with same method, you can capture enough .hap mood script to get a pretty complete library of behavior for moving the character. and if you need to create your own hap, you still can refer to haptek free guide, that list all the commands/query available.
This make the 3500$ for a bunch of utility and 2 basic torso looks even more ridiculous, since all of this can be found for free and should cover most of your needs.
Additionally , creating your own body or half body seems not a good idea, since you need to create all the parts (bones, joints, anchor points) in a way they stay compatible with the accessories or the movement files (.hap) , or else you could end up being forced to recreate everything by yourself, especially if you want a lot of different movements with arms and legs.

So currently the situation is pretty clear.
Buy People putty, hack as many standard characters and accessories from the web and limit you changes to "skin swapping" or "wig swapping"

To answer to you question, it seems you would need the utility from haptek that let you calculate the difference between a standard head and a custom one and apply this file to a standard torso.
I am afraid that still require the use of maya or 3dstudio.

Frankly the product is so good and powerful as it is, that it does not worth to bother of spending so much money or time to make small change.
Better to use this energy to implement it properly into a web page, master the TextToSpeech/emotion feature and create a nice stuff.

If you visited the pages from the companies working with haptek torso or body you will find they are all using the same standard characters.

the fact is i get the main page for login  and whatever i click i get this page only.
sorry but i was expecting something else than just a silly question.
If i post a request here explaining it does not work, it is not to hear "hey man, what is your problem, it works for me, it should work for you !"
Did you try the link above anyway ?
Thanks for the help anyway.

ok , i follow the link at the bottom of your answer and get a forum that looks like the one i was looking for.
I found too a post about head and torso, but it is not very helpfull.
It says cut and past skin from head to skin torso. Ok so where do i find skin torso ? I got many torso, but never found a skin for it, neither know how to extract them. cannot load a torso into people putty... still need help.

hello

I am trying to weld head to torso, but the answer published above (link to another post in another forum) is not available to me.
can somebody write the answer to me (here or in mail)

Regards