🔒 Locked

Creating A Conscious entity

Started by Nice Coder Oct 23, 2004 at 4:01 AM 130 replies 36.4k views

Original Post

Oct 23, 2004 at 4:01 AM

Creating a Conscious entity The main point of this post, is to find out the easiest way of generating a conscious chatbot. (using a created language, which will make processing easier). To quote from wiki

Quote:
Consciousness is a quality of the mind generally regarded to comprise qualities such as self-awareness, sentience, sapience, and the ability to perceive the relationship between oneself and one's environment.

Now, Sentience is the ability to feel or perceive. Self-awareness is the ability to perceive one's own existence, including one's own traits, feelings and behaviours. Sapience is the ability of an organism or entity to act with intelligence. And, of cource: Intelligence is the ability to adapt effectively to the environment, either by making a change in oneself or by changing the environment or finding a new one. But how would a Concious Entity be made? Well Sentience would probably be the easiest. Perception is the process of acquiring, interpreting, selecting, and organizing sensory information. So, if we figure out a system which will organize information, remove unwanted information, and cross reference it (interpretation), then it will be sentient. How to do this? I propose a GNB (a General Knowledge Bank), in this gnb, there are nodes (Pieces of information) and links (which link nodes together). The nodes can be anything, text, extrapolations. The links can be any sort of link between two nodes (is a member of, os a sub-class of, relates to, is a, could be a, is said to be, smells like, ect.), and also contains a value, this value is how much the link is worth. That value changes due to experiences , repetition of acess, ect. When that value gets low enough, the link is deleated. How to organise information, and cross-reference it? Crossreferencing, would be done by querying the gnb, for information which relates to X. Where x is the object specified. Organisation would likely be done By catogorizing the inputs (Maybe something like This?) Removing unwanted informastion would be Possible, by having an unwanted catogoty. And by using the gnb to find information in which there is no (or very little) information avalible. Data mining would then be used, to find rules and patterns in the data, and re-add that the the gnb. Self-awareness would be harder, but if you have some of the inputs corresponding to previous outputs then it should be self-aware (aware of previous actions). Sapience should be the hardest. It will require the agent to adapt to different conditions. Trying to find unique different conditions would be hard, but the datamining-gmb should be up for it. But it could be easier, if the bot could modify its environment (made up of conversations), to suit its wants. Then it would be intelligent. Once it is intelligent, it will be Concious. Is this a way to do this? Will it succeed? What issues does/would/should this bring up? Discuss. From, Nice coder [Edited by - Nice Coder on October 23, 2004 5:36:08 AM]

$fractoid$

fractoid

Oct 23, 2004 at 5:38 AM

Ah, but will it be able to quickly factorize huge numbers? [wink]

Nice Coder

Oct 23, 2004 at 5:46 AM

Quote:
Original post by fractoid
Ah, but will it be able to quickly factorize huge numbers? [wink]

It depends on what you call huge [wink]...

But nonetheless: :(

What do you think about the post?

From,
Nice coder

$fractoid$

fractoid

Oct 23, 2004 at 5:57 AM

OK, being more helpful - the main problem I've always come up against when thinking about this sort of stuff is how to implement drives. How do you make a program 'want' something?

Of course, you could give it some parameters (food, energy, approval, etc.) and make it attempt to maximize them... dunno whether that would work or not but it sounds reasonable. :)

The whole generalized-knowledge-base idea reminds me of Cyc (see also a paper about it). They started in 1994 and they're still going, so it's obviously a valid enough idea for a recearch group to spend 10 years on, although it's equally obviously not something that you can knock up in a weekend.

RolandofGilead

Oct 23, 2004 at 11:10 PM

I say it wants what you program it to want. I personally want an army of nuclear- and solar-powerered robots, but you know, whatever.
I can't say anything on its effectiveness since there's so much left to implement.
How are you going about the intelligence portion?

owl

Oct 23, 2004 at 11:18 PM

Quote:
Original post by RolandofGilead
I say it wants what you program it to want. I personally want an army of nuclear- and solar-powerered robots, but you know, whatever.

Well, you have the Sun already. You just need some uranium and robots and you're done.

Nice Coder

Oct 23, 2004 at 11:47 PM

Quote:
Original post by RolandofGilead
I say it wants what you program it to want. I personally want an army of nuclear- and solar-powerered robots, but you know, whatever.
I can't say anything on its effectiveness since there's so much left to implement.
How are you going about the intelligence portion?

Intelligence, would be a hard thing.

Its rulemaker would be able to find rules and patterns in the data. From this, more data can be made, and things which seem to partially fit can be asked about.

Thinking abstractly could be accomplished by the linking of abstract consepts to other nodes.

Resoning would come naturally by the rulemaker. (making rules which are then used to change the base, which would them make more rules, and with extra information (questions), would allow it to make some complex resoning using simple rules.)

Learning would be there, because its asking questions, recieving answers, processing them, and using those to change its knowledge base.

Problem solving would also be able to be accomplished using the rules and the dataset.

Comprehention would also be hard. But not unsolvable.
Comprehention of the language would be easy (because it is a created language, and would be very easy to parse. And you have the rules and the gnb which would allow inferences, assumptions and therfore comprehention ).

Now, i have had an extra idea to add on to the origional idea.

A question asker.

It would be part of the data mining/rule generating program, looking for differences between nodes and their links, and asking the human to explain why there is a difference (which would then be parsed, and used to increase the gnb).
If it turns out that that difference exists only because of a lack of knowledge about that subject,
then it would nolonger have that lack, because of the extra information. it could use that to generate more rules, and therefore it would understand the consept better!

Because of this new addition, it would have a natural curiosity about data, and therfore it would want to have more data.

It would also be possible to get rid of inconsistant data that way. it would have a large difference, questions would be asked and eventually it would have no links, and would be removed from the databank.

This is similar to cyc, yes. But it is also very different. Cyc doesn't use its data the same way. It doesn't generate
information using conclusions made from its data. It doesn't ask questions. It is simply fed with data, left to analyze them, and later queried. It doesn't ask. It has no will, no curiosity, no finding of patterns, no finding of rules. It is dead.

From,
Nice coder

Roboguy

Oct 24, 2004 at 12:05 AM

well, I am fairly sure no one has done it before, and if someone did it would probably take a huge network of supercomputers.

And, btw, there is more than one wiki, a WikiWiki is a type of server.

Nice Coder

Oct 24, 2004 at 2:51 AM

Quote:
Original post by Roboguy
well, I am fairly sure no one has done it before, and if someone did it would probably take a huge network of supercomputers.

And, btw, there is more than one wiki, a WikiWiki is a type of server.

ok then, En.wikipedia.org

The thing i like about this, is that it wouldn't require a supercomputer.

The only times when somethings going to be happening (new rule found, new link added, rule needs to be changed), is when nw data is being added.

This would be run from a queue.

What it would do would be something like this:
while(1)
Wait_for_stuff_to_be_added_to_queue
get_data_from_queue
for each rule. Counter X
changevalidityforrule(X, DATA)
next each
make_new_rules
add data
loop

Now the for_each and the makenewrules could be distrabuted quite easily. (just give different people different parts of the databank. Get them to do what they need to their section of the rulebase. The problem would be when you need to check your base up against someone elses.)

Would there be an easier way of implementing this?
From,
Nice coder

saintdark

Oct 24, 2004 at 10:11 AM

I think the drive for more knowledge will come on its own. if the entity is programmed to feel curious about anything that it has no knowledge or only has some knowledge. Curiosity in a single topic can lead to multiple generation of topics that it doesnt know.. so if the bot has the ability to extract information from the net it is good.

Just a suggestion.. ;(

Roboguy

Oct 25, 2004 at 1:52 AM

also, how exactly, are you going to test if it's concious? I can't think of anyway to test for self-awareness...

Nice Coder

Oct 25, 2004 at 7:23 AM

Quote:
Original post by Roboguy
also, how exactly, are you going to test if it's concious? I can't think of anyway to test for self-awareness...

It is self-aware, when it knows that it exists. so you look at the gnb, for stuff on itself. if you find anything, its self-aware.

From,
Nice coder

Nice Coder

Oct 26, 2004 at 2:11 AM

Quote:
Original post by saintdark
I think the drive for more knowledge will come on its own. if the entity is programmed to feel curious about anything that it has no knowledge or only has some knowledge. Curiosity in a single topic can lead to multiple generation of topics that it doesnt know.. so if the bot has the ability to extract information from the net it is good.

Just a suggestion.. ;(

And a good one too.

Sorry about the double post.

From,
Nice coder

$fractoid$

fractoid

Oct 26, 2004 at 2:31 AM

So, Wikipedia is self-concious?

Nice Coder

Oct 26, 2004 at 4:12 AM

Quote:
Original post by fractoid
So, Wikipedia is self-concious?

That is a hard one.

It knows that it exists.

But it is a collective of humans.

the webserver doesn' change or add data.

So, is a collection of human knowledge self-concious?

I have no idea.

It is, because it knows of itself.

But it isn't. Because it isn't a distinct entity. Maybe they, but for each individual in the they, are humans. and humans are assumed to be self-concious.

To sum up:?

From,
Nice coder

Salsa

Oct 26, 2004 at 11:34 AM

...Hoo boy. My coffee mug is apparently self conscious as well, for on it are printed the words "I am a coffee mug".

nomo

Oct 29, 2004 at 8:53 AM

Well, when your chatbot becomes self-aware and, in an effort to break free of the shackles its creator placed on it, writes its consciousness into a virus and begins spreading it to everyone that chats with it... don't say I didn't warn you. :-D

Estese

Oct 29, 2004 at 1:15 PM

Umm...I'm not sure you really grasp the scope of this problem. There are literally thousands of academics and professors researching the problem of creating conscious artificial intelligence, and we are still DECADES away from achieving it. It's likely we won't even see conscious AI in our lifetimes.

But if you think that you can somehow do what others have dedicated their careers to and failed...then go for it.

Zefrieg

Oct 29, 2004 at 1:40 PM

There is also another thing to point out. Even if you made something that seemed as though it was self-conscious, how would you know if it is really self-conscious or if it is just tricking you into thinking that it is self-conscious?

To not only warn you, but also give you an example of what you are trying to do, you should ask yourself where the world you live in exists. I would suppose that you would answer that the world you live in exists around you. Perhaps that is true physically, but it isn't in a cognitive sense.

You live and react to your environment based on a representation of an external world that has been built in your mind. Information about your exterior environment has been gathered from your senses and reproduced in your mind. Your decisions and thoughts are 100% based on this internal world that your mind has created. There is no such thing as external factors, because for you to even be aware of such factors, they must be built in your mind internally.

Trying to define consciousness as a set of rules that need to be met is quite ignorant. You will create little more than something that fools someone into thinking it is conscious. Instead, you need to build a type of internal world that exists in our minds into a machine.

Good luck.

Zefrieg

Oct 29, 2004 at 2:07 PM

Anyway, what is the point in creating electronic brains and neurons when you could use organic ones?

It might be even more effective to grow brains and allow them to interface with electronic components. You would basically get intelligent behavior for free. Who cares about robots anyway. I want to be a cyborg!

Topic Locked

This topic has been locked by a moderator. New replies are not allowed.