Dynamic, lifelike AI

[Enieublis McShlaggrmasker]

I've been thinking for a while about an AI that could adapt to almost any environment and duplicate itself throughout that environment like a super-virus or a semi-advanced life-form. I think it could be used for research since the adapted code could be opened and read.

So far this is only a thought experiment, but what seems to work is having three different systems in every AI program.


First, there is the curiosity system. It would store data from all of its inputs and outputs, and try to compress them into objects of data, functions about how those objects work or change given any change (even just change in time), clusters of objects and functions acting as single objects, functions describing how these clusters work given certain actions to/from other clusters, etc. If the environment around the AI always fits within the rules in this system's database, then this system "gets bored" and recommends exploring something that it knows less about.

Second, there is the self-preservation system, it would store data about the curiosity system's efficiency with its current structure and environment. If the AI was once in an environment or had a structure that was more efficient than where it is now, this system would look at recent or long-term events that might have caused this change. Then it would recommend going back to the better efficiency. It is basically designed to protect the curiosity system.

Third, there is the communication or empathy system. It could be considered an extension of the empathy system since it would store an object defining this AI and how it acts, then it would compare that object with other objects it finds, and create objects that consist of deviations from the self object. Then it can use those objects to recommend a course of action to help the other systems in this AI and the AI that it is communicating to.


Each system would consider each others action and add their own recommendation for or against it. Then the AI would perform the action with the highest recommendation, which could include modifying some parts of itself and creating other AIs.


Is this an unnecessarily complicated system? When would killing these AIs become unethical? Can anyone think of a better AI?

[Shokushu]

To get to the point you can call it an AI in the first place you've got to work out consciousness which implies that it is doing more than just giving a canned response to environmental stimulus like is suggested here.

There are a lot of interesting little systems we've found in the brain such as the piece that makes you feel like "you" are inside of your body (so the big that malfunctions during out of body experiences,) that we could replicate in AIs and just target synthetic versions of these to people or at least something other than the actual container of the AI. Same way you might understand that you shouldn't punch a hole in the wall of a submarine the AI could understand that it shouldn't beat up it's computational machinery yet not necessarily view that machinery as "itself."

When we know more about these various systems that come together to make a thinking entity it should be fairly easy to make advanced thinking machines without the ethical issues of creating what is essentially a mind.

[DXnobodyX]

Lets call it MAGI

[Ryu Kei Shou Kawazu]

Enieublis McShlaggrmasker

I've been thinking for a while about an AI that could adapt to almost any environment and duplicate itself throughout that environment like a super-virus or a semi-advanced life-form. I think it could be used for research since the adapted code could be opened and read.

So far this is only a thought experiment, but what seems to work is having three different systems in every AI program.


First, there is the curiosity system. It would store data from all of its inputs and outputs, and try to compress them into objects of data, functions about how those objects work or change given any change (even just change in time), clusters of objects and functions acting as single objects, functions describing how these clusters work given certain actions to/from other clusters, etc. If the environment around the AI always fits within the rules in this system's database, then this system "gets bored" and recommends exploring something that it knows less about.

Second, there is the self-preservation system, it would store data about the curiosity system's efficiency with its current structure and environment. If the AI was once in an environment or had a structure that was more efficient than where it is now, this system would look at recent or long-term events that might have caused this change. Then it would recommend going back to the better efficiency. It is basically designed to protect the curiosity system.

Third, there is the communication or empathy system. It could be considered an extension of the empathy system since it would store an object defining this AI and how it acts, then it would compare that object with other objects it finds, and create objects that consist of deviations from the self object. Then it can use those objects to recommend a course of action to help the other systems in this AI and the AI that it is communicating to.


Each system would consider each others action and add their own recommendation for or against it. Then the AI would perform the action with the highest recommendation, which could include modifying some parts of itself and creating other AIs.


Is this an unnecessarily complicated system? When would killing these AIs become unethical? Can anyone think of a better AI?

I think you accidently stumbled upon the three parts of conciousness the id ego and superego. But I do beleive for AI to be more efficient itd need a collective unconcious as well, like a higher AI in charge of helping lower AIs

[Ryu Kei Shou Kawazu]

Shokushu

To get to the point you can call it an AI in the first place you've got to work out consciousness which implies that it is doing more than just giving a canned response to environmental stimulus like is suggested here.

There are a lot of interesting little systems we've found in the brain such as the piece that makes you feel like "you" are inside of your body (so the big that malfunctions during out of body experiences,) that we could replicate in AIs and just target synthetic versions of these to people or at least something other than the actual container of the AI. Same way you might understand that you shouldn't punch a hole in the wall of a submarine the AI could understand that it shouldn't beat up it's computational machinery yet not necessarily view that machinery as "itself."

When we know more about these various systems that come together to make a thinking entity it should be fairly easy to make advanced thinking machines without the ethical issues of creating what is essentially a mind.

The left brain hemisphere side thats correlated to obe's is also correlated to dopplegangers, and once I had a dream a woman got stabbed there with a kitchen knife and started twitching/spazzing.

But I have a strong magnet Im thinking about putting to to the right hemispehre side of it to have an obe, sinc ethey say mri's can help the brain or something and how th enorth magnetic pole is actually healthy for the nerves, but thats very limited research I suppose.

[Enieublis McShlaggrmasker]

Shokushu

To get to the point you can call it an AI in the first place you've got to work out consciousness which implies that it is doing more than just giving a canned response to environmental stimulus like is suggested here.

Actually I don't believe that consciousness is necessary for Artificial Intelligence. AI is defined as "the theory and development of computer systems able to perform tasks normally requiring human intelligence"(The New Oxford Dictionary of English, 1998.). Those computer systems do not have to perform all such tasks including consciousness. (if conscious is a task requiring intelligence)

Shokushu

When we know more about these various systems that come together to make a thinking entity it should be fairly easy to make advanced thinking machines without the ethical issues of creating what is essentially a mind.

This contradicts what you said originally about an AI needing consciousness to be an AI, but... never mind. I agree that you cannot tell whether things are conscious until you know the properties that create the consciousness that you are looking for.

Ryu Kei Shou Kawazu

I do beleive for AI to be more efficient itd need a collective unconcious as well, like a higher AI in charge of helping lower AIs

Interesting, do you mean a massive AI that works for the betterment of all other AIs. If so, I think anything it would do would happen anyway because of the empathy system. However, an AI encompassing all others and giving recommendations to different sub-AI's could speed things up in some situations. Instead of one AI sending a recommendation to the next and so on, a massive AI could, for example, notice two or more AIs working towards similar things and team them up.

DXnobodyX

Lets call it MAGI

No.

I've actually never seen that anime or manga. Anyway, I couldn't find what MAGI stood for, and I like my acronym better: Curious Living Artificial Intelligence, CLAI.

[Shokushu]

Ryu Kei Shou Kawazu

Shokushu

To get to the point you can call it an AI in the first place you've got to work out consciousness which implies that it is doing more than just giving a canned response to environmental stimulus like is suggested here.

There are a lot of interesting little systems we've found in the brain such as the piece that makes you feel like "you" are inside of your body (so the big that malfunctions during out of body experiences,) that we could replicate in AIs and just target synthetic versions of these to people or at least something other than the actual container of the AI. Same way you might understand that you shouldn't punch a hole in the wall of a submarine the AI could understand that it shouldn't beat up it's computational machinery yet not necessarily view that machinery as "itself."

When we know more about these various systems that come together to make a thinking entity it should be fairly easy to make advanced thinking machines without the ethical issues of creating what is essentially a mind.

The left brain hemisphere side thats correlated to obe's is also correlated to dopplegangers, and once I had a dream a woman got stabbed there with a kitchen knife and started twitching/spazzing.

But I have a strong magnet Im thinking about putting to to the right hemispehre side of it to have an obe, sinc ethey say mri's can help the brain or something and how th enorth magnetic pole is actually healthy for the nerves, but thats very limited research I suppose.

Actually I think you'd need a more precise magnetic field to accomplish that.

Enieublis McShlaggrmasker

Shokushu

To get to the point you can call it an AI in the first place you've got to work out consciousness which implies that it is doing more than just giving a canned response to environmental stimulus like is suggested here.

Actually I don't believe that consciousness is necessary for Artificial Intelligence. AI is defined as "the theory and development of computer systems able to perform tasks normally requiring human intelligence"(The New Oxford Dictionary of English, 1998.). Those computer systems do not have to perform all such tasks including consciousness. (if conscious is a task requiring intelligence)

I didn't say that AI's need it, just that you need to know how consciousness works to make an AI. Sort of set it as a milestone in understanding how humans think, as it would be difficult to grasp enough about our minds without having delved into that particular question. It's rather central to the issue so to speak, though not necessarily something we'd want to take on the burden of being creators of.

Plus it's an easy goal to understand sort of what the endpoint looks like and what hurdles we've got to clear to get closer to it.

[Enieublis McShlaggrmasker]

Shokushu

Enieublis McShlaggrmasker

Shokushu

To get to the point you can call it an AI in the first place you've got to work out consciousness which implies that it is doing more than just giving a canned response to environmental stimulus like is suggested here.

Actually I don't believe that consciousness is necessary for Artificial Intelligence. AI is defined as "the theory and development of computer systems able to perform tasks normally requiring human intelligence"(The New Oxford Dictionary of English, 1998.). Those computer systems do not have to perform all such tasks including consciousness. (if conscious is a task requiring intelligence)

I didn't say that AI's need it, just that you need to know how consciousness works to make an AI. Sort of set it as a milestone in understanding how humans think, as it would be difficult to grasp enough about our minds without having delved into that particular question. It's rather central to the issue so to speak, though not necessarily something we'd want to take on the burden of being creators of.

Plus it's an easy goal to understand sort of what the endpoint looks like and what hurdles we've got to clear to get closer to it.

OK, but you don't need to know how consciousness works to make an AI, you just need to know how people solve problems and create an intelligent agent that mimics that problem solving procedure. I'm just adding a little to the definition I found originally.

Consciousness may be related to the ethics issue, but I'm really not sure how related it is to Artificial Intelligence. I'm also not sure whether or not we would need to mimic conscious entities to find out what consciousness is, or if that would even help.

In fact, since consciousness is hard to define and since I have no idea how close we are to understanding it, I think a better basis for determining ethics is whether something is alive. Oxford dictionary defines life as: "the condition that distinguishes animals and plants from inorganic matter, including the capacity for growth, reproduction, functional activity, and continual change preceding death". The AI I described would have all of those capacities.

[DXnobodyX]

Enieublis McShlaggrmasker

Shokushu

To get to the point you can call it an AI in the first place you've got to work out consciousness which implies that it is doing more than just giving a canned response to environmental stimulus like is suggested here.

Actually I don't believe that consciousness is necessary for Artificial Intelligence. AI is defined as "the theory and development of computer systems able to perform tasks normally requiring human intelligence"(The New Oxford Dictionary of English, 1998.). Those computer systems do not have to perform all such tasks including consciousness. (if conscious is a task requiring intelligence)

Shokushu

When we know more about these various systems that come together to make a thinking entity it should be fairly easy to make advanced thinking machines without the ethical issues of creating what is essentially a mind.

This contradicts what you said originally about an AI needing consciousness to be an AI, but... never mind. I agree that you cannot tell whether things are conscious until you know the properties that create the consciousness that you are looking for.

Ryu Kei Shou Kawazu

I do beleive for AI to be more efficient itd need a collective unconcious as well, like a higher AI in charge of helping lower AIs

Interesting, do you mean a massive AI that works for the betterment of all other AIs. If so, I think anything it would do would happen anyway because of the empathy system. However, an AI encompassing all others and giving recommendations to different sub-AI's could speed things up in some situations. Instead of one AI sending a recommendation to the next and so on, a massive AI could, for example, notice two or more AIs working towards similar things and team them up.

DXnobodyX

Lets call it MAGI

No.

I've actually never seen that anime or manga. Anyway, I couldn't find what MAGI stood for, and I like my acronym better: Curious Living Artificial Intelligence, CLAI.

The point was its already been thought of before.

[Enieublis McShlaggrmasker]

DXnobodyX

The point was its already been thought of before.

Then the point is wrong. Just because my AI and another AI have three parts doesn't mean they're exactly the same. If you can link to a page that describes it in more detail then I might agree with you. But so far the only information I found on that fictional computer that actually means anything is that it has three parts.

[DXnobodyX]

Enieublis McShlaggrmasker

DXnobodyX

The point was its already been thought of before.

Then the point is wrong. Just because my AI and another AI have three parts doesn't mean they're exactly the same. If you can link to a page that describes it in more detail then I might agree with you. But so far the only information I found on that fictional computer that actually means anything is that it has three parts.

curiosity - scientist
mother - communication/empathy
self preservation - women

Better that you just watch the episode
http://www.dubbedepisodes.com/neon-genesis-evangelion-episode-13-english-dub/

[Ryu Kei Shou Kawazu]

Ryu Kei Shou Kawazu

Shokushu

To get to the point you can call it an AI in the first place you've got to work out consciousness which implies that it is doing more than just giving a canned response to environmental stimulus like is suggested here.

There are a lot of interesting little systems we've found in the brain such as the piece that makes you feel like "you" are inside of your body (so the big that malfunctions during out of body experiences,) that we could replicate in AIs and just target synthetic versions of these to people or at least something other than the actual container of the AI. Same way you might understand that you shouldn't punch a hole in the wall of a submarine the AI could understand that it shouldn't beat up it's computational machinery yet not necessarily view that machinery as "itself."

When we know more about these various systems that come together to make a thinking entity it should be fairly easy to make advanced thinking machines without the ethical issues of creating what is essentially a mind.

The left brain hemisphere side thats correlated to obe's is also correlated to dopplegangers, and once I had a dream a woman got stabbed there with a kitchen knife and started twitching/spazzing.

But I have a strong magnet Im thinking about putting to to the right hemispehre side of it to have an obe, sinc ethey say mri's can help the brain or something and how th enorth magnetic pole is actually healthy for the nerves, but thats very limited research I suppose.

Actually I think you'd need a more precise magnetic field to accomplish that. More like a cylindrical pyramidal or spike-like field rather than sphereicallish because it hits too much region sinprecisely without significant depth perhaps? Well my magnet is sort of strong, though not comparatively to electrical ones and such I would think. If I put a fridge magnet on my head thatd be a little ridiculous lol.

[Ryu Kei Shou Kawazu]

DXnobodyX

Enieublis McShlaggrmasker

DXnobodyX

The point was its already been thought of before.

Then the point is wrong. Just because my AI and another AI have three parts doesn't mean they're exactly the same. If you can link to a page that describes it in more detail then I might agree with you. But so far the only information I found on that fictional computer that actually means anything is that it has three parts.

curiosity - scientist
mother - communication/empathy
self preservation - women

Better that you just watch the episode
http://www.dubbedepisodes.com/neon-genesis-evangelion-episode-13-english-dub/

Dont show him that lolll.
Its messed up.
But yeah I understand the three parts, its in alot of psychological theories and such. Id ego superego, concious unconcious subconcious collective-unconcious lol.

[DXnobodyX]

Ryu Kei Shou Kawazu

DXnobodyX

Enieublis McShlaggrmasker

DXnobodyX

The point was its already been thought of before.

Then the point is wrong. Just because my AI and another AI have three parts doesn't mean they're exactly the same. If you can link to a page that describes it in more detail then I might agree with you. But so far the only information I found on that fictional computer that actually means anything is that it has three parts.

curiosity - scientist
mother - communication/empathy
self preservation - women

Better that you just watch the episode
http://www.dubbedepisodes.com/neon-genesis-evangelion-episode-13-english-dub/

Dont show him that lolll.
Its messed up.
But yeah I understand the three parts, its in alot of psychological theories and such. Id ego superego, concious unconcious subconcious collective-unconcious lol.

Im not advocating the idea or anything, just pointed out that its already been done.

[Enieublis McShlaggrmasker]

DXnobodyX

Im not advocating the idea or anything, just pointed out that its already been done.

But... they're completely different. My machine isn't made out of human brains or whatever that thing was. I think the way I summarized my AI just happened to be similar in some way to the story of biblical magi, which that computer was based off of.