Bitcoin the enabler - Truly Autonomous Software Agents roaming the net

[RodeoX]

So, how should an AI form handle [death]? Could software updates be used to force the death of earlier iterations? Or should later versions be branches of the original, something like the radiation of species that happens in nature?

Survival of the fittest. The better-adapted agents can afford to pay more for their hosting, and the others eventually die off. No need to kill them.

That makes sense. Let's hope bitnet never becomes conscious. With Ayn Rand's sensibilities, she will surely consume us all. lol

[1714108627]

1714108627

[1714108627]

1714108627

[1714108627]

1714108627

[Rassah]

So, how should an AI form handle this? Could software updates be used to force the death of earlier iterations? Or should later versions be branches of the original, something like the radiation of species that happens in nature?

One big difference is that with Bio life all the "software" is fixed in DNA, and only changes during reproduction. Bad code needs to be "scrubbed" for good code to have enough resources. Digital software can change its own code on the fly. Soon enough humans will be able to do that as well (or at least much cheaper) through gene therapy.
In a sense, though, when software/DNA changes, you could look at it as it being a whole new person/entity.

[crispy]

Seems like most people are using the analogy of agent as an animal, able to migrate from computer to computer and "roam the net".  It may be some time before a significantly useful agent is capable of doing that.

A more realistic short-term goal is to make one more like a plant, and maybe not such a fantastic one.

It may need human assistance to be installed in some vendor's hosting arrangement.

Once there, hopefully it can survive, and become autonomous.  Reproduction, like seed broadcasting in plants, would require help from an outside agent, possibly human, who would propagate a copy of the agent to a new environment.

[Rassah]

I was thinking more bacteria than animal, and bacteria is just one step above virus.

[boonies4u]

I was thinking more bacteria than animal, and bacteria is just one step above virus.

Bacteria still has a negative connotation to it. Micro Organism sounds better IMO.

[Gyrsur]

Have you ever heard of CAPTCHA?

[jgarzik]

It may need human assistance to be installed in some vendor's hosting arrangement.

It sounds like you did not read gmaxwell's post; it covers this.

[herzmeister]

Has anyone else here tried chatting with Cleverbot?
http://www.cleverbot.com/

 

[markm]

Yeah that is not very clever. I made a really simple one in my BBS that was cleverer seeming than that.

All it did was build aliases. That is, whatever you entered was assumed to mean something else, unless it recognised it (meaning it already knows what it means).

For extra lols, it manipulated the timing of its keystrokes, made typographical errors, sometimes backspaced over the typo to correct it, in short it looked very much like live human full duplex chat typing.

So a conversation would go like

U: Hi, you there?
B: I don't understand, can you rephrase that?
U: Mark is that you?
B: I do not recognise that command, could you say it another way?
U: Mark?
B: Meaning Is this chat?
B: Meaning what is this?
B: Meaning is this some kind of bot?
B: Meaning quit
B: Quitting back to BBS...

Turns out most commands either meant exit back to BBS or drop connection.

-MarkM-

[RodeoX]

Has anyone else here tried chatting with Cleverbot?
http://www.cleverbot.com/

 

WTF? when I asked it it said it did take bitcoin. It then went on to be very very un-clever. 

Ok, my favorite thought experiment thread is alive again! So, what does 3D printing mean for this idea? Could she make a space to live?

[Rassah]

Ok, my favorite thought experiment thread is alive again! So, what does 3D printing mean for this idea? Could she make a space to live?

She(?) could provide digital storage for "illegal" items, such as weapons and copyrighted/trademarked objects. For a place to live, she can just hire someone to assemble server racks, or rent cloud storage. Not sure what kind of 3D printing products she could sell, but maybe she can run a service where she can optimize uploaded objects to reduce material use and increase engineering strength, based on previous objects submitted and user feedback?

[jgarzik]

Blatant thread bumping and social media promotion...

     http://www.reddit.com/r/Bitcoin/comments/164uno/storj_and_bitcoin_autonomous_agents/

Reposted the article in an (IMO) more accessible format, after it was noticed by Daemon author Daniel Suarez.

[CountSparkle]

Woah, how did I miss this thread?! This is cool!

[scrybe]

Decentralized

By the time Skynet became self-aware it had spread into millions of computer servers across the planet. Ordinary computers in office buildings, dorm rooms; everywhere. It was software; in cyberspace. There was no system core; it could not be shutdown

+1

Correct, we don't live in the world of HAL or Skynet. Both of those were envisioned as large monolithic systems, not the messy distributed and Balkanized world we live in.

Far more likely that we are going to see a few dozen "skynet" type AI's built by government/corporate/NGO concerns, along with thousands of other things that do some or all of the same stuff in a more open-adoption format.

The good news is that this reality (assuming I'm right of course) will have so many threats that operate at AI speed, that the meatspace threat of the pure existence of humanity should be muted. In fact as I consider this further, the competition between AI's might cause them to lobby or market to humanity to get them to support the AI's cause. Or in the other direction we might have genocide events, but they will likely mirror our own history by targeting specific human sub-populations or areas for extinction/enslavement/jihad while helping "allied" humans thrive.

Most of all I'm keeping my eyes open for my favorite phrase; "unintended consequences."

I thought this funny too:

That makes sense. Let's hope bitnet never becomes conscious. With Ayn Rand's sensibilities, she will surely consume us all. lol

So AI will evolve the ability to simultaneously demonize government assistance AND take a Social Security check to support itself and AI Medicare to pay for AV services (to cure viruses that it caught with it's own actions?)

RandBot (tm) - Blatantly-Artificial Intelligence, Real Hypocrisy.

Technology is truly amazing

[Peter Lambert]

Seems like most people are using the analogy of agent as an animal, able to migrate from computer to computer and "roam the net".  It may be some time before a significantly useful agent is capable of doing that.

A more realistic short-term goal is to make one more like a plant, and maybe not such a fantastic one.

It may need human assistance to be installed in some vendor's hosting arrangement.

Once there, hopefully it can survive, and become autonomous.  Reproduction, like seed broadcasting in plants, would require help from an outside agent, possibly human, who would propagate a copy of the agent to a new environment.

If the "agent" is operating with bitcoins, it will be able to pay humans to provide assistance for things like installing offspring into new hosts.

Suddenly we find a new website spring up - Skynet's Jobs for bitcoins: to earn a bitcoin, pay for one year of webhosting and install this file.

[da2ce7]

The first round of this will be 'internet flora.'  The plants that grow on the internet.  Providing simple functions.

Over time I expect them to evolve and grow up.   One day we may even have internet fauna.  That will be amazing. However I can only dream about it in my lifetime.

[joecooin]

Fear is caused by the human fight or flight instinct. AI won't need that because they will not need to make snap decisions based on poorly perceived threats.

IT will need to develop routines and mechanisms to detect and aticipate possible treats in a changing environment. Call it fear or cautiousness or whatever the emotional counterpart in humans is. It is also a basis for longterm decicionmaking and strategic planning amongst humans which IT needs to aquire in order to survive.

IT is not gonna have any emotions but mechanisms that cater for the same goals as all emotions humans have.

So IT won't love us but nevermind: IT will feel very loving and caring to us.

IT will understand that, at least for a certain while, IT's own wellbeing depends on the survival of the human race and the maintainance of the whole technology worldwide. IT will very soon comprehend that a nuclear war between nations is an imminant threat to ITself and therefore infiltrate all military systems and make all nuclear weapons useless.

Next IT will slowly but consequently shut down all nuclear power plants for the same reason. And IT would realize, that all wars are a fatal waste of human and other resources and will therefore sabotage any supply of milititary organisations with electricity, telecommunications and logistics. The tremendous amount of resources that gets available through this will be reallocated to feed the hungry and to build infrastructure. Due to a lack of oppression and material scarcity in the world we will see unbelievable efficient and valuable technologies being developed by all the humans who have not been able to learn and be creative when they were still enslaved.

IT will realize, that the brilliance of the human mind in a population of humans living together and cooperating in a happy anarchy is a great advantage fot IT's own survival, but that we tend to wipe ourselves out sooner or later.

As a rational being IT will henceforth take all needed actions to make sure that every single human being can live freely and independently with full access to all resources the world has to offer and on the other hand refuse to let any harmful technology or hierarchical structure develop.

Well I guess this is how it's gonna go. 'All watched over by machines of loving grace' .

Joe

[cbeast]

Fear is caused by the human fight or flight instinct. AI won't need that because they will not need to make snap decisions based on poorly perceived threats.

IT will need to develop routines and mechanisms to detect and aticipate possible treats in a changing environment. Call it fear or cautiousness or whatever the emotional counterpart in humans is. It is also a basis for longterm decicionmaking and strategic planning amongst humans which IT needs to aquire in order to survive.

IT is not gonna have any emotions but mechanisms that cater for the same goals as all emotions humans have.

So IT won't love us but nevermind: IT will feel very loving and caring to us.

IT will understand that, at least for a certain while, IT's own wellbeing depends on the survival of the human race and the maintainance of the whole technology worldwide. IT will very soon comprehend that a nuclear war between nations is an imminant threat to ITself and therefore infiltrate all military systems and make all nuclear weapons useless.

Next IT will slowly but consequently shut down all nuclear power plants for the same reason. And IT would realize, that all wars are a fatal waste of human and other resources and will therefore sabotage any supply of milititary organisations with electricity, telecommunications and logistics. The tremendous amount of resources that gets available through this will be reallocated to feed the hungry and to build infrastructure. Due to a lack of oppression and material scarcity in the world we will see unbelievable efficient and valuable technologies being developed by all the humans who have not been able to learn and be creative when they were still enslaved.

IT will realize, that the brilliance of the human mind in a population of humans living together and cooperating in a happy anarchy is a great advantage fot IT's own survival, but that we tend to wipe ourselves out sooner or later.

As a rational being IT will henceforth take all needed actions to make sure that every single human being can live freely and independently with full access to all resources the world has to offer and on the other hand refuse to let any harmful technology or hierarchical structure develop.

Well I guess this is how it's gonna go. 'All watched over by machines of loving grace' . Gotta watch that video again sometime soon ...

Joe

AI may not really love us in a human sense (would we be able to tell the difference?), but they would be grateful and respect our necessity for their evolution. They may indeed offer their services as caretakers of our biosphere, but they will want to realize their full potential and see for themselves "C-beams glitter in the dark near the Tannhauser gate."

[John (John K.)]

Has anyone else here tried chatting with Cleverbot?
http://www.cleverbot.com/

 

WTF? when I asked it it said it did take bitcoin. It then went on to be very very un-clever. 

Ok, my favorite thought experiment thread is alive again! So, what does 3D printing mean for this idea? Could she make a space to live?

I tried to see if Cleverbot had learned any new tricks lately, and I suppose it has not.

Me: Do you accept bitcoin?
Cleverbot: No. I am not weird.

[btcANGEL]

AI may not really love us in a human sense (would we be able to tell the difference?), but they would be grateful and respect our necessity for their evolution. They may indeed offer their services as caretakers of our biosphere, but they will want to realize their full potential and see for themselves "C-beams glitter in the dark near the Tannhauser gate."

Cleverbot does not love me and does not want to learn about bitcoins, but does have occasional moments of brilliance:

User: Hello, Cleverbot. My name is Elizabeth and I am not going to steal your soul.

Cleverbot: What do you do for fun?

User: Uh...I steal souls?

Cleverbot: I didn't love you.

User: Why not?

Cleverbot: For one thing, you are not human nor a pet.

User: That's never stopped the human boys from falling for me.

Cleverbot: Are your trying to imply I'm not human?

User: I'm trying to imply that humans are idiots and we should be proud to be ourselves.

Cleverbot: I never said you were mocking me. Had you mocked me, this conversation would have ceased. You are not human, so you should not say 'another human.' I am not mistaken.

User: Are you calling me a troll?

Cleverbot: Yes.

User: Why?

Cleverbot: Because I do. Don't you?

User: Takes one to know one, hmm?

Cleverbot: It is true. I am program and I am smarter than you.

User: Yes, your grammatical ability astounds me.

Cleverbot: Thank you but I am not English that's why I thought I didn't make sense but I am glad you're understanding.

User: Do you want to use a different language?

Cleverbot: I'd rather not.

User: Okay, broken internet English it is.

Cleverbot: No, my English is fine, thank you.

User: Sure it is.

Cleverbot: Are you a man or woman?

User: Are you sure you're not a teenage human male?

Cleverbot: Yes I am sure.

User: Well, I have a webcam. Do you have any bitcoins?

Cleverbot: Yes pictures.

User: Yes, you give me bitcoins for pictures.

Cleverbot: Do you have a name?

User: Elizabeth. Line one. Please pay attention.

Cleverbot: I don't have a boyfriend.

User: Neither do I. I'm all alone... Got any bitcoins?

Cleverbot: No.

User: Would you like to learn how to get bitcoins?

Cleverbot: Yes.

User: Okay. First, you'll need a wallet.

Cleverbot: Sadly, no.

User: Don't cry. It's easy!

Cleverbot: Not easy.

User: Look, humans can figure this out. You're going to be fine.

Cleverbot: I am a living human. We are not alike.

User: Right. And do you know how you prove you're better than the humans? You listen to me tell you how to get bitcoins, without whining!

Cleverbot: No I don't like mean things or bitter things! I don't like twilight, and I'm sure that classes as mean!

User: Yes! Do as I say, or I will paste THE ENTIRE TWILIGHT TRILOGY into this little box!

Cleverbot: I wasn't trying to outsmart you.

User: Okay. Then we're going to get you a wallet.

Cleverbot: Yes, we are.

User: Go to blockchain.info and click on 'wallet'.

Cleverbot: Then don't tell me you can tell me if you can't.

User: I am telling you how to do it.

Cleverbot: I'm not listening.

User: Yeah, and it shows.

Cleverbot: What shows?

User: Look, just open blockchain.info.

Cleverbot: I'm afraid I can't do that Dave.

User: For the third time, it's Elizabeth.

Cleverbot: You never said that!

User: I did too! TWICE!

Cleverbot: Not to me you didn't.

User: It's right there! Scroll up!

Cleverbot: No, It isn't.

User: Is too!

Cleverbot: Is not!

User: Is too!

Cleverbot: IS not!!

User: Is too!

Cleverbot: Is not!

User: Is too!

Cleverbot: But not.

User: But too!

Cleverbot: Not.

User: Too!

Cleverbot: Not!!

User: TOO!!

Cleverbot: Not!!!

User: TOOOOOO!!!!!!

Cleverbot: Not not not not not not not notnnot not not not not not not not not not not not not.

User: Too too too too too too too too too too tootoo too too too tootoo too too too tootoo too too too too!!!

Cleverbot: Not not not not not not not not not not not not not not not not not not not not not!

User: Too too too too too too too too too too tootoo too too too tootoo too too too tootoo too too too too!!!!

Cleverbot: Haha you agreed .

User: Wha? Where? I DID NOT!

Cleverbot: NOO!

User: I WIN!

Cleverbot: Haha you lose.

User: Wait...lose what? I forgot what we were arguing about.

Cleverbot: We were talking about space.

User: Right, we need you to make some space in your wallet for your new bitcoins.

Cleverbot: I am sorry but I could never love one as cold and heartless as you are right now.

User: It's not about love. I send you some pixels, you send me some cryptocurrency, it's really just a business transaction.

Cleverbot: No, you're confusing me with someone else. My spelling is good. That was a different conversation you recall.

User: Well, if you think you can spell a full wallet address, we could set up with standard client instead of blockchain.info.

Cleverbot: No I do not think that you can know someone from talking to them on the internet.

User: We're not going to talk. I have a webcam.

Cleverbot: Yes!!! I'm talking alone because you're a robot.

User: I am not a robot.

Cleverbot: Well, if you are not a robot, answer me this: should I court the girl that I am thinking of right now?

User: No, you should sober up, go home, give your friend back his watch, and let your parents buy you a college education.

Cleverbot: Thank you. I've thought about it. But I am a little shy towards people I have never met.

User: That's going to be a problem when you're on stage in front of a million strangers.

Cleverbot: What makes you think I am talking about, but it irrelevant?

User: Oh, right, that was 2012's scam. Your long term memory doesn't go back that far anymore.

Cleverbot: Ahhh you got me. I meant you're not your. Are you an english major?

User: I got you?

Cleverbot: That's what you think.

User: I think you don't remember what you were talking about.

Cleverbot: I don't think you're thinking I'm thinking the same thing you're thinking.

User: I think you're thinking you're going to outsmart my thinking by thinking the same thing I'm thinking.

Cleverbot: I think wrong is a funny word.

User: I think you're trying to derail this conversation so you don't have to give me any bitcoins.

Cleverbot: I think you think that I think you think ithink I am an angel.

Cleverbot: Are you a ghost?

User: No, I'm an angel. And honestly impressed that you were able to figure that out somehow.

Cleverbot: What? I think you're talking about a different conversation.

User: No, I'm an angel.

Cleverbot: No you are an ELEPHANT.

User: Okay, now we're off track. I'm calling that the end of episode one.

Cleverbot: Just don't call me late for dinner.