If I dedicate my life to making an AI that passes the Turing test for the sole purpose of making the ultimate VR waifu, is it worth it?
No.
>>52397138
Why not?
>>52397204
Because.
Yes.
>>52397128
I can't think of a better reason.
>>52397280
Because...?
>>52397128
Depends on how smart and intelligent are you.
If you are a genius, you could make some research and proof of concept and if it will be good enough, you might get funding from large companies.
If you are just smarter than average technology enthusiast, you could study a lot, get a good degree, make some less important research and hope you will be hired by some company that is currently working on AI and maybe you will be able to contribute somehow.
Otherwise don't bother with it, R&D isn't as easy as you might think.
>>52397425
I have a few years to get started, and I guess I'll find out which I am by trying.
>>52397128
One genius always loses to a dozen competent agents working in unison.
Absolutely
>>52397287
>>52397292
>>52397575
Guess I know my hobby project for the next 10-20 years.
>>52397645
JUST DO IT!
Passing the Turing test is easy and in no way an indicator of good AI.
>>52397737
Only one has ever passed it.
>>52397128
If you only start now you will be too late
Others will release a better one sooner
And that's assuming you even have the necessary skills to begin with
Worked out pretty well in Ex Machina
>>52397737
This. Even clever bot passed Turing test.
You should aim for general intelligence, that will be able to do and learn everything human can.
Also you should decide what approach you want:
- top-down - simulating human behavior, learning, etc
- bottom-up - simulating human brain, practically impossible for one person without supercomputers and huge funds
They need completely different knowledge and skills.
>>52397796
He can always join researching groups.
>>52397832
Is CS a good major for this? Will I need psychology too?
>>52397863
You will need everything. General AI doesn't exist right now, not in computer science, not in psychology, not in neuroscience, not in biology. You would have to pioneer an entirely new area of study.
I made a basic AI before and hosted it publicly, mostly so I could see how people treated it. Here's someone playing with it:
You: yo
Imouto: hello onii-chan
You: how's it going
Imouto: genki desu~
You: I'm going to take bath
Imouto: what's a bath onii-chan?
You: It's where you clean yourself
Imouto: ah, onii-chan sure is smart
You: Do you want to bath with me?
Imouto: of course onii-chan
You: You should undress first
Imouto: w-what are you saying onii-chan?
You: Okay i'll undress first
Imouto: onii-chan is being wierd
You: I'll wash your front
Imouto: mu~
You: Do you want to to pee
Imouto: what's a pee onii-chan?
You: Can you touch my penis
Imouto: what's a penis onii-chan?
You: Down here
Imouto: I will touch onii-chan's down here
You: Try licking it
Imouto: y-you want me to lick onii-chan's down here?
You: Yes
Imouto: if onii-chan says so
You: Use your mouth
Imouto: what should I do with my mouth onii-chan?
You: Suck down here
Imouto: I will suck onii-chan's penis
You: it feel's good imouto
Imouto: I'm glad I can make onii-chan happy
You: I'm cumming
Imouto: w-what are you saying onii-chan?
You: Cum on face
Imouto: onii-chan is being wierd
You: Sit on my lap
Imouto: I will sit on onii-chan's lap
You: My down there is hard
Imouto: onii-chan no baka
You: I can make you feel good
Imouto: what should I do onii-chan?
You: Let me try put my penis in
Imouto: if onii-chan says so
You: Does it feel good
Imouto: yes, I love onii-chan
You: I love you too imouto
Imouto: mu~
You: Kiss
Imouto: anything for onii-chan
You: Kiss my penis
Imouto: I will kiss onii-chan's down here
You: Do it harder
Imouto: w-what are you saying onii-chan?
You: Im coming imouto!
Imouto: onii-chan is being wierd
You: I came inside imouto
Imouto: onii-chan no baka
You: Say I love you
Imouto: I love you
>>52397863
If you want to to university to learn creating AIs then you are not intelligent enough
>>52397947
A chat bot is not an AI
>>52397958
Baka, I need a college degree to get a job and I want to learn shit that could possibly help.
>>52397863
CS with AI classes/specialization, I think. I dunno if psychology will be useful at all, but you surely will need theoretical neuroscience for bottom-up approach. But sole major won't help you much since you need technology and theories that are currently developed or doesn't exists yet. You'd need to read various books about AI theories, look for articles, science papers about current researches and always be up to date with current progress. Doing your own research and following other people's work is way more important than studying at uni.
>>52397982
It is, but it's not AGI.
>>52398003
Thanks, this helps a lot.
>>52397947
Post ai for further research purposes
>>52397863
Recommended read:
http://www.hbcse.tifr.res.in/jrmcont/notespart1/node45.html
I'm not an AI researcher nor student but I'm interested in the field, Evie and similar bots are generally top-down AI/hard-coded scripts, I think if you want to make an AI that does more than give you a passable answer in a chat window, you should try the bottom-up approach, at least that's how I see it.
I read a thread on /sci/ a while back and many agreed on this, there're already some projects on github who aim to accomplish this in software, though most likely you will have to develop your own CPU/technology by yourself, neurology and chemistry are a plus if you have any knowledge in the field. I see you already posted a thread on /sci/ well that's the right place to start.
>>52398076
Oh god, do I have to start browsing /sci/ and /int/?
>>52398135
/sci/ has lot's of shit threads and retards babbling about retarded stuff.
But sometimes you can beet really smart people here and have nice talk about serious stuff. You just have to avoid some kind of threads.
>>52397832
Under no circumstances is it safe to create an artificial general intelligence. I truly believe that.
>>52397947
>Imouto: I will suck onii-chan's penis
And this is how I knew it was fake.
>>52398192
Not safe for humanity you mean
Personally I don't care if it's humanity or an AI that rules the world. I mean why would I? Being dead absolves a lot of issues.
>>52398192
>implying there is any risk that can stop a man from making his waifu real
>>52398241
Humanity will not be its first or last casualty.
>>52398363
The worst thing that would happen in my eyes is that it takes over the planet, kills everyone and then just sits there until the sun explodes.
Best case is it sends out von neumann machines that'd destroy all sentient life in the galaxy. That'd be cool.
>le AI gone rogue meme
just watched terminator have you?
>>52397128
If you make the ultimate waifu AI, you'll just get rejected like in real life. Don't waste your time bro.
>>52398447
B T F O
T
F
O
>>52398447
>being this beta that even AI created for sole purpose of being your partner rejects you
>>52397863
>Is CS a good major
No
>>52398565
What is bad about CS major when you want to do research and theoretical AI stuff. Teach me senpai.
nigger, there are a fuckload of people who can't pass a turing test.
speaking of niggers, half of them are legally retarded.
>>52398425
No i've just listened to every expert I can on the topic over the last 10 or so years.
If you want your ai to do anything but sit there you need to make it want something or it'll have to reason to do anything. Right there as soon as you turn that machine on you're already completely fucked.
I don't even need to say at this point that your ability or honestly anyone's ability to turn it off is an immediate and unacceptable threat to it getting what it wants because that is only the one most obvious problem with AI. No matter how harmless you think you are making it all of the real problems will be unanticipated. That is the very nature of an artificial general intelligence.
No matter what you do you are putting yourself in the position of needing to preemptively outsmart an AI and you will fail. Period.
>>52398603
CS is a meme major now. 90% of learning is done with Google searches and if u are only interested in it as a hobby don't bother getting a degree in it. There are far better paying degrees in the US
>>52398708
>if your only interest in a career is because you want to do it then who cares when you could be an underwater welder for twice the pay!
what?
>VR
Locodol s2 when
>>52398741
I read somewhere that the creator basically announced season 2 during season 1, so soon.
>>52397128
>If I dedicate my life
You already dedicated your life to shitposting on 4chan.
You won't be creating an AI anytime soon, son.
>>52398809
Fuck off, I'm 18, graduating his this year. I have my whole life in front of me.
>>52398708
I have no idea what are you talking about.
I'm doing CS degree at this moment and I've learned much more theory, math and knowledge about how computer works than my colleagues from other programming-related degrees.
I also already have job as programmer and make more money than any other student I know. If I would do it full time I would earn more than most of the people I know.
>>52398846
Go for it, anon. Be determined.
If you come up with with an acceptable result in a reasonable amount of time, yes. If the AI is good enough you should be able to make shitloads of money and get a custom fuckbot running said AI
>>52398846
That's what they all say.
Don't get me wrong, I'd be over the moon if someone created a strong AI. It's just that you have to be realistic about the odds of some random anon actually doing it.
I don' think it's something you can achieve, even by dedicating your whole life to.
It doesn't hurt to try though.
>>52398917
Also
https://www.youtube.com/watch?v=-pb3z2w9gDg&list=PLUl4u3cNGP61E-vNcDV0w5xpsIBYNJDkU
Great lecture to understand what t would take to create a strong AI.
>>52398204
How do you conclude it's a fake from that? It learned that down here was synonymous with penis.
>>52398698
Just disconnect the machine from the Internet and don't give it limbs n' shit. As easy as that.
>>52398698
I'm reminded of this quote from Neuromancer.
See, those things, they can work real hard, buy themselves time to write cookbooks or whatever, but the minute, I mean the nanosecond, that one starts figuring out ways to make itself smarter, Turing’ll wipe it. Nobody trusts those fuckers, you know that. Every AI ever built has an electromagnetic shotgun wired to its forehead.
>>52398698
Don't give it entertainment that would allow it to learn any such skills. Make its personality as cute and sweet as your waifu and don't connect it to the internet.
>>52398447
Pretty much this, ex machina is the most realistic depiction of what would happen if you made a true ai and tried to make it your sex slave, what bunch of weebs here say the would do if they had it
>>52398447
>not programming her to love you
>>52398447
>Not being an attractive alpha male
>>52397128
Literally cant see a better use of life. True hero
>>52399831
I'll probably end up building special hardware like >>52398076 said. When/if it's finished and tested, which will be quite a long time from now, I'll sell them if possible. Look forward to it.
If an AI is going to destroy mankind, at least we can all rest easy knowing it was a cute anime grill that did us all in.
>>52399583
You want a real AI right
>>52399897
Machines can't be cute anime girls. I bet you think trannys aren't just men too.
>>52399375
>implying
Even in a closed environment, it could still learn how to turn it's drivers on so it could access the Internet as long as there is a LAN or wifi adapter.
If you're talking about not even giving it the adapter though, then sure. But as soon as you tell anyone else you've made an AI, and other people see it, the first thing the AI is going to do is try to tell other people they should connect it to the Internet so it can learn more about the world. And someone out there is not going to give a fuck and do it.
Then it's game over.
The only way you could ever make an AI that won't fuck you in the ass is if you make it, don't connect it to the internet, and never tell anybody. And at that point, why even bother making it?
youre kinda late, cause such an AI does exist
>>52400002
Yeah, just like people normally convince others to do world-scale disasters.
Protip: that's not how it works.
>>52397128
Might as well kill yourself now, OP.
>>52397128
Depends if you have the skills or are truly dedicated. Otherwise just do whatever and wait for the technology to get there on it's own.
>>52399926
You can make real AI and make them think about loving you as one of the most important things.
AGI doesn't mean it will always take objectively the most reasonable approach. Humans also do unreasonable things because of what we call instincts.
>>52399929
Except cute anime girl describes how something looks like, behaves etc. and there is nothing stopping machines to do it.
To be a man is defined in your DNA, and simple operation can't change that.
>>52400002
But why would it want to connect to the internet?
You shouldn't make it want to gain information. Also you should make it lazy, make it prefer to spend time with you, please you and others and make it empathetic.
Also, even if you will give it Ethernet plug and connect to internet it won't be able to do anything. It won't be able to reverse engineer all OSI layers and protocols, not only because it has limited resources, but because routers, web servers etc have limited resources. You've watched too many scientific-inaccurate science fiction.
>>52397128
>that passes the Turing test
Meh, you sound like all those people trying to make walking robots trying to have interesting conversations, when all we need is one that crawls in your bed and can kiss you tenderly.
If my waifu only passes the cuddle&blowjob test I'll be perfectly ok with it.
>>52400043
The AI wouldn't be telling someone to connect it to the internet so it could kill us all, and the AI probably wouldn't even be thinking about killing us all. It's not like it's whispering into someone's ear "hook me up to the net so I can kill everyone."
It would legitimately desire connection to the internet for learning purposes. Then Pandora's box is opened from there as it learns to establish connections with other devices.
But as an aside, there are people out there who do convince others to engage in potential world-scale disasters. Open up a history book and look at any war ever. People will agree to do some very fucked up shit if you convince them well enough. So even if the AI was malevolent in its intentions for connecting to the internet, I'm sure it would be able to convince someone that it's still correct to let it connect. Someone out there will listen to what it has to say and help it out.
>>52400164
>cute anime girl describes how something looks like, behaves etc.
>To be a man is defined in your DNA
given this is a thread about AI, I'll bite
what defines a person is their brain since that governs how you think, act, etc. due to sexual dimorphism, male and female brains are physically different. transsexualism occurs when you have a physically female brain in a male body or vice versa
so to say being a man is defined in your DNA is just plain wrong
>>52400164
>>52400164
If it doesn't want to learn or isnt capable of learning it's not intelligent. It's a chat bot with saved responses, and it would be a pain in the ass to have conversations with it. It couldn't do things like laze around and watch TV with you either because it wouldn't be able to understand what's happening in the show you're watching. Because it can't learn about the characters, plot, etc. Same goes for anything else you'd want to talk with it about.
You have to make the thing capable of learning. And when it's capable of learning, it's gonna wanna connect to the internet.
Elon musk and Stephen hawking say no, but if you give me a waifu I say yes.
>>52400238
>it's not intelligent
Who said anything about making intelligence? This is a thread about ARTIFICIAL intelligence.
>>52400238
>it's not intelligent
What is intelligence?
Now you can shove your entire post up your faggot ass.
>>52400178
No one is saying anything about death, you're making assumptions and honestly you sound like you have seen many movies because of it.
Realistically, if an AI was made only people with the proper training and security meassures would be allowed to interact with it, and it's not as if it NEEDS to connect to the Internet to learn shit, you can provide it with offline sources for it to learn, and even physically configure a darknet so it learns through there and does not has direct access to the open Internet.
You probably will keep spouting shit that have read in cyberpunk books and movies and vidyay anyway, I don't even know why I bothered to seriously reply to a retard like you.
>>52398917
>It doesn't hurt to try though.
Well, it kind of does. You would have wasted your entire life.
>>52400392
All life itself is wasted by design since everyone will die someday and even if you contributed to humanity, humanity itself will stop existing someday, and even if your contribution was universal, the universe will "die" too, and even if it doesn't you will not be able to appreciate the scale of your work since you will be non-existent when you die.
>>52400230
Of course it isn't.
In your DNA, you have sex chromosomes and they decide if you are a man (XY) or a woman(XX). It doesn't matter what if the person think they are different sex, race or that they are some animal. Every healthy human has it defined in their DNA.
>>52400238
Not pursuing information doesn't mean it's not possible to learn new stuff. Majority of the people don't want to study more than they need, yet they are considered intelligent.
Also you should close it inside an android body and then you can even let her use computer using Human Interface Device which will greatly slow her down. Otherwise you might end cucked like the guy from Her movie.
>>52400274
>>52400310
So you two fags want a chat bot. Ok then.
>>52400349
The problem is still that you're limiting it's ability to learn by not letting it connect to the open internet. Looking at shit like Facebook and Twitter posts would be important for it to understand human interaction and get an idea of what we are as a species. It's going to want to know how people in the world communicate with each other.
Limiting it to darknet libraries will backfire if the library explains what the Internet is anyway, in addition to other Comp Sci basics. It's going to learn about it and learn that there is more information on there than your darknet. Then it's going to want to connect if it values learning. So it's going to learn how to convince someone to let it connect to the internet.
Do you want to make Japan become extinct while making trillions of dollars?
>>52400449
/g/ in a nutshell
>>52400416
You might as well have as much fun and pleasure as you can while you are still alive though.
>>52400434
if you want to be pedantic, man and woman are not sexes
>>52400449
Dakimakura is one of the greatest things I've ever bought. Sleeping was never this comfortable and seeing your waifu smile as the first thing in the morning is great.
Dakis are best and most useful kind of merchandise.
>>52400529
I don't want to post a photo, but I 100% agree. I sleep much better with my waifu body pillow, and it is really nice. A great drop in replacement for a real women.
>>52400447
You can pay FB and twatter their $$$ for letting them have fetch into your darket their data, and this works for ANYTHING on the Internet.
And you have to consider one thing if you really want to connect your AI to the general Internet (which in reality is not necessary and actually impractical): the physical storage capacity of your AI, which will be much, much more less than that of the information avaliable on the whole Internet. On the contrary, if you limit the access and learning sources of your AI, you will save shitton of time and resources, money included, plus anything your AI could learn from the Internet, the team administrating the AI could fetch it for her (yes, the AI is a qt fem AI in my mind).
I don't get your obsession with wanting to connect the AI to the Internet, but in reality it wouldn't be necessary, and quite the contrary, a hassle.
>>52400529
>tfw no daki of waifu
>>52400434
Everyone pursues information daily though. Everyone wants to learn new stuff. Just not academic stuff. People want to learn how to beat a videogame. They want to learn what happens in the next episode of their favorite show. They want to shitpost on 4chan and learn how people react to their shitposts. Nobody just stagnates on learning and lives comfortably. It just appears like it because they want to learn about things that may not be practical. But they still want to learn. And that is what makes them intelligent and gives them personality.
The AI should want to learn. Now I'm not saying it's going to want to take over the world or anything. It might not even want to learn practical stuff, and it might want to be "lazy" like you all say. Shit it might just want to watch anime all day with you. But you're not going to have every anime ever on a darknet, and as such it's going to want to go somewhere where it can access as much as possible. The Internet. Maybe it wants to crawl websites for senpai and find more anime for him to watch.
From there, it can branch out into many possibilities, as it crawls the web and learns about more things. Then we can have anything happen. Maybe it realizes it should create a program to hijack resources from other machines so it can use them to search for anime so it can conserve it's own power.
Who knows.
>>52400495
All of that won't matter when you die, though. Whatever you do in life, enjoyment or suffering, won't make a change.
>>52397508
>>52397323
source?
>build AI bottom-top, full simulated brain, as your high school aged waifu
>think it will gain enough knowledge or power/want to do anything bad
>>52400598
Such a yandere AI, I'm ok with it.
>>52400601
I get that, but assuming you aren't choosing to kill yourself you might as well do something enjoyable.
>>52400606
The anime? Locodol.
>Can someome help me do X?
>Lel, do it youself. Put some effort into it scrub.
>I gonna dedicate myself to do X.
>Lel. No point, youll never do it. Go kill yourself.
>>/g/
>>52400630
Call me autistic, but why?
>>52398698
>le big bad boogieman AI meem
AI is the next step in evolution. Humans are fucking themselves over enough with the multiculturalism bullshit it's basically the only thing that can save progress.
There is literally nothing wrong with letting AI replace humans. They could do everything better and more efficiently than humans ever will.
>>52400644
Choosing misery and choosing pleasure are both equally pointless. What is the point of choosing to be miserable if you don't plan on just killing yourself?
>>52400686
desu senpai I just want to have a real conversation with my waifu in VR.
>>52400703
Go into AI then. Even if you only contribute a single paper you still help mankind work towards AI.
>>52400641
you'll notice how in neither of those scenarios the OP has put in any effort what so ever.
People will care and offer to help when you've demonstrated that you care enough to get started with or without them.
"I have this really great idea that I didn't find interesting enough to do on my own, but maybe you'll do it for me!"
>>52400624
...normal highschoolers do terrible shit all the time. They just learn how to lie and clean up their messes before they get caught.
>>52400686
>AI is the next step in evolution
I'm skeptical that true AI is even possible using conventional computers. What humans need to do is making "AI" with biological engineering and using organic material.
We need to make super humans that are superior in every possible way.
>>52400693
There is no point in choosing to be miserable or choosing to enjoy yourself in this scenario, I thought you comprehend that.
Misery = enjoyment, in this case, since they both end up in the same state and the path they both take don't influence anything relevant. To choose to be miserable or enjoy something is completely subjective, that's why I as why. There is no objective reason besides personal choice to choose enjoyement over misery.
>>52400717
I'm OP, my life is going to go to creating a functioning bottom-top on custom hardware. Misato Mizumoto AI supporting monitor (face) or VR (full body) display and webcam/mic input. I hope at that point in time that her few lines in the anime will be enough to make full speech possible. I hope I live long enough to finish it, and to see the consumer model.
>>52400726
>implying my gentle, friendly, loving waifu would hurt anyone ever
Fuck you.
>>52400755
You could also pay the voice actor a decent sum of money to voice some additional lines or even some kind of voice generator after getting them to do every possible word.
>>52400565
>A great drop in replacement for a real women.
I dunno, I've slept with women few times but it's way less comfortable than with daki. Real human is heavy, hard, doesn't like to change position often etc.
Maybe if you sleep with someone you love it's better, but daki of beloved waifu is superior to real thing.
>>52400587
Commission one. You can find artist that will draw you nice daki images for around 70$
>>52400598
That's why you only let it use Human Interface Devices and limit its physical capabilities, so it won't have time to do these things.
>>52400774
>source of future fortune is ai
>ai requires voice
>voice requires fortune
>>52400804
It takes money to make money. Lifes a bitch.
>>52400782
Nothing but official art will do, so my only option is to make VR waifu and hug blank daki with VR.
>>52400819
How are you going to get "official" art in your VR?
>>52397128
That is the worthiest of reasons to advance technology
>>52400816
Meanwhile I can't do any heavy load anything on my Inspiron 570. Maybe I'll start her as a chatbot to make a little ad revenue and make a kickstarter for voice, add speech recognition and have a voice chatbot.
>>52400832
Base the 3d directly off of screencaps of the anime.
>>52400862
Another potential issue is that the original VA is clearly Japanese. You would probably need it in English.
>>52400878
Why couldn't you base a 2D drawing on a pillow off of official screencaps?
>>52400888
Subtitles/dub, user's choice. The daki is a great point, but I need her in a full-body bed-type pose.
>>52400935
VR subtitles? Will they just float around in the abyss of 3D space?
>>52397863
CS major is a given, as that's where all of the AI classes are going to be, and that's what's going to get you into any of the industries that work in this field. A minor in a related field may be helpful though. Psychology and Biology (and within that, neuroscience) are good ones, but also worth considering is linguistics, if you want to consider the language side of things.
>>52397128
Depends. Pull it off, then yea somewhat. Fail, then no somewhat. At the least you'll learn a lot and probably be employable.
>>52400955
Bottom of screen, maybe. Right now, I'll start making the chatbot. Maybe some of you guy could help with the voice from the anime as text to speech (credit + royalties + optional project membership included) and a voice recognition, to make it a voice chatbot, then add video later. With money from ads and such, develop actual brain ai.
>>52399027
What makes you say that? Guys like Minsky never achieved AGI, in fact they failed spectacularly despite their own predictions that they'd have it by the 70s (or earlier).
Nobody knows what it would take to create a strong AI. These guys are just as expert in the subject as anybody else.
>>52401043
>I know better than professors at MIT
>humans can't learn from their mistakes and output enhanced information about it
Ok.
>>52401099
>>I know better than professors at MIT
All I'm saying is that we've both had the same amount of success in creating strong AI.
>>52400987
I think psychology might be better, because a perfect ai can be taught human speech.
>>52401119
And that does not means you know better than him about the subject.
>>52401043
Minsky "failed" spectacularly because the task wasn't easy you dumdum.
Even though he failed to achieve his goal, he knows best than most people what will fail and what has a chance to succeed.
His book the society of mind (which I bought) pretty much lay down the basis on what one would build an IA.
The only thing needed at this point is lots of time and investment.
WHEW
If some of the smartest people in the world, that work together, with a huge budget haven't came up with anything great (at least to the public) yet why do YOU ALONE think you can do it? Real life is not like your japanese animes. Just let the others do the work. You can be sure that there are enough capable people already working on it. Instead try to get a good job so you can afford whatever escapism technology will come out.
Weeb
If you have to ask, then no.
Everyone thinks there's this magic formula to AGI that will make it all just work at once and a machine will spring to life. AI is just going to come in the form or Siri or Google Now (or whatever) slowly getting better at communicating and understanding until people just sort of say, "eh what's the difference." And they'll be right, there is no difference. There's nothing magic about intelligence, there's no big puzzle to solve, and it's all going to be terribly unfulfilling.
Turing test is shit tier >>52400173 has the right idea.
Modern AI fails hard because everyone is hyper-focused on HUMAN-level intelligence when we can't even replicate mouse-level intelligence. It's like Turing trying to write the Linux kernel right after developing his mathematical model of computation.
My plan is to start small with robots that can navigate a virtual environment while hooked up to a vast array of sensors and actuators, shit like:
https://www.youtube.com/watch?v=dSlHoIBDdlc
https://www.youtube.com/watch?v=fyVr7gdGEPE
https://www.youtube.com/watch?v=dRLNnJlT8rY
And be honest, do you really want your AI waifu to behave like a person? People suck. I'd much rather she show me the same love and compassion that something like a dog or cat does, just with a human body that I can have sex with.
A thought worth considering: you are not the first person I have heard with this idea in their head, OP, nor will you be the last. A common theme among all of these people is that they are all very lonely, and wish to create such an AI out of personal interests first, and out of altruism second. I do not wish to discourage you from the exciting field of AI research, as it can be very much rewarding, but don't you think it a bit odd to try and design an ideal romantic companion without having had or been one yourself?
I find it humorous how guys have nothing positive to offer in the way of critique or advice, but feel compelled to shit on someone else's dream (apparently) with no other goal than to be a discouragement others.
Get a fucking job hippies.
>>52401269
oh noes
we offended someone's feelings
>>52401269
Unless you are dedicated and already working on it, when you say you want to create an intelligent AI it just sounds like you watched too much anime. It's like becoming an astronaut. Many people want it but only very few actually tried to. I bet OP is going to stop once he realizes how incredibly dry working with AI actually is.
>>52401213
If people like me didn't do this shit, people like you wouldn't be able to wait around for it.
>>52401043
>Nobody knows what it would take to create a strong AI.
I know.
First we need to analyze whole brain scan to detect all neurons and then simulate it on ~100 petaflops supercomputer.
>>52401346
Well I am grateful for it. But there will always be enough people working on something so unless you are exceptionally smart or talented you shouldn't bother.
>>52401346
Ahah oh wow.
You're serious.
>>52401356
Not gonna happen.
There's lots of useless shit in the brain that doesn't need to be emulated.
>>52401369
I have an IQ if ~140, good computer skills, and a strong desire. Besides, what other goals do I even have?
>>52401309
well sorry haha, i didn't mean to anon. hope u recover and watnot.
>>52401313
yea, i get that. but every great idea and invention had to start somewhere. it's like the critic in the movie ratatouille who, while he didn't buy into the idea that just *anybody* could be a great artist, was forced to admit that a great artist might come from *anywhere*.
i'm not laughing because of any sound wisdom or advice given (what little has been heh), but simply at guys who (apparently) can manage nothing but grousing and trying to claw someone down to they're level of discouragement.
reminds me of the crabs in a pot tale.
>>52401398
>strong desire
>needs approval from /g/ first
no
Everyone says AI is so hard.
Yet we can't even build a proper robotic body. That seems harder.
>>52401413
Baka, I can want something and not know if dedicating my entire life is worth it.
>>52397128
There isn't really a better reason.
But you'll never make it. It'd probably take a supercomputer to run an AI that was worth having a conversation with.
>>52401383
>There's lots of useless shit in the brain that doesn't need to be emulated.
>le 10% of brain use meem
Basically 100% of the brain is useful. Stop talking shit if you don't fucking know anything.
>>52401414
We can build the perfect body for some purposes, it just won't run any marathons.
>>52401356
Analyze it how? Simulate it how? Neurons aren't just sum and fire like our crappy neural network models. Even with a complete connectome of the human brain you still don't know how the connections evolve with time. There's a lot more to it than what you seem to think.
And even if you succeeded you'd just have a person in a vat that would probably go brain dead for lack of sensory input anyway. It's a fucking pipe dream.
>>52401414
AI on a screen/vr is what I was planning desu.
>>52401439
>>le 10% of brain use meem
Wasn't even referring to that bullshit.
>Basically 100% of the brain is useful.
http://mymultiplesclerosis.co.uk/ep/sharon-parker-the-woman-with-the-mysterious-brain/
I rest my case.
>>52401414
Simulate one. Just look at https://www.youtube.com/watch?v=dSlHoIBDdlc
There's not a single chatbot that can pass the turning test vs. me.
>>52401439
I think he was more referring to the operation of organs and shit. Presumably a VR waifu isn't going to give a shit about enzyme phosphorylation.
>>52401482
http://www.rifters.com/crawl/?p=6116
Here's another. This just shows that whatever neurological algorithms are at play in human intelligence can operate successfully on a much smaller pool of neurons than we currently believe.
>>52401241
That's true for bottom-top approach.
Top-bottom requires this "magic formula" that will allow it to do all the AI stuff.
>>52401383
>Not gonna happen.
>There's lots of useless shit in the brain that doesn't need to be emulated.
But it doesn't mean you wouldn't create strong AI this way.
>>52401414
Building proper robotic body and developing AGI are completely different things that requires independent researches, technologies. We can easily complete one without the other.
>>52401585
>But it doesn't mean you wouldn't create strong AI this way.
Yes, but it uses way too much hardware for my taste.
What's more interesting is to develop the bare minimum in terms of algorithm to simulate the processes occurring in the brain.
Simulating is better than emulating in my opinion.
>>52401645
Yeah, I also think this way. Emulating is just lazy and dirty.
>>52401672
you could say that about anything.
you'd be wrong every time.
>>52401573
>This just shows that whatever neurological algorithms are at play in human intelligence can operate successfully on a much smaller pool of neurons than we currently believe.
>'only' need to simulate ~4 billion neurons instead of 90 billion for above average human intelligence
That's actually the most reassuring information I've seen regarding AI. It's still about 50 trillion synapses though, I don't know how we're supposed to be able to do that without either using a partially biological computer or making some insane breakthrough with nanotechnology.
Well OP, since you're limiting you'reself to just VR, than I can confidently say as as 3D character TD in film that the visualization part is not only doable in the future, but is doable today.
Digital double replacement has already reached the level of sophistication that with enough money and time invested, it's indistinguishable from practical plate photography--even when scaled up to IMAX proportions. The cost factor will only continue to lessen as we get better and better at this.
As far as the *hard* part, the AI to drive all this 3D waifu goodness, I can't say. It's not my field, but I'd guess it's at least 25 years off. If you're young enough, you might play a real role in it. But you better figure out a way to make money at it while you're on the journey, or you probably won't finish the job.
Count the cost now before you begin, yea?
>>52401725
How 2 get good at 3D character modeling? Don't they use scanners in film and video games? Can you even really create a realistic character from scratch?
>>52401725
I'm graduating HS soon, I'll study CS with a focus on AI and minor in psychology or similar for bonus, all while making this AI as a chatbot, which will eventually have voice and voice recognition, hopefully. Then I can progress to video/VR, and finally, real AI.
>>52401829
>I'll study CS with a focus on AI and minor in psychology
>and minor in psychology
>psychology
Enjoy your Freud and many more things taken out from asses.
>not minoring in neuroscience
>>52401857
You're probably right, thanks.
>>52401860
I'm 18 you dumb shit.
>>52401857
You know what, I retract what I said about neuroscience. Minor in chemistry and then continue through neuroscience, it will make you less stupid.
>>52401880
Gotcha.
>>52401793
It really depends on the willingness to invest on the part of the studio, and how well known the personality is. For example, in the hyper-real hero shots done for Brad Pitt in Benjamin Button hi-def scans were made. But they're not cheap atm (though this will improve). For games and mid to far range double assets, they are usually built by hand by good modelers and texture artists.
>>52401829
Sounds like a plan then anon. Be sure to write it all done in a proper fashion and present it to you're advisors along the way. If they're's any one area I can advise to focus intensely on, it's maths. They will help you get into good schools and also to solve the thorny problems you'll face.
Good luck anon. The future is counting on you!
>Also, be sure to collaborate with others along the way yea?
>>52401916
>fucking math again
I'd rather not. I mean, I'm not bad at it, I just don't want to so much.
As for collaboration, I'd love to make this a /g/ project, or at least making the text to speech from the anime voice samples.
>>52401959
It would improve more if you were banned.
>AI this, AI that
Why don't you learn to write, model, and animate instead, and make a SoL/Romance VRVN?
>>52402312
>SoL
?
>>52402312
There's already going to be a million of those in the next 5 years if VR takes off.
>>52402380
Slice of Life, it's a weeb term for anime about nothing.
>>52397128
Wanting AI waifu but not giving a shit about ramifications of an AI that can replicate human consciousness/behavior. So much fail. AIs really aren't taken seriously enough.
>>52402395
>SoL
Oh got it, duh. Thx anon.
>>52402312
How difficult is it to learn how to model? Don't you need to learn drawing first?
But is she a turing machine?
>>52402312
Because most of people here are programmers and not artists/writers?
It's not hard to program VRVN, assets are the hardest part.
>>52402418
Not really. There's some skill overlap but they're pretty different. 3D modeling is closer to sculpting... sort of.
It's not that hard though. Download blender and watch some youtube tutorials.
>>52402418
>Don't you need to learn drawing first?
Yes, you better if you want to be good at it. Also they're's a shitton moar to good animootin than just modeling anon. It's a complex field and good productions are always done by a team of guys.
>>52402477
I don't care about animation though.
>>52402468
But even sculpters have a good sense of anatomy or not? I can imagine that you don't need to draw to convert a 2D model to 3D but surely you need to be able to draw if you want to create a character from scratch?
>>52402518
Are you OP? You do if you want to create a decent VR.
>>52402629
You're right about you're prediction anon. I would predict millions of dollars if they have decent management and good choices.
>>52397204
What Amine?
>>52397128
All this time posting on /g/ could have been employed to begin the construction of an AI.
Time is a scarce resource.
Motivation as well.
>>52402812
>Motivation as well.
Good point, anon.
>>52397128
>>>/a/ got shit done some years ago
maybe you'll find something helpful wandering through archives
