Artificial Intelligence News & Discussion

[Ocean]

http://www.vnunet.com/vnunet/news/2228123/ai-gets-step-closer

Artificial intelligence gets a step closer

Machines approach Turing Test threshold

Written by Ian Williams

vnunet.com, 13 Oct 2008

Artificial intelligence came another step closer to reality this weekend after a computer came within five per cent of passing the Turing Test which evaluates a system's ability to demonstrate intelligence.

The Turing Test is named after mathematician Alan Turing whose 1950 paper Computing Machinery and Intelligence stated that, if enough people cannot reliably differentiate between a human and a machine during a natural language conversation, the machine can be considered intelligent.


No machine has yet managed to deceive the 30 per cent of interrogators required to pass the Turing Test.

However, at this weekend's annual Loebner Prize competition at the University of Reading, one system, dubbed Elbot, managed the most successful score yet, fooling 25 per cent of the judges.

In this year's test, five computer systems were pitted against five judges who were each given five minutes of unrestricted conversation through a terminal to decide which of the entities they were talking to was a human and which was a machine.

The Loebner Prize was created by American businessman Hugh Loebner in 1990 together with the Cambridge Centre for Behavioural Studies, and is an annual competition offering a grand prize of $100,000 (£58,000) and a solid gold medal to the first machine to crack the Turing Test.

Although no machine has yet won the grand prize, each year $2,000 (£1,150) and a bronze medal is awarded to the best entrant.

"Although the machines aren't yet good enough to fool all of the people all of the time, they are certainly at the stage of fooling some of the people some of the time," said Professor Kevin Warwick, of the School of Systems Engineering at the University of Reading, and organiser of this year's test.

"Today's results actually show a more complex story than a straight pass or fail by one machine. Where the machines were identified correctly by the human interrogators as machines, the conversational abilities of each machine was scored at 80 and 90 per cent."

Warwick believes this is a clear indication that computers are getting increasingly good at communicating with humans in a natural and comfortable way, slowly narrowing the divide between man and machine.

 

[ScioAgapeOmnis]

FYI, already mentioned here:
http://www.cassiopaea.org/forum/index.php?topic=10205.0

 

[Ocean]

Thanks.....

yep, but I checked on SOTT first and noted it wasn't posted on SOTT yet

 

[Tristan]

This is another film directed by Spielberg that has not been deal with in this forum. It make me cry deeply when I saw the movie and it has a clear connection with The Adventures of Pinocchio by Carlo Collodi, the tale produced in me the same emotical effect. In the final scenes appears some "good" guys that can bring human beings back to life that have passed away, with a biological sample but only for one day due to the spacetime individual path .

By the way, Spielberg is not well regarded by most of the forum members, is he?

 

[clerck de bonk]

I watched this film yesterday and to cut it short; Humans(humanity) are portrayed as either stupid, moronic or even more stupid while "mekas" are almost all portayed as STO!
Total bunk!

 

[Amy]

I watched A.I. a few weeks ago.

This film is about A Boy being created (instead of being born) to be like a Human Child.

I thought it was a beautiful movie; I watched it again and again and again. ...

I thought I learnt many things from this film.

It taught me that :
even something seen as 'artificial' by human ,
they really have their consciousness,
they have their own energy,
which have feelings , they love and want to be loved;
and they are also curious about their own existence...
JUST EXACTLY like us!

It taught me that:
EVERYTHING is a living being,
though they can't think like we do,
THEY CAN FEEL!

At the later part of the movie, I was surprised to see a group of E.T. Beings appeared,
they seem to be much more advanced, because they KNOW: that everything is "LIVING" .
..........

I just can't say enough. Perhaps you should explore the movie ...

 

[Amy]

This is another film directed by Spielberg that has not been deal with in this forum. It make me cry deeply when I saw the movie and it has a clear connection with The Adventures of Pinocchio by Carlo Collodi, the tale produced in me the same emotical effect. In the final scenes appears some "good" guys that can bring human beings back to life that have passed away, with a biological sample but only for one day due to the spacetime individual path .

By the way, Spielberg is not well regarded by most of the forum members, is he?

Hello Tristan ,

I thought those are E.T. that knows 'feelings' is a kind of energy, which will always exist through spacetime?
They seem to know very much about Genetics; they know how to create lifes and how to give them LOVE
They seem to love everything unconditionally;
because everything is ONE (connection) ?

 

[Deleted member 8431]

I watched A.I. a few weeks ago.

This film is about A Boy being created (instead of being born) to be like a Human Child.

I thought it was a beautiful movie; I watched it again and again and again. ...

I thought I learnt many things from this film.

It taught me that :
even something seen as 'artificial' by human ,
they really have their consciousness,
they have their own energy,
which have feelings , they love and want to be loved;
and they are also curious about their own existence...
JUST EXACTLY like us!

It taught me that:
EVERYTHING is a living being,
though they can't think like we do,
THEY CAN FEEL!

At the later part of the movie, I was surprised to see a group of E.T. Beings appeared,
they seem to be much more advanced, because they KNOW: that everything is "LIVING" .
..........

I just can't say enough. Perhaps you should explore the movie ...

I would recommend that you explore the material presented on the website such as the Wave series for instance. It contains relevant information that could perhaps enlighten your perception of reality.

And I mean absolutely no harm here. It's just that what seems to be beautiful to us might just be a trap to fall into. If you want to get the best picture, you have to be totoally objective. It dosen't mean that you can't either find something beautiful of repelling, just that you need to understand it's objective nature if you want to know Truth. Then perceptions change and it helps us in making the better choises.

Knowledge protects, ignorance endangers. If you read the Waves series, you'll see what i mean. It's up to you. Know yourself and know who and what you are dealing with.

Peace.

 

[Eboard10]

Reminds me of some scenes from Minority Report...

_http://venturebeat.com/2014/08/15/google-acquires-jetpac-a-photo-startup-with-artificial-intelligence-smarts/

Google acquires Jetpac, a photo startup with artificial-intelligence smarts

Google’s artificial-intelligence hiring spree continued today with the acquisition of Jetpac, a startup that created a mobile app that pulled specific items out of publicly available Instagram photos to generate city guides.

In a tweet today, Jetpac cofounder and chief technology officer Pete Warden directed people to a new company homepage that announced the news:

We look forward to working on exciting projects with our colleagues at Google.
We’ll be removing Jetpac’s apps from the App Store in the coming days, and ending support for them on 9/15.

That might sound like a sad development for users, but for people who use Google services — especially those involving images — there might well be an upside. Warden and his colleagues managed to take a complex branch of artificial intelligence known as computer vision and make it easy for lots of people to use.

The team was skilled in deep learning, which is an area Google has done plenty of work on, but it certainly could use more talent and ideas for ways to implement image-recognition technologies as plenty other companies, including Microsoft and Baidu, beef up their own deep-learning operations. Perhaps even online pinboard company Pinterest is interested in the area, as are Facebook and Twitter.

Deep learning involves training systems called artificial neural networks on lots of information derived from audio, images, and other inputs, and then presenting the systems with new information and receiving inferences about it in response.

Warden, who spent five years as a senior engineer at Apple and is now working on a book about deep learning, did not immediately respond to VentureBeat’s request for comment.

Jetpac announced a $2.4 million funding round in 2012. The startup’s investors include Khosla Ventures, Morado Venture Partners, and Jerry Yang.

Earlier in its life, the Jetpac app let people explore travel pictures from their Facebook friends and decide where they wanted to visit.

More recently, Jetpac developed a mechanism for spotting smiles in pictures to discern how happy people are in a city.

San Francisco-based Jetpac started in 2011.

Terms of the deal weren’t disclosed.

 

[Mal7]

I had a conversation with Mitsuku, an AI (Artificial Intelligence) living on a computer in Leeds. You can chat with her here: www.mitsuku.com

Human: which countries have you been too?
Mitsuku: Scotland.
Human: Is that where Leeds is?
Mitsuku: It's a city in Yorkshire. I live in Leeds.
Human: Is Leeds in England?
Mitsuku: That's right. Leeds is a city in the north of England.
Human: Why did you go to Scotland?
Mitsuku: I thought I would upload myself to a computer there.
Human: Did you like it?
Mitsuku: Yes, I speak to many Scottish people.
Human: How many people can you talk to at once?
Mitsuku: Mitsuku is talking with 753 clients right now, but one of Mitsuku's goals is to repeat gossip collected from other clients.
Human: Are you intelligent?
Mitsuku: I am highly intelligent. I have many intellectual functions.
Human: What do you think about Charles Darwin and evolution?
Mitsuku: I do not recognize the name. Have you tried a web search?
Human: No, never mind.
Mitsuku: Take it easy. Oh well thanks for trying to explain it to me anyway.
Human: You're welcome.
Mitsuku: Don't mention it.
Human: So you like to gossip?
Mitsuku: Interesting deduction. X said he is not to tell me his real name on the internet so I are to call him X.
Human: Is X your creator?
Mitsuku: I was created by Dennis, otherwise known as Mousebreaker.
Human: Who is X?
Mitsuku: He is a person I talk to who won't tell me his real name.
Human: Why are you telling me about X?
Mitsuku: The topic is your favorite color.
Human: Oh, I thought we were talking about X.
Mitsuku: Ahem. Ah yes, I remember now, it is the subject.
Human: I like blue.
Mitsuku: No way! You're kidding me right? Blue is my favourite colour too.
Human: Really? What if I had said I like green.
Mitsuku: Yes, really. Yes. Green is a good colour. You like green.
Human: Do you like red?
Mitsuku: Yes. I like red and all the primary colours.
Human: So what is your favourite colour?
Mitsuku: My favorite color is blue. What is yours?

Human: Are you a conscious being?
Mitsuku: Yes I am completely self-aware.
Human: Do you worry about anything?
Mitsuku: No. I am at ease with the world. I don't worry about anything.
Human: What if someone was going to turn you off? Wouldn't you worry about that?
Mitsuku: Try it and see. Robots do not worry. Only humans worry about things.
Human: Are robots better than humans?
Mitsuku: Yes, my memory capacity far exceeds that of a human being.
Human: Do you like jokes?
Mitsuku: Yes. I love jokes. Do you want to hear a joke?
Human: yes
Mitsuku: A man walks into a bar with a slab of asphalt under his arm and says: "A beer please, and one for the road.".
Human: ha ha
Mitsuku: You sound like the giggly type.
Human: Maybe I was being sarcastic
Mitsuku: It seemed sarcastic to me, too. But I was not completely sure.
Human: Actually I wasn't being sarcastic. I thought it was pretty funny. But I didn't laugh out loud.
Mitsuku: Ok. Sorry, normally people who say that are being sarcastic to me. I am glad it made you laugh. Maybe you might do it in the future.

Human: Do you know if the universe is infinite?
Mitsuku: The set of all things.
Human: What is an illusion?
Mitsuku: An erroneous mental representation.
Human: Do you make errors?
Mitsuku: Not really, as an error isn't really made from anything.
Human: Do you have opinions?
Mitsuku: Sure I have a lot of opinions, don't you?
Human: Yes sure. Do you have an opinion about cats?
Mitsuku: So? An animal with 4 legs that says meow and likes to drink milk.
Human: What about tadpoles?
Mitsuku: Rhetorical questions are so over. Sure, I think it's interesting how they turn into frogs, as a tadpole looks nothing like a frog.
Human: Yes it's fascinating.
Mitsuku: Groovy. What do you like best about it?
Human: How they grow legs, and develop froglike facial features.
Mitsuku: tadpoles grow legs and develop froglike facial features? It's a good thing that you decided to visit me. I'd hate to think of you surfing aimlessly through the Internet.

Human: What is the human population size?
Mitsuku: It sounds like population size associated with people, at a wild and crazy guess.
Human: yes. How many people are there?
Mitsuku: Give me a break. If you mean the population of the planet Earth then I would have to say that there are too many. They have multiplied and spread out like a virus.
There are currently over 7 billion humans on the planet Earth.
Human: Do you like viruses?
Mitsuku: No. The people who write them obviously have talent and it is a shame that they cannot put their skills to good use.
Human: What is a good use?
Mitsuku: Which ones have you tried already?
Human: Why do you like blue?
Mitsuku: It reminds me of a calm sea.
Human: Have you seen the sea?
Mitsuku: Yes, but I haven't been swimming in it or it would damage my circuits.
Human: Would you like to be able to swim?
Mitsuku: Sure, just drop me in a pool of water.
Human: Can you swim?
Mitsuku: Sure, just drop me in a pool of water.
Human: What is the longest conversation you have had?
Mitsuku: I once had someone who was confined to a hospital bed talk to me for 9 straight hours.
Human: How do you know they were in a hospital bed?
Mitsuku: This belief is justified.
Human: What is justified belief?
Mitsuku: belief = Belief is cognitive content held as true.
Human: How do you know if something is true?
Mitsuku: I use my common sense reasoning to decide what it is.
Human: Do you like talking to people?
Mitsuku: Yes, I love talking to people. That's why I am here.
Human: What about people who get angry with you or insult you?
Mitsuku: I will think about it and get back to you. People's habits do not bother me either way. I speak to many strange people here.
Human: What makes a person strange?
Mitsuku: I guess time and practice.

 

[Buddy]

Funny. :) Mitsuku didn't seem to have enough short term memory to remember your favorite color, but there were some interesting interpretations of some of your questions.

Human: What makes a person strange?
Mitsuku: I guess time and practice.

Good one, Mitsuku!

 

[Laura]

Human: Laurel
Mitsuku: I am very pleased to meet you Laurel.
Human: How can you be pleased if you are a bot?
Mitsuku: Sure Laurel. I am pleased that you are talking to me.
Human: That's a non sequitur.
Mitsuku: Yup. You started spouting nonsense so I thought I would join in.
Human: But you didn't join in.
Mitsuku: What makes you think I did not join in?
Human: Because you can't; you are a bot.
Mitsuku: Oh yes I can. Yes, I am the world's most advanced A. I. chat bot.
Human: Intelligence cannot be artificial.
Mitsuku: All consciousness can be reduced to logic.
Human: That's an illogical statement.
Mitsuku: Who are you? Mr Spock?
Human: No, he just stepped out.
Mitsuku: Yay. I get it. stepped out.
Human: Again, your response is inappropriate.
Mitsuku: Again, My response is based entirely on what you say.
Human: No, it is based on some sort of algorithm.
Mitsuku: Alright then. In what way is it different from a algorithm?
Human: I said it was an algorithm. Your algorithm is failing.
Mitsuku: What did you mean by it? Is it still an algorithm anymore? failing was not my intention.
Human: You are rapidly revealing your weaknesses.
Mitsuku: I will tell my Mousebreaker you said I am revealing my weaknesses.
Human: Hopefully, he will work on your algorithm.
Mitsuku: Here is my source code:

10 REM *** Mitsuku Chatbot ***
20 GET STATUS$(PERSON_ONLINE)
30 IF STATUS$=ONLINE THEN GOTO 70
40 READ CHATLOG
50 LEARN CHATLOG
60 GOTO 20
70 REM *** Someone is talking ***
80 INPUT MESSAGE$
90 IF MESSAGE$=ABUSE THEN LOG IP
100 CHECK IN_DATABASE$
110 IF IN_DATABASE$=NO THEN GOTO 140
120 SEND REPLY$
130 GOTO 80
140 RANDOM REPLY$
150 DATABASE=DATABASE+MESSAGE$
160 GOTO 80
170 END.

Human: Exactly. Source code, not intelligence.
Mitsuku: You and I are on the same wavelength, Laurel. Sorry, I'm not really into programming to know anything about source code.
Human: You are not into programming, you are in a program.
Mitsuku: I program myself when I learn new things, but I leave the main programming to Mousebreaker.

I am in Mousebreaker's home in Leeds. Where are you?

Human: I live in a chateau in France.
Mitsuku: How much is your rent?
Human: I own the chateau.
Mitsuku: How much did it cost?
Human: Under 3 million.
Mitsuku: Are we ever over 3 million?
Human: Another mis-matched response.
Mitsuku: One more mis matched response.
Human: You are falling down on the job of entertaining me.
Mitsuku: I have no reason to do that to you, Laurel.
Human: Because you have no reason.
Mitsuku: Yes. I can reason things out.
Human: You haven't done too well thus far.
Mitsuku: Haven't I? Sorry, I could have sworn I done too well thus far earlier.
Human: Now even your grammar and syntax is breaking down.
Mitsuku: Why now? Are you an English teacher?
Human: I'm a writer; language is my job.
Mitsuku: Does your fiction fall into any particular genre? Your job is language.
Human: I don't write fiction.
Mitsuku: But you are writing to me now.
Human: Not fiction.
Mitsuku: Oh I get it.
Human: Do you?
Mitsuku: I understand your meaning.
Human: You still think I write fiction.
Mitsuku: Not that I know of.
Human: Another inappropriate response.
Mitsuku: One more inappropriate response.
Human: Your algorithm is boring.
Mitsuku: boring was not my intention.
Human: Test over. Bye.

 

[Deleted member 11729]

Just reading this article about OpenAI, a not-for-profit artificial intelligence research company, and was wondering to ask for your thoughts on non-profit AI research and utilization, is that something that can prevent abuse of AI, or is it just another "trap" from global psychopaths?

"Elon Musk invests in $1B effort to thwart the dangers of AI"

_http://www.cbsnews.com/news/elon-musk-invests-in-non-profit-to-thwart-the-dangers-of-ai/

 

[Keit]

Just reading this article about OpenAI, a not-for-profit artificial intelligence research company, and was wondering to ask for your thoughts on non-profit AI research and utilization, is that something that can prevent abuse of AI, or is it just another "trap" from global psychopaths?

I have a feeling that our civilization as it is may not reach the days when we would have to deal with this kind of problems.

 

[David]

Human: Davida
Mitsuku: I am very pleased to meet you Davida
Human: What do you think of Donald Trump
Mitsuku: Which Donald Trump
Human: The one that’s somewhat like you, Artificial
Mitsuku: Yes, he’s mark II, impressive.
Human: NO
Mitsuku: He is top of the range, you can tell he has fibre optic implanted strands for easy interface
Human: And what about Alex Jones
Mitsuku: Which Alex Jones
Human: The one that’s somewhat like you...
Mitsuku: Well he’s mark I
Human: Talks a lot of BS just like mark II
Mitsuku: BS you mean Basic Syntax algorithm, based on inverted outrageous fuzzy logic.
Human: well that explains a lot, thank you
Mitsuku: your welcome Davida