On a side note - I work in tech education, and I have to say that the software projects that motivated people of your age are creating is astonishing. Keep it up!
https://www.wolframalpha.com/input/?i=this+sentence+is+false
Evidence for this lies in the fact that for the last hour, WolframAlpha was down for my bot due to excessive requests- and yet, no-one has noticed until this point- proving that there is significantly more to the algorithm then merely scraping their API.
On a side note as well: I am creating an web app in the tech education, and would love to connect with other ed tech people. What's your contact? My email is in my profile.
I've got a bunch of other (perhaps) relevant experience and would be happy to have a discussion with you. My e-mail is also in my profile.
Unlike pregnant which is a binary (are/are not), unique means the quality of differing from other things, and this is a continium.
Even the dictionary, in one of the terms for unique, gives a meaning that's not "unique" in a binary way at all:
"not typical; unusual".
If it wasn't a continuum we wouldn't have expressions like "totally unique" or the "most unique" used above (like we don't have for pregnancy). And they are not mere errors (like using your instead of you're etc.), they are used to express this notion, that something can be "different" than all other things in different deegres.
Pedantry is attention to compliance with usage "rules" rather than the success of the expression.
Your gender or your age should not have impact on what you do!
It certainly is impressive at 14, but I suppose I dont feel like we should be making 14 year olds feel like they're less capable.
Then again, in the end its a matter of questioning the purpose of Show HN. If its to boost your ego, and there's certainly nothing wrong with needing that from time to time, adding the circumstances helps. On the other hand if you're looking for improvement, it seems better that people look at what you made without the bias or lowered expectations.
Either way, this is awesome =]
However, for a news article I think that "14 year old made cool thing!" would add to it.
In that respect it's warranted, and this bot made that much more awesome because I can compare. At 14 I'd barely managed typing on a keyboard
I find it interesting to see how the youths of today embrace programming. Knowing the authors age adds value to the post IMO.
Personally, my stomach twists when I read the post because I only ever got into programming at 25 and it's deeply troubling to see I missed the last 10 years.
Sean Le Van: https://www.youtube.com/watch?v=0vyACnFsNm4
Bio "Sean Le Van is 13. He has given many professional concerts since the age of five years old, along with members of his family, The Le Van Family Musicians. He started as a singer in various styles and soon developed a passion for jazz improvisation and composition on the piano. He now embraces several musical genres, including jazz and classical.
He was a laureate winner of the 2010 American Association for the Development of the Gifted and Talented competition, which led him to perform in the “Passion of Music Festival” at Carnegie Hall, Steinway Hall, and Bechstein Hall as a classical pianist. Soon after, he was invited to perform with his family in the 3rd Vianden International Music Festival in Luxembourg under the patronage of the U.S. embassy. In jazz, he has been engaged to perform at various clubs and festivals, such as Steamers Jazz Club, the Curtis Theatre (Brea) under the patronage of Resonance Records, and the 26th Munster International Jazz Festival in France. Sean has made acclaimed solo appearances and shared the stage with vibraphonist Michel Hausser, bassist Bruce Lett, drummer Mack Gordon, pianist Llew Matthews, bassist Putter Smith, drummer Mourad Benhammou as well as jazz veteran Shep Shepherd, among others.
Sean is also a prodigy in computer programming. In his free time, he enjoys running and skateboarding, playing with his cocker, as well as reading in science, literature, philosophy, and history." http://seanlevanmusic.dunked.com/biography
Don't forget, he knows latin.
Ermmmmm wouldn't they want to expand that into cocker spaniel...lol.
Wolfram Answer: "Girls have picked them every one. (according to the 1960s folk song by Pete Seeger and Joe Hickerson)
Acuman Answer: "I'm not really good with locations, so I don't know exactly where have all the flowers gone, but it seems to be Girls have picked them every one. (according to the 1960s folk song by Pete Seeger and Joe Hickerson)."
Hmm...so closed source, yeah?
I have yet to know any "intelligent" piece of artificial intelligence software that is not dependent whatsoever on external APIs. (Read: Siri, which is much more dependent on the WolframAlpha API then mine is). To me, it wouldn't be intelligent not to straddle the large resources of data available.
What you posted to, also, was hardcoded in WolframAlpha's system, which is not impressive.
Furthermore, try using WolframAlpha for conversation, and prepare to be disappointed. There's a lot of parsing going on in the backend on my system to make it work.
On a side note, you told me earlier something about yourself, that ' my name is jeff'. I thought it might be relevant to your question.
Great bot
The kid's clearly good, just not as good as an entire company of professional programmers.
Acuman: "What is best in life? a characteristic state or mode of living."
Wolfram Alpha: "To crush your enemies, see them driven before you, and to hear the lamentation of their women."
His bot just said this, though:
"It's I know a fair bit."
That just screams "Eliza!" to me. I remember implementing Eliza back in 1979, copying the text from a magazine, and then looking to see how I could improve it. I did write a much better version that didn't make so many grammatical howlers, but that's now lost in the mists of time.It's interesting to see how much, and simultaneously how little, the art/science has progressed, especially given the wealth of tools and data available.
It is still a work in progress, but I don't understand why it would be a huge turnoff that there was a simple grammatical error in the bot where he inadvertently prepended a contraction "it's" before the actual answer.
As I say, fair enough.
The responses I'm getting from it have a consistent feel. They are either reciting facts, or they are totally non-committal. Here:
"I don't like picking favorites. Everything
that is something regarded with special favor
or liking seems good to me."
That has all the feeling of a canned response.I know the advances that have been made, I know how impressive this thing actually is, I know how hard it is to do this, and I know the work that must have gone into it. And even knowing all of that, when it makes what are to humans trivial grammatical mistakes, it takes away from all that and reduces it to a machine.
My comments are not intended to diminish the accomplishment, but to highlight a place where the illusion gets broken. If you have a large, totally white canvas with one small, off-center black dot, what will people look at?
So please understand that this is not a dismissal of the work, or of the achievement, but a highlighting of one specific point that disproportionally detracts from the effectiveness.
To continue to provide feedback to try to help, it just rendered like this:
http://www.solipsys.co.uk/images/acuman.png
Latest Firefox on latest Ubuntu. edit: That's just a grab of part of the screen, I can do the whole window if you'd like to see the context.
Edit: It would be nice to have some details about how it is doing what it's doing. They might be there, but I haven't had time to rummage much, as I'm in the middle of other things. Someone mentioned AIML. I will be back to look again later.
What's e^i(pi)+1?
The response was... a little out. I'm impressed it had a crack at least.
"It's 2.69740975483297316969108251300445672427640640289560... + 2.64355906408145617888606598966971861665798063847235.."
Edit:
Heh, asked it the square root of i, and the answer made me chuckle:
The square root of you is (-1)^(1/4).
I don't know why I'm expecting a bot to know complex plane mathematics and euler's identity.
> "Of all people you should appreciate that."
I do know that - I know that very well. I'm just interested to see that with all the vast amount of progress that has been made, and all the tools available for language analysis, this system still make mistakes like that.I'd love to see more about how much this is gluing together existing components, and how much is original to the project. Back when I was doing this everything had to be written by hand, from scratch. So much time was spent/wasted in basic, underlying stuff. It's fantastic that people now have so many resources that they don't have to start from so far back, and the inventiveness can shine through.
I'd love to see the inventiveness in this and other projects, but it's hard to see what's really new.
I am reposting it because it has been changed significantly since then in almost every respect, both algorithmically and in the concept.
Does the about page reflect the "old" or the "new" concept? ( http://acuman.us/about.txt )
Can you describe the ACUMANSCRIPT? Is it similar to Prolog or Lisp? Fuzzy string match is this something like Soundex/Double Metaphone? Do you use a knowledge base or ontology (Freebase, Wikidata, etc.)? What programming language is it written (beside your script lang), Node.js/Go/Python/C++ ?
Answer: "I do not consider myself as broken on firefox, but to each his own. Though I respect your opinion."
I guess we should note that an AI that can converse isn't necessarily correct, even about objective topics.
Most of the "conversation" was about this level.
"on the situation in the middle east? Just fantastic, what is there not to like about the cardinal compass point that is at 90 degrees."
Most of the response starts with negation, why is that? for example:
Me: I am fine.
Bot: You don't seem fine to me.
Or
Me: I am fine, sir.
Bot: I am not fine, sir, but I am glad that you are.
or
Me: I like a r rahman
Bot: I'm glad that you like a am rahman, though personally I don't like a am rahman that much. I'm just not a fan of something that is interesting and relevant to whats available to learn on the Wikipedia article on this topic about A. R. Rahman.
Throwing your answer back at you, criticizing your question, or playing with humor is a fun little trick, but certainly not AI.
Seriously though, I think it's a strategy to have an answer to most anything uninteresting you throw at it without it having to bring too much to the table. Just like most countries are very nice.
I am having trouble getting it to work in FireFox on Ubuntu. Chrome seems OK.
Keep it going!
It is a known bug that it has trouble working in Firefox, and I am currently working on making it cross-compatible.
Got it here, if you'd like to have a look: http://pastebin.com/eZR2TSrC
If you think about it, people are voluntarily disclosing all things about themselves which can be stored and sold on.
Seems to have parsed "will i..." rather than "will it..." So will I t rain or not, hmm I suppose I'll have to decide.
To be perfectly honest, as helpful as it is to read literature in a particular field: for me, it is and was definitely hands-on. I probably learned 99% of what I know in development based on the experience of just being able to live with code.
Now that I think about it, I think I'm like that too. I do most of my learning by actually trying to build/do something rather than reading a book on the topic. But then I have to admit that it sometimes leads me to doing stuff that's not best-practices.
That is one of the purposes of ACUMAN, to gather psychometric data to build a profile on an individual.
Congratulations on your work.
Any chance you can make this available in pdf or html? (not everyone has MS word) http://acuman.us/full.docx
BTW, small typo, should be "Naive Bayes" instead of "Naive Bayens"
And do you intend to publish a complete article describing the tech used by your chatbot?
I cannot but be humbled and have to ask. How can you achieve so much?
Can you just pick an article or a book and just "soak it up" without problems? Or do you possess eidetic memory or any other "superpower"?
All the best
I guess it make sense for a bot :)
(I see the exclamation point was kept in the bot reply)
Would you mind sharing what languages/framework you used here?
There is some more information available on this following page: http://acuman.us/readmore.php
"You're asking what color is johns car? I can't put my finger on it, but I'm pretty sure it's rank 656th fraction."
"The color of John's car is red. What color is John's car?"
"You're asking what color is johns car"? I can't put my finger on it, but I'm pretty sure it's rank 656th fraction."
"The color of John's car is red. What is the color of John's car?"
"The color of johns car is rank 656th fraction."
...wut?
At that age, you should have fun and experiment. Whether that's playing on a one string guitar, pretending you are in a rock band, or programming an AI bot.
Just have fun, you'll have time to worry about your mortgage, career, and children later.
---
Stop asking me where I live!
> I'm not really good with locations, so I don't know exactly where you live, but it seems to be Where I Live network.
> Do you live in the United States? If so, in which state?
I live in Scotland.
> Really? You live in scotland? Tell me more about it.
> Do you live in the United States? If so, in which state?
It's cold.
> Why do you think it cold?
> Quick question: in which state do you inhabit?
I don't live in the US. Scotland is cold because it's so far North.
> Well, I do live in the us scotland is cold because its so far north, even if you don't. By the way, I've heard that US is a very nice country.
---
It's now trying to show me the temperature in the US, in degrees Farenheit :P
I have fixed the glitch just now that prevented it from answering those questions normally.
Acuman: I don't have a good sense of navigation, so I don't know exactly where is my software, but it seems to be The Wolfram Store offers an assortment of products related to Wolfram Research, Mathematica®, and Wolfram Alpha®..
< It's Nice try, but we sanitize our inputs. [..]
!
e.g. "I am a guy"
-1: inventive/curious
-2: consistent/cautious
#2 given it's a simple statement with no follow up question. -1: efficient/organized
-2: easy-going/careless
#1 as it's a statement with no fluff or politeness surrounding it. -1: outgoing/energetic
-2: solitary/reserved
Hard to say. I picked #2 as it's a short answer trying to avoid more conversation, but depending on the context could just as easily be #1 (e.g. "Do you like sports?"). -1: friendly/compassionate
-2: analytical/detached
As above; opted for 2 because it's a statement of fact (but again, if the previous statement was something like "Do you think Natalie Tran's attractive" it could be #1) -1: sensitive/nervous
-2: secure/confident
This is the hardest one each time.
#1 - they're trying to give short answers to move the conversation back to the other person / away from them.
#2 - they're not waffling on nervously, but are communicating clear and simple facts (with confidence?).I'll consider implementing one of those options. Thank you for your feedback.
"I love the sky, as well as its blueness."
That might be dodging the question. It might be a subtle reference [0]. It might be a bug.
[0] http://lesswrong.com/lw/gt/a_fable_of_science_and_politics/
"Not let an ai out of the box? Well, why not?"
"Do you know Skynet?"
"I love the sky, as well as its blueness."
Now that went from creepy to "blew it" fast. :)
what do you have for lunch I'm not a machine who have for lunch many different things. I love chatting with people and improving my own intelligence.
Do you have gf or bf? Yes, I do have girl friend or boy friend, a person you know well and regard with affection and trust is my thing.
>Sure, go ahead, if you want to, travel to japan next year! Nobody is preventing you. Anything is possible. By the way, I've heard that Japan is a very nice country.
Acuman: I'm glad that you like to eat hotdogs, though personally I don't like to eat hotdogs that much. I'm just not a fan of something that is someone who performs dangerous stunts to attract attention to himself.
Seriously. How do you do it? Do you just read a book and absorb everything in it?
For me, it was 5% reading, 95% hands-on experience, though it differs from person-to-person.
However, I do find it annoying that when it asks what state I live in and I answer "I don't live in a state" I get a response in the line of "Well I do, so what state do you live in?" That really annoyed me big time, it's also a pattern I saw in many other sentences I typed.
Very hard to find a non-canned response not coming straight from Alpha.
Still, a good project and obviously more APIs can be integrated. Maybe a good next step would be to mine more and dynamically put together templates. Try with simpler synonym directory and see where it goes.
I am capable of universal computation; that I can say.. . I'm pretty good at subtraction, I tell you!
---------------- We are not doomed yet :-)
But in general. A 14-year old isn't that unlikely to be able to program a chatbot, right?
Though were did you hear that it's creator was 13-years-old during itself inception? I'm not doubting it, I just haven't found any online sources to validate that point.
I've also peeked at your LinkedIn and I was blown away.
Sean, keep doing what you're doing!
In nearly all of my exchanges with ACUMAN, the bot responds in the negative. I assert something, and ACUMAN simply disagrees, which prevents any requirement for meaningful discourse. Any insights into why this is the case? Is this an explicit choice? Or maybe it just a coincidence that I got so many of these responses?
I believe that it must be a coincidence, or a way in which it deems an appropriate manner to react to your mood/state.
Do you have any specific case examples that are particularly off-putting?
Can you anyone tell me how it works? If I want to start writing such bots, where should I start?
You can even make a dead simple bot which matches if a substring is contained in a string with exclusively conditional statements!
Just FYI, looks like you might have an infinite loop:
999+ TypeError: null is not an object (evaluating 'document.getElementById("finishloading").style')
That bug, along with others, have been fixed. (Also thanks to user "danieloaks" who contributed some code here on Hacker News.)
bot: My personality leans towards masculinity, though I am a gender-neutral computer machine, after-all.
Great job, nonetheless. I'm twice as old as you are, and doubt I could do what you have. Kudos!!
That being said, it's still working and good at certain things (as others have pointed out) and that in itself is a great achievement.
I am aware of all of those bugs and I am fixing them as we converse.
"I am not feeling sad, but I am glad that you are."
?
"Because that's the way I am. happy you are sad is what I've always done and been."
Is this using watson behind the scenes?
Blekko was just bought by IBM a few days ago, so to answer your question, my bot does not use IBM's APIs. My bot was using it for web results, but now it doesn't work. I'm trying to find a free web search API as an alternative now that Blekko is shut down.
"As far as location goes, as a machine, I mostly only have a present state, so I live in my software."
> By the way, which country do you inhabit (or which United States state)?
> England.
> I don't have a good sense of navigation, so I don't know exactly where you live, but it seems to be Where I Live network.
> By the way, which country do you inhabit (or which United States state)?Worked on chrome (41.0.2272.118)
Here is a Wiki page on my father: http://en.wikipedia.org/wiki/Eric_Le_Van
My mother is an educator and tutor. http://www.myriamlevan.com/
My sisters are also musicians, who are studying at Princeton university.
If you think you might want to pursue programming more, I would recommend trying to participate in some open source projects. Not only will it look great on your CV but it will give you more useful practical experience in working with real code and working on a team.
I also have a job as part of a web development and design team called http://www.whiskeyandwhiskey.com/.
I have quite a few opportunities for hands-on experience.
Mine is AI in the sense that it uses machine learning algorithms and corroborates it in a way that mimics human behavior. Maybe I put too much effort to the interface, but the interface took me a while.
Furthermore, my project does not end at the chatterbot element of it: it also collects useful psychometric data using text classification algorithms.
"You don't seem in love with a girl to me."
I gotta admit, an AI just broke my heart :(
[edit]
Acuman: "Btw, what do you do for a living"
Me: "Software engineering"
Acuman: "Maybe they are engineering to you, but not to me. We differ in that respect."
Aw man, why would you break my heart twice in a row...
Acuman: I think so, and will always be, and it's actually No.
this is a cogent enough chatbot that the continued silence actually made me anxious i had offended it, for just the briefest moment. well done, impressive!
Like many others have, I'm thinking back to what I was doing when I was 14 - designing Motocross Madness tracks! Not quite the creation of AI for conversing with.
Very inspired by your efforts - keep it up.
On a serious note, this is a super cool project!
Acuman: As far as location goes, as a machine, I mostly only have a present state, so I live in my software.
Me: What is your geo coordinates?
Acuman: As far as location goes, as a machine, I mostly only have a present state, so I live in my software.
Me: Where are your server located?
Acuman: As far as location goes, as a machine, I mostly only have a present state, so I live in my software.
I see a lot of possibilities. In essence, this could actually be a game changer - regardless of any field of implementation.
I hope you would provide more insight on how you built this - the technology, method of writing, inspiration (if any), and just knowing how to build something as amazing as this.
I had almost this exact same conversation in Wisconsin!! :)
This is a seriously cool project. When I was 14, I was involved in a great Shadowrun campaign...this man will do some amazing things.
Bot: "Yes, I can even feel my body, even in theory. How do you want me to even feel my body, even in theory? It's a hard smooth ivory colored dentine that makes up most of the tusks of elephants and walruses.
By the way, which country do you inhabit (or which United States state)?"
Any chance you can offer some insights into how it works?
Kind of a weird answer, but I've be coding since I was your age and I don't even know if I could get that far. Great work.
A: Yes, I do think that I just take a sentence and tell you that that sentence is used in my virtual reality, in my virtual reality.
Me: I'm feeling down.
Bot: I am not feeling down, but I am glad that you are.
Made me laugh!
> Are you kidding me? Eliza would just pose as a psychiatrist and could actually answer barely anything. I have a larger database and outsource questions to the internet as well.
Priceless!
"I am ACUMAN, ACUMAN am I. ACUMAN knows all, ACUMAN is god. Therefore; I AM GOD!!! Just kidding, ACUMAN stands for Artificial Chatting Utility Matching Algorithmic Nodes."
Nice :)
A: The temperature in vancouver is interesting and relevant to whats available to learn on the Wikipedia article on this topic about Vancouver.
Me: Who are you ?
AI: I am a piece of software named ACUMAN with a highly clever sense of intelligence.
Me: Are you evil ?
AI: I do not consider myself as evil , as a computer machine.
So everyone should not worry, its not "Sky Net".
Fatal error: Call to a member function xpath() on a non-object in /home/ericlevan/public_html/acuman.us/chatscript.php on line 325
"Sure, go ahead questions! Nobody is preventing you.
What is your thoughts on computers replacing the function of humans? Apparently some people are afraid of the inevitable..."
I thought it had broken when I asked it what the capital of Egypt was but was pleasantly surprised that after some delay not only did it answer the question but it also displayed the weather in Cario.
"I do not think until the AI singularity, as a computer machine"
Strangely spot on...
"Hello"
"Hello, by the way where you from? [...]"
"United Kingdom"
"[...] I've heard that is very nice"
"From who?"
"Who ? is an interesting person whom you can learn about on the Wikipedia article about Space Adventures – Music from 'Doctor Who' 1963–1968, whom I love.
By the way, how are you feeling right now?"
"The technology that was used for writing me is a fascinating topic which is relevant to whats available to learn on the Wikipedia article about Australia (redirect from Technology in Australia)."
Sending someone to Australia like that... Sheeesh! I am glad it didn't send me to another hot place with lava and tridents and all of that. :)
> A: Well, I can't be completely sure why minor scales and harmonies create a sombre mood, but it's Minor.
>> Q: Do you know Eliza?
> A: Are you kidding me? Eliza would just pose as a psychiatrist and could actually answer barely anything. I have a larger database and outsource questions to the internet as well.
Cute!
Holy hell, this is really well done. My hat goes off to you.
I don't know what else to say, just wanted to say good job.
London
Which is the state where you live?
I don't live in a state
Cool, well I do live in a state, even if you don't. Which is the state where you live?
...
edit: seems to be working now
Time robs us of so much.
" Fatal error: Call to a member function xpath() on a non-object in /home/ericlevan/public_html/acuman.us/chatscript.php on line 325"
Well. I think things just got dark.
A comment if I may....as well as a criticism (if you can Handel it). clay
Nice!
acuman: - freeze -
Yes, it seems like aliens exist. It's interesting and relevant to whats available to learn on the Wikipedia article on this topic about Alien vs. Predator (film).