Show HN: I'm a 14 year-old dev who has programmed an artificial intelligence bot
acuman.us
acuman.us
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
A child prodigy has the potential to be successful at any point in their life. It could be both a blessing and a curse to push for 'winning' so much acclaim at a young age.
Ermmmmm wouldn't they want to expand that into cocker spaniel...lol.
Don't forget, he knows latin.
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!
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.
Pedantic, but you can't. Unique is not a gradable adjective. This is not just my opinion :
http://blog.oxforddictionaries.com/2012/05/an-extremely-most...
http://learnenglish.britishcouncil.org/en/grammar-reference/...
https://www.englishclub.com/grammar/adjectives-gradable-non....
> we wouldn't have expressions like "totally unique" or the "most unique"
I wouldn't normally bring this up, but while we're being pedantic, there are lots of reasonably common expressions that exhibit gratingly poor grammar or sematics. You have quoted two of them above.
> unique means the quality of differing from other things, and this is a continium.
Ah no. Unique means "one of a kind", not merely "differing". "uni" as a prefix means one, e.g unicycle, universe, unitard. "one of a kind"-ness is not continuous! As per the second link, "unique" already contains the idea of "very different".
I don't use "unique" that way. Do you want "unique" to be just a redundant synonym for "different" or not?
I could care less.
Maybe you could, but I could not ;)
Nor are there "multiple languages". There's one language and in that language, unique IS used that way by some (most) people.
The cat's out of the bag.
Maybe not, but it is about what I do or don't say.
> Nor are there "multiple languages". There's one language
I don't think so, actually. There are differences in usage e.g. from. US to UK.
"My matter hath no voice, to your own most pregnant and vouchsafed ear." -- Viola, "Twelfth Night"
"It just means what I choose it to mean" is the basis of Relativism.
Could Humpty Dumpty say "I like ice cream" and mean "atoms are actually divisible"? If not then does that mean your argument is a boatload of crap?
Humpty is a great story: http://sabian.org/looking_glass6.php, it's a wonderful exploration of meaning and usage.
But I'll unpack some of here.
Here's the lead up to the quote I gave:
"[Humpty said:] As I was saying, that seems to be done right — though I haven't time to look it over thoroughly just now — and that shows that there are three hundred and sixty-four days when you might get un-birthday presents —'
'Certainly,' said Alice.
'And only one for birthday presents, you know. There's glory for you!'
'I don't know what you mean by "glory",' Alice said.
Humpty Dumpty smiled contemptuously. 'Of course you don't — till I tell you. I meant "there's a nice knock-down argument for you!"' 'But "glory" doesn't mean "a nice knock-down argument",' Alice objected."
I think it is clear that Humpty's meaning was quite obvious, and Alice's complaint a bit dense. But while Humpty insists that he must tell Alice what he means, we can see that he needn't.
Of course, this word commanding business is as dangerous as you note, and Lewis Carroll is on the case:
"Alice was too much puzzled to say anything; so after a minute Humpty Dumpty began again. 'They've a temper, some of them — particularly verbs: they're the proudest — adjectives you can do anything with, but not verbs — however, I can manage the whole lot of them! Impenetrability! That's what I say!'
'Would you tell me please,' said Alice, 'what that means?'
'Now you talk like a reasonable child,' said Humpty Dumpty, looking very much pleased. 'I meant by "impenetrability" that we've had enough of that subject, and it would be just as well if you'd mention what you mean to do next, as I suppose you don't mean to stop here all the rest of your life.'
'That's a great deal to make one word mean,' Alice said in a thoughtful tone.
'When I make a word do a lot of work like that,' said Humpty Dumpty, 'I always pay it extra.'"
On the one hand, words can have many meanings, and any particular meaning must in part be taken from context. On the other hand, if we just try to _impose_ a meaning on a word, we defeat all communication, and make ourselves ridiculous to boot.
That doesn't work when people are exchanging ideas on a forum and not everyone has read the same body of work. Because of the difficulty inherent in estimating who has read what, it is usually smart to avoid arguments "from the arts".
> allowing us to use quotes as "pointers" to ideas much larger than anything we could state briefly.
Larger than you could state briefly. Plus, aphorisms exist to fill in the gap you're talking about - all the benefits of brevity without the need for previous literary knowledge.
The excerpt you quoted reads like a boring story about a character that suffers from an affectation that makes him (her?) obsessed with trying to find reasons for using words loosely. I also didn't understand what he/she meant by "there's glory for you" even after the supposed explanation of what "glory" means in Dumpty's head.
"'If you can see whether I'm singing or not, you've sharper eyes than most,' Humpty Dumpty remarked severely."
If you think "Alice In Wonderland" is boring, you're missing out.
Read How to Speak and Write Correctly by Joseph Devlin for several instances of where Shakespeare made English mistakes and how to actually write correct English without appeal to authority.
That argument works, though, if we were speaking a language with a regulating body, such as French or Portuguese. Those regulating bodies define their languages in such a way that the "famous writers" never make mistakes. That's not the case with English. Let's keep English real. Shakespeare made several mistakes, read Devlin's grammar.
There are, therefore, no hard and fast authorities on English usage. English has principles and precedents, but not rules, and good writing is that which uses or violates those principles to communicate effectively. Shakespeare isn't an authority on usage, he's a compendium of examples of how usage can be harnessed for expression.
Now following those principles, and leveraging the readers' understanding and usage of them, allows far more expressive sentences. Gibbon writes enormous sentences that are clear as water and more efficient than any possible revision. Lincoln, by mastery of grammar, was able to express himself both powerfully and precisely. But the rules are in the service of expression, and good writers depart them when they don't permit the expression of what they want to say.
Complaints about the "mistakes" of great authors are generally mistakes about what the other meant to say, or insistence on some compliance that would damage brevity or power or nuance without adding any clarity. On ten minutes googling Devlin, I couldn't find a single "mistake" whose correction would clearly improve the sentence. Several of his examples miss the point, or weaken the sentence.
But if you want an authority, go to C.S. Lewis:
"About amn't I, aren't I and am I not, of course there are no right or wrong answers about language in the sense in which there are right and wrong answers in Arithmetic. . . . Don't take any notice of teachers and textbooks in such matters. Nor of logic. It is good to say "more than one passenger was hurt," although more than one equals at least two and therefore logically the verb ought to be plural were not singular was!"
http://www.lettersofnote.com/2012/04/c-s-lewis-on-writing.ht...
"More than one person is" is correct not because of any systematic reason, but because of euphony - it is more pleasing to the ear than "more than one person are". That, and whether the communication was effective, are the rulers of languages. That's how we got to where we are and how we go to where we are going. Not with central bodies regulating languages and not with language authorities we must emulate or check our usage against.
> Complaints about the "mistakes" of great authors are generally [...]
Yes, a lot of people have trouble accepting that even the greats make mistakes.
>However, sometimes the situation isn’t so cut and dried. There’s a set of adjectives (including perfect, infinite, and unique) which fall into both categories, gradable and absolute. (...)
>(...) unique has developed a weaker, less precise meaning: ‘very remarkable, special, or unusual’. The historical Oxford English Dictionary first records this sense in the 19th century, and it’s now well established. The ‘very remarkable or special’ meaning is not an absolute concept and is therefore gradable, so it’s grammatically acceptable to use modifying adverbs:
√ I saw a guy wearing some really unique eyeglasses. √ They’ve devised a highly unique way to cook and serve meals.
http://blog.oxforddictionaries.com/2012/05/an-extremely-most...
The letter "R" is unique in the English alphabet. The particular grain of sand in the palm of my hand is unique to the world's beaches.
Are "R" and this grain of sand equally unique? Might there be a way to compare them?
I don't want to debate the point, rather to pose the question and see what any responses might illuminate.
Have a nice day. :)
I think that, from context, it was clear I was using "pregnancy" to mean "the state of being pregnant" and not referring to the nine month gestation period.
That'll teach me to contribute to pedantry-focussed subthreads. :-)
Hella Nor Cal or Totally So Cal? The Perceptual Dialectology of California
http://eng.sagepub.com/content/35/4/325.abstract
http://people.duke.edu/~eec10/hellanorcal.pdf
This study provides the first detailed account of perceptual dialectology within California (as well as one of the first accounts of perceptual dialectology within any single state). Quantitative analysis of a map-labeling task carried out in Southern California reveals that California's most salient linguistic boundary is between the northern and southern regions of the state. Whereas studies of the perceptual dialectology of the United States as a whole have focused almost exclusively on regional dialect differences, respondents associated particular regions of California less with distinctive dialects than with differences in language (English versus Spanish), slang use, and social groups. The diverse sociolinguistic situation of California is reflected in the emphasis both on highly salient social groups thought to be stereotypical of California by residents and nonresidents alike (e.g., surfers) and on groups that, though prominent in the cultural landscape of the state, remain largely unrecognized by outsiders (e.g., hicks).
[...]
By far, the most frequently remarked-upon slang term in the map-labeling data was hella, accounting for 47.4 percent of the slang and other lexical labels. Hella is a slang term originating in Northern California and one that remains—aside from a few brief moments in the national spotlight due to its circulation in popular culture— largely restricted to that region (Bucholtz 2006). The term, which apparently lexicalized from (a) hell of (a), functions as both a quantifier (There were hella people there) and an intensifier (He runs hella fast). Four respondents also mentioned the slang term hecka, the G-rated equivalent of hella, but this term was not counted separately, because tokens of hecka always co-occurred with hella. For Southern Californians in particular, hella represents a crucial shibboleth separating the two major regions of the state. As shown in Figure 7, respondents tended to identify hella overwhelmingly as a Northern California slang term, and its appearance in other regions of the map drops dramatically from north to south. Thus Northern California was variously labeled the hellas, Land of the Hella’s, and Hella capital, and one respondent provided an isogloss designating “the ‘hella’ line.” (In the map data, the Central Coast around Santa Barbara seemed to be the dividing line between users and nonusers of hella, and the fact that the study was conducted in this region may have enhanced respondents’ focus on this particular issue.) [*10: The respondent’s confusion may also be due to the existence of the Crips, a notorious Los Angeles–based gang.] Hella users were also negatively evaluated by Southern Californians, and the term came in for a good deal of criticism, such as Hella is not a real word and [hecka is] probably the worst word ever.
Pedantry is attention to compliance with usage "rules" rather than the success of the expression.
Your English is far, far better than my command of whatever your native tongue is.
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.
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.
"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...
Your gender or your age should not have impact on what you do!
1) From the perspective of the Turing Test, it biomimics human behavior and intelligence.
2) The field of artificial intelligence deals with a computerized comprehension of data. ACUMAN is heavily dependent on machine learning, natural language processing, and text classification algorithms, which facilitate understanding. It also gathers psychometric data, which allows the machine to take its communication with a participant in context of their personality.
3) A computer able to interact with a human in a similar way that a human would with another human. ACUMAN matches this definition because it accepts and can converse in both speech input and text input, all in the english language and manifesting its "intelligence" in the form daily communication.
The project qualifies to all three of these pieces of criteria.
Re 1. Yes, it does attempt to pass the Turing test.
Re 3. Yes, that includes interacting with a human in a similar way that a human would with another human, that's part of the Turing test.
My own experience was: it asked me how I was, I told it I had a hangover, it thought that was great and that I was 100% happy. Which wasn't a long test. Obviously your own experience might have varied.
Re: 3. Isn't machine learning just machine learning and NLP just NLP?
I personally don't feel like my app suddenly becomes 'AI' if I import nltk and start tokenising some corpus to train it with, or load opencv and tell my drone to avoid the big red thing. If the app would work out how to /train itself/ I would consider it an AI.
Eg, the drone having the objective to follow me at a safe distance for as long as possible, then working out that the big red thing is dangerous and avoid it.
Or the chat both to, say, have an objective of beating the human at the turing test for a certain amount of time, then working out how it gives itself away, then avoiding doing that.
I acknowledge that's just a feeling though, and many definitions online would qualify 'thing that loads library and needs human training' as AI.
However I can't help but think that's going to promote the Reading University 'captain cyborg' school of cranks.
Honestly, I would say "chatbot" is a class of primitive AI - I'd also class Eliza as an (extremely) primitive AI.
I feel like you're making a distinction without a difference because you have some arbitrary barrier in mind for "sufficiently non-primitive to have earned the term AI" and are then applying that.
Would "a chatbot with primitive AI capabilities" seem like a reasonable compromise definition?
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.
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
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.
"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."
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
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?
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."
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
His bot just said this, though:
"It's I know a fair bit."
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.
> "Of all people you should appreciate 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.
Everything is made from scratch. From the ground-up. I could have used AIML (the AI version of XML), or anything I wanted. But instead, to make it unique and customizable to the demand of this project, I created my own markup language entitled ACUMANSCRIPT. Even the sentiment analysis algorithms are made from scratch by using Naive Bayens algorithms. The only APIs in use are those for some aspects of the knowledge base, which is a must in any machine learning or artificial intelligence project, as not leveraging the massive amount of data available on the internet would be a waste.
I sincerely doubt that we are anywhere near a flawless piece of artificial intelligence software, but this is not a result of people's lack of diligence in the field, but rather a testimony to it's complexities.
Google has made a short documentary explaining why natural language processing and machine learning are some of the hardest fields due to their surprisingly complex nature:
... doubt that we are anywhere near a flawless piece
of artificial intelligence software, but this is not
a result of people's lack of diligence in the field,
but rather a testimony to its complexities.
... a quick glance at the "read more" page on the
technologies ...
Here is the URL: http://acuman.us/readmore.php
I decided that AIML was not useful to me because it was too rigid in syntax and was too static. This is particularly in the manner in which most AIML interpreters parse the syntax, making a rigid "if hello is in string, then say nice meeting you" syllogism (basically a beefed-up conditional statement) that essential has no room or place in actual artificial intelligence. I could have adjusted it to match my needs by creating my own interpreter, but I thought if I was going to accomplish that, why not create my own syntax that matches my needs better and has syntax that is even less convoluted and more focused on pattern-matching and machine learning?
I thought of releasing an API where you can code using the syntax of ACUMANSCRIPT- but I am unfortunately not prepared for open-sourcing ACUMAN's main architecture code due to it still competing in contests and fairs.
My ideas are definitely half-baked and may be completely wrong/useless/inappropriate, or it may even be that you prefer to continue to work largely independently. That's not a bad thing, as getting input from other people may stifle your own creativity and ideas.
Regardless, thanks for the responses and for the interesting project.
Since you wrote the entire thing, you could AGPL it for now and then pick a less restrictive license later.
(could, is, of course, not should, but it's an option people don't always consider)
I do not care about speech recognition when we are talking about AGI.
I care about AGI being able to understand written text - the most natural form of communication between humans and AGI.
The problem is that AGI is not able to understand written text well, cannot build good mental models and cannot make meaningful decisions based on them.
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."
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.
e^i(pi)+1
(pi * (e^i) ) + 1
2.69740975.. + 2.64355906... i
And sqrt(i) is sqrt(sqrt(-1)) which is (-1)^(1/4), so again, it was right (excepting that it put "you" instead of "i")
So it did better than you think.
just one drop of the sense of humor maybe :)
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.
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.
Throwing your answer back at you, criticizing your question, or playing with humor is a fun little trick, but certainly not AI.
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?
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
Acuman: I think so, and will always be, and it's actually No.
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.
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!
I am reposting it because it has been changed significantly since then in almost every respect, both algorithmically and in the concept.
"What is my account on hacker news? I don't actually have a account on hacker news, as a computer machine."
Acuman denies.
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++ ?
The "about page" reflects the "old" concept, as stated on this new page: http://acuman.us/readmore.php
The syntax of the ACUMANSCRIPT markup language is actually more similar to XML (or, in the AI field, AIML) due to its rigid structure. It's fundamentally based on pattern matching akin to regex. However, the backend processing which alters ACUMANSCRIPT and processes the individual data is what makes it unique.
The knowledge base used for the Named-entity recognition for the processing of ACUMANSCRIPT is Wikimedia and WolframAlpha, used in conjunction.
It is all processed in the backend using PHP.
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.
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.
Most of the "conversation" was about this level.
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
-1: efficient/organized
-2: easy-going/careless
-1: outgoing/energetic
-2: solitary/reserved
-1: friendly/compassionate
-2: analytical/detached
-1: sensitive/nervous
-2: secure/confident
I'll consider implementing one of those options. Thank you for your feedback.
If you think about it, people are voluntarily disclosing all things about themselves which can be stored and sold on.
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 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. :)
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?
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.
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.
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.
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.
Me: I'm feeling down.
Bot: I am not feeling down, but I am glad that you are.
Made me laugh!
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.
> 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.
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.
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.
"I do not think until the AI singularity, as a computer machine"
Strangely spot on...
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.
"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?"
I am capable of universal computation; that I can say.. . I'm pretty good at subtraction, I tell you!
---------------- We are not doomed yet :-)
"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!
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!
That is one of the purposes of ACUMAN, to gather psychometric data to build a profile on an individual.
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.
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?
> ACUMAN: Tell me what US state you live in.
> MILLOY: New Hampshire, but I'm moving to North Carolina soon!
> ACUMAN: You do not seem to be moving to North Carolina soon to me.
> MILLOY: You are very sceptical then.
> ACUMAN: I do not consider myself to be very sceptical, but to each his own. Though I respect your opinion.
> MILLOY: You don't believe what I tell you, so you are sceptical.
> ACUMAN: You may think that, but I think that I believe what you tell me.
I also got: "I'm at work right now" > "You don't seem to me at work right now to me" which is also not exactly an opinion.
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.)
I can't speak from experience, all I know is that the fellowship supports bright young talent much like you.
Anyhow, keep up the amazing work!
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.
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?
...
I am aware of all of those bugs and I am fixing them as we converse.
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"
"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.
>tell me a joke >>What's the difference between a feminist and a computer? >>You can punch information into a computer.
If you don't see what is wrong with that, ask around.
"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)?In fact, ACUMAN beat the ALICE bot in the last Chatterbox Challenge by over 20 points, winning the "Best New Bot" prize.
Well. I think things just got dark.
A comment if I may....as well as a criticism (if you can Handel it). clay
I assure you that's not the problem. :) I was tampering with a source code, and simply incorrect PHP syntax (a missing bracket) broke it for a few minutes.
It's In[1]:= Speak[youve].
Worked on chrome (41.0.2272.118)
Nice!
acuman: - freeze -
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.
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).