Beta
×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

Wolfram Promises Computing That Answers Questions

timothy posted more than 5 years ago | from the he's-feeling-lucky-you-feel-lucky-too dept.

The Internet 369

An anonymous reader writes "Computer scientist Stephen Wolfram feels that he has put together at least the initial version of a computer that actually answers factual questions, a la Star Trek's ship computers. His version will be found on their Web-based application, Wolfram Alpha. What does this mean? Well, instead of returning links to pages that may (or may not) contain the answer to your questions, Wolfram will respond with the actual answer. Just imagine typing in 'How many bones are in the human body?' and getting the answer." Right now, though the search entry field is in place, Alpha is not yet generally available -- only "to a few select individuals."

Sorry! There are no comments related to the filter you selected.

Lojban (2, Interesting)

Sybert42 (1309493) | more than 5 years ago | (#27115369)

I don't think this can be examined without language issues. Lojban attempts to make a parsable constructed language (currently undergoing a few grammar issues, but mostly locked down). As we get closer to the Singularity, with regards to infant-style general AI and perhaps even transhuman implants (thought detector or such), we'll see perhaps a myriad of unambiguous languages.

Re:Lojban (2, Funny)

msuarezalvarez (667058) | more than 5 years ago | (#27115477)

There is no need to fully parse natural languages (or to substitute them with made up languages you can parse...) in order to answer questions posed in natural languages. Indeed, one does not need to *understand* a question (in whatever AI meaning you want) in order to find its answer.

Re:Lojban (3, Insightful)

goombah99 (560566) | more than 5 years ago | (#27115583)

is the answer to this question "no"?

If you want to answer a question without understanding the question then how do you know when the question can be answered?

Re:Lojban (1, Insightful)

poopdeville (841677) | more than 5 years ago | (#27115599)

You look for an answer until you find it or give up.

Re:Lojban (4, Funny)

linhares (1241614) | more than 5 years ago | (#27115871)

You look for an answer until you find it or give up.

Oh, so (i) you don't understand the question, then (ii) you look for an answer, (iii, A) you find it (how? how will you know you found it?), or (iii, B) you give up.

Just wanted to make sure that this thread was really about this. Here's a new low, even for slashdot.

Re:Lojban (-1, Flamebait)

poopdeville (841677) | more than 5 years ago | (#27116257)

I am not answering the questions goomba99 was referring to. A computer is. And a computer does not need to "understand" a question in order to answer it. It searches through data sets or computes results in order to answer questions, presumably generating the computations from an appropriate formal question asking language. This process is "undecidable" -- as a consequence, you cannot know if a question can be answered at all, until you TRY.

Good job looking like an asshole, asshole.

Re:Lojban (1)

linhares (1241614) | more than 5 years ago | (#27116297)

Hi twitter, didn't know it was you.

Re:Lojban (3, Interesting)

fractoid (1076465) | more than 5 years ago | (#27116179)

To my mind, any reasonable definition of understanding a subject includes the ability to reason based on information about the subject. In the case of a question, this would include the ability to say, at the very least, whether a given answer is a correct answer for the question.

From this, we can see that if we can build a reasoning engine that can determine if a given answer is correct for a question, hypothetically we can iterate over a large set of answers and apply our filter to each one. This provides us with a machine to answer questions (although depending on the size of the set of answers, "I don't know" might be a frequent response) which (by my definition, at least) 'understands' the question.

Re:Lojban (1)

Thinboy00 (1190815) | more than 5 years ago | (#27116203)

is the answer to this question "no"?

[snip]

five.

Re:Lojban (4, Funny)

Bandman (86149) | more than 5 years ago | (#27116281)

three, sir

Re:Lojban (1)

home-electro.com (1284676) | more than 5 years ago | (#27115609)

It is useless thing even if it works as advertised. I can find an answer to "how many bones" much faster by typing "bones human body" and then quickly glancing through google search results to select a page that will have an answer.

Typing the complete question takes longer, and there is also a question of the information source. With search results you can always select a page that you trust to be accurate. With this thing -- I am not so sure.

Re:Lojban (1)

Bandman (86149) | more than 5 years ago | (#27116295)

But asking the question is so much easier than coming up with the magical query which will return the right "I'm feeling lucky" result, which is really the answer you want.

Re:Lojban (4, Funny)

gardyloo (512791) | more than 5 years ago | (#27115523)

I don't think this can be examined without language issues. Lojban attempts to make a parsable constructed language (currently undergoing a few grammar issues, but mostly locked down). As we get closer to the Singularity, with regards to infant-style general AI and perhaps even transhuman implants (thought detector or such), we'll see perhaps a myriad of unambiguous languages.

Your cautiousness and pragmatism in the first two sentences was noted and admired. Then you used the word Singularity in the Vinge sense, and my woo-detector pegged.

Re:Lojban (3, Interesting)

dkf (304284) | more than 5 years ago | (#27115527)

I don't think this can be examined without language issues. Lojban attempts to make a parsable constructed language (currently undergoing a few grammar issues, but mostly locked down). As we get closer to the Singularity, with regards to infant-style general AI and perhaps even transhuman implants (thought detector or such), we'll see perhaps a myriad of unambiguous languages.

Any language that is truly unambiguous is uninteresting. Firstly, you've got Goedel incompleteness to worry about (which stems from statements that are fundamentally ambiguous as to their interpretation, such as "this statement is false"). Secondly, languages are there for people to communicate with, and people seem to prefer ambiguity. Ask a poet if you need proof of that.

"When are you going to crash?" (3, Funny)

AliasMarlowe (1042386) | more than 5 years ago | (#27115531)

Either:
1. Windows version of program crashes without answering
2. Mac version of program says "after your next question, smartass"
3. Linux version of program says never, 'cos it can't even drive a car

Re:Lojban (2, Funny)

linhares (1241614) | more than 5 years ago | (#27115823)

"will you answer no to this question?" kernel panic

Re:Lojban (3, Interesting)

HiThere (15173) | more than 5 years ago | (#27115977)

Are you limited to yes/no answers?

Why are people presuming that the program will be limited to yes/no answers?
Q: Will you answer no to this question?
A: It's rather unlikely.

(Or, "I doubt it" or any of several different answers.)

There are enough legitimate paradoxes that you don't need to construct such obvious losers.

How about:
Is "This statement is false." false?

It's still easy enough to handle (in several different ways), but at least it's a valid challenge.

Re:Lojban (2, Funny)

linhares (1241614) | more than 5 years ago | (#27116173)

Why are people presuming that the program will be limited to yes/no answers? Q: Will you answer no to this question? A: It's rather unlikely. (Or, "I doubt it" or any of several different answers.)

Q: What made you think it's rather unlikely? kernel panic

Re:Lojban (1)

Bandman (86149) | more than 5 years ago | (#27116305)

Are you implying that the computer hasn't been programmed to lie?

How many bones (4, Interesting)

icebike (68054) | more than 5 years ago | (#27115391)

Q: How many bones are in the human body
A: Did you mean cumulatively or at any point in time?

Re:How many bones (5, Funny)

Anonymous Coward | more than 5 years ago | (#27115433)

Q: How many bones are in the human body?
A: Did the human in question eat fish recently?

Re:How many bones (1)

DMUTPeregrine (612791) | more than 5 years ago | (#27115947)

Q: How many bones are in the human body? A: Did the human in question have a recent encounter with 2 mafia men and a baseball bat?

Re:How many bones (0)

Anonymous Coward | more than 5 years ago | (#27115491)

A: Who said anything about a body?
Aren't they still looking for her?

Re:How many bones (1)

micromuncher (171881) | more than 5 years ago | (#27115539)

Actually a good point; bones fuse over time so children have more bones than adults.

Then again, this kind of system will fall out of favour as soon as it delivers incorrect answers, especially when there is a clear context.

I like answers like SAL in 2010...

Re:How many bones (2, Funny)

PrescriptionWarning (932687) | more than 5 years ago | (#27115573)

A: Adult content detected, please submit age verification to see the answer.

Re:How many bones (5, Funny)

something_wicked_thi (918168) | more than 5 years ago | (#27115595)

Q: How many bones are in the human body?
A: How does bones are in the human body make you feel?

Re:How many bones (1)

SolusSD (680489) | more than 5 years ago | (#27115993)

Why hello doctor! Glad to see they're giving you a bit of exposure outside of our mid-coding help sessions.

Re:How many bones (0)

Anonymous Coward | more than 5 years ago | (#27116277)

Your response rocks. Thanks for the hearty laugh :)

Re:How many bones (2, Interesting)

davester666 (731373) | more than 5 years ago | (#27115617)

Wasn't this done? answers.com, askjeeves.com (now ask.com)

Re:How many bones (2, Informative)

linhares (1241614) | more than 5 years ago | (#27115909)

Wasn't this done? answers.com, askjeeves.com (now ask.com)

the answer to your question is yes.

There's also the pathetic Powerset [powerset.com] , which was sold to microsoft for 100 million bucks [venturebeat.com] . Very pleasing see ms burning money on such hyped shit.

Re:How many bones (1, Funny)

macraig (621737) | more than 5 years ago | (#27115649)

My buddy Guido can reduce the number.

Re:How many bones (0)

Anonymous Coward | more than 5 years ago | (#27115715)

Wouldn't he be more likely to increase it?

Re:How many bones (1)

ckthorp (1255134) | more than 5 years ago | (#27115911)

Not if he's cutting off fingers...

Re:How many bones (1)

solafide (845228) | more than 5 years ago | (#27115957)

melelaswe@localhost ~ $ python
Python 2.5.2 (r252:60911, Dec 11 2008, 09:55:54)
[GCC 4.1.2 (Gentoo 4.1.2 p1.0.2)] on linux2
Type "help", "copyright", "credits" or "license" for more information.
>>> reduce(the,number)
42

Re:How many bones (1, Funny)

Anonymous Coward | more than 5 years ago | (#27115887)

Q: How many bones are in the human body
A: What do you mean? An African or European body?
Q: Huh? I... I don't know that. [NO CARRIER]

Oblig (1)

4D6963 (933028) | more than 5 years ago | (#27116191)

Q: How many bones are in the human body
A: What do you mean, an African or European human?

Re:How many bones (1)

fractoid (1076465) | more than 5 years ago | (#27116207)

"You should have one more bone in your body... want me to help?" ;)

Re:How many bones (0)

Anonymous Coward | more than 5 years ago | (#27116291)

Q: How many bones are in the human body?
A: *IN* the human body? Well, men can have a maximum of two (one in the rear, one in the mouth), while women can have at most three (rear, mouth, vaginal).

Oh, does that say "bones"? I misread "boners". :'(

"where is the source" (1)

nurb432 (527695) | more than 5 years ago | (#27115393)

Odd, i didn't get an answer.

Simple: (4, Funny)

kbrasee (1379057) | more than 5 years ago | (#27115395)

package com.wolfram;

public class Alpha {

    public static void main(String[] args) {
        System.out.println("42");
    }

}

Re:Simple: (1)

DavidD_CA (750156) | more than 5 years ago | (#27115797)

Six minutes for the inevitable Deep Thought joke?

We're slacking.

Anyone remember AskJeeves? (3, Informative)

SirLurksAlot (1169039) | more than 5 years ago | (#27115411)

Been there, done that. [ask.com]

All that is old is new again.

Re:Anyone remember AskJeeves? (0)

Anonymous Coward | more than 5 years ago | (#27115519)

It's interesting, but not that new. Maybe I haven't dug deep enough, but it looks similar to a lot of existing work.

This project came to mind, and it's been around at least a couple of years... http://chnm.gmu.edu/tools/h-bot/

Nope. (1)

captainboogerhead (228216) | more than 5 years ago | (#27115557)

Ask Jeeves fails if you simply substitute one word:

How many bones are in the parrot's body

The reason? It doesn't actually know anything.

If you RTFA, you'll see that something entirely different is being discussed here. Alpha is supposed to actually answer the question because it knows a lot of facts, not because it's been programmed to look for certain phrases and respond with certain strings of text.

It's not a search engine, it's a calculator.

Re:Nope. (5, Informative)

captainboogerhead (228216) | more than 5 years ago | (#27115585)

Actually, the original source, TechCrunch [techcrunch.com] , not the dumbed down linked article, discusses in much better detail what Alpha is about.

Re:Nope. (1)

retchdog (1319261) | more than 5 years ago | (#27115641)

I guess you can call that "detail". I call it a fawning press release.

Still, from what I read it's a proprietary summary of a lot of expert knowledge with a token cellular automaton thrown in somewhere to satisfy Wolfram's ego. Prediction: fades from prominence within a year of release, as 1) the summarized knowledge goes out of date and can't be maintained in realtime (human labor required too expensive); and 2) knockoffs emerge.

Re:Nope. (4, Insightful)

SirLurksAlot (1169039) | more than 5 years ago | (#27115785)

It doesn't actually know anything.

If you RTFA, you'll see that something entirely different is being discussed here. Alpha is supposed to actually answer the question because it knows a lot of facts, not because it's been programmed to look for certain phrases and respond with certain strings of text.

Good points, but this is still just a different (better perhaps?) implementation of the same concept. The big issue with the implementation is that it will only "know" what you tell it, the same as any other computer. Further it will only be able to tell you about what you want to know based on the system's ability to parse your question and return what it "thinks" you want to know.

Look, I'm not saying it isn't a cool idea, I'm just saying that it isn't as shiny and new as the creator would lead you to believe. I'm also not inclined to be impressed considering that it isn't even available to try yet. It hasn't even been released yet.

Re:Anyone remember AskJeeves? (1)

Ian Alexander (997430) | more than 5 years ago | (#27115563)

IIRC AskJeeves just searched the web for you. This, according to the summary, tries to pull the answer to your question out of the web for you. IE, if you searched "how many rupees in a dollar?" AskJeeves would give you a link to a currency converter; this would, in theory, give you "50 rupees" (or whatever the exchange rate is now).

Re:Anyone remember AskJeeves? (4, Insightful)

Korin43 (881732) | more than 5 years ago | (#27115869)

Atomic mass of plutonium? [google.com]
Circumference of the earth [google.com] ?
Number of horns on a unicorn [google.com] ?

Google already does this. It's giving you the answer and linking to the page that has it. All Google needs is to be able to use these things in the calculator ("circumference of the earth in furlongs").

Oh and related to your "rupees in a dollar". "1 dollar in indian rupees [google.com] " will tell you.

A.I. (3, Informative)

unlametheweak (1102159) | more than 5 years ago | (#27115413)

Google already does this. Type a question like "What is one plus one?" and you will get an answer. It's artificial intelligence.

Re:A.I. (3, Interesting)

philgross (23409) | more than 5 years ago | (#27115549)

It goes further than that. Try Googling "how old is Britney Spears" and "what is the population of iceland" (without quotes). The answer appears at the top, separately from the search results.

Re:A.I. (2, Interesting)

am 2k (217885) | more than 5 years ago | (#27115627)

That seems to be hardcoded though, it already fails at "how old is Steve Jobs".

Re:A.I. (2, Interesting)

Anonymous Coward | more than 5 years ago | (#27115665)

It also fails on This [google.co.uk] - seriously...

Re:A.I. (0)

Vectronic (1221470) | more than 5 years ago | (#27116105)

Probably because it's not fact. The answer will always be estimation and speculation, no one knows, it's not January 17th 949,490,865 BC, like a humans birth date where depending on the hospital, may even be accurate to the minute.

Re:A.I. (1)

unlametheweak (1102159) | more than 5 years ago | (#27115721)

That seems to be hardcoded though, it already fails at "how old is Steve Jobs".

Any intelligent system that relies on knowledge of the world requires at least some "hard coding".

Re:A.I. (1)

Korin43 (881732) | more than 5 years ago | (#27115899)

The age isn't hard coded, there are probably just a small number of trusted sites (or maybe it needs to get a consensus?). How to figure out when a website is talking about age is probably hard coded though, unless Google already is Skynet.

Re:A.I. (1, Funny)

Anonymous Coward | more than 5 years ago | (#27116267)

Try asking what is the latest ubuntu release.

Sweet! (1)

hoytak (1148181) | more than 5 years ago | (#27115437)

The first question I'll ask it: "Is the Riemann Hypothesis [wikipedia.org] true?" The answer would probably be a good indicator of how useful the system will be.

Re:Sweet! (2, Interesting)

poopdeville (841677) | more than 5 years ago | (#27115687)

Isn't a proof of the Riemann Hypothesis necessarily non-constructive? If so, a computer can't answer your question.

Re:Sweet! (1)

Coryoth (254751) | more than 5 years ago | (#27115825)

Isn't a proof of the Riemann Hypothesis necessarily non-constructive? If so, a computer can't answer your question.

A computer can answer the question if the answer is that the hypothesis is false. A proof would indeed be non-constructive, but a counterexample is perfectly constructible (though there are theorems demonstrating that it has to be potentially computationally infeasibly large -- at least on current hardware).

Re:Sweet! (1)

hoytak (1148181) | more than 5 years ago | (#27115835)

Good point. The intent of my question is to gauge how well it replies to currently unanswerable questions. If it said: "I don't know, as a proof of the Riemann Hypothesis is necessarily non-constructive", then I would be quite impressed. If it says "I don't know what you mean; please rephrase", I'd be less impressed.

Re:Sweet! (1)

fractoid (1076465) | more than 5 years ago | (#27116311)

I'm pretty sure its response would be along the line of:

INSUFFICIENT DATA FOR A MEANINGFUL ANSWER.

Obvious joke... (0)

Zapotek (1032314) | more than 5 years ago | (#27115445)

I'd put up a form on my website that returns 42 regardless of input but I cba. So if you could just mod me +5 funny already that'd be just peachy...
/ducks

Can he do this for politicians, as well? (1, Insightful)

PolygamousRanchKid (1290638) | more than 5 years ago | (#27115497)

a computer that actually answers factual questions

I've never seen a politician who has been able to do that. But I guess they don't want to either.

Wolfram = Tungsten (1)

Zymergy (803632) | more than 5 years ago | (#27115501)

Maybe it should be called it "Tungsten"?
Tungsten has the symbol "W" from its original name, "Wolfram" (which comes from wolframite, one of the ores from which it is extracted.)
http://en.wikipedia.org/wiki/Tungsten [wikipedia.org]

Re:Wolfram = Tungsten (1)

msuarezalvarez (667058) | more than 5 years ago | (#27115553)

How do you know that Stephen Wolfram's last name comes from wolframite?

Yeah, but... (2, Funny)

Ieshan (409693) | more than 5 years ago | (#27115625)

Why would someone brand something that was supposed to be an intelligent machine as "W".

Computers are useless... (4, Insightful)

st0rmshad0w (412661) | more than 5 years ago | (#27115565)

...they only give you answers.

Re:Computers are useless... (2, Insightful)

MBCook (132727) | more than 5 years ago | (#27115725)

Questions are a burden to others. Answers are prison for oneself.

Re:Computers are useless... (1)

st0rmshad0w (412661) | more than 5 years ago | (#27116069)

Wow, I like that. Is that yours? Mine was Picasso I think, probably paraphrased.

WHO... DOES NUMBER TWO... WORK FOR?!?! (0)

Anonymous Coward | more than 5 years ago | (#27115571)

"What do you do, Number Two?"
"That's my business."

Let me guess, the most popular answer is... (1)

xactuary (746078) | more than 5 years ago | (#27115589)

42

A new kind of askjeeves... (2, Funny)

fuzzyfuzzyfungus (1223518) | more than 5 years ago | (#27115591)

Wolfram seems to be his, er, original self as always. Isn't phrasing search results in the form of a question old news by now?

Re:A new kind of askjeeves... (1)

solafide (845228) | more than 5 years ago | (#27115973)

Oh no! Timothy is turning into kdawson!

Just Imagine! (1)

quonsar (61695) | more than 5 years ago | (#27115603)

Just imagine typing in 'How is babby formed?' and getting the answer.

Deep Thought version 0.1? (1, Insightful)

FlyByPC (841016) | more than 5 years ago | (#27115631)

"What is the ultimate answer to Life, the Universe, and Everything?"

"Hmm. Tricky." ...


We miss you, Mr. Adams.

I hope this is what I think it is (2, Interesting)

physicsphairy (720718) | more than 5 years ago | (#27115651)

Trying to find mathematics/physics information is often pretty terrible. I mean, if you are just looking for a topic you can generally pull up related papers, but that is about the depth of complexity you are capable of searching for.

Unfortunately there is no convenient (or universal) plaintext notation. If you are doing anything serious you probably use latex markup (e.g., \Psi^{*}\Psi) or something similar to render images of your equations. That's well and good for people who just want to read your paper, but for people who want to do a complex search to find very specific bits of contextual information, it is just about useless.

So if I can hope that Wolfram's goal is to make his company's math and science knowledge base searchable by some sort of contextual framework, then that could be pretty awesome for those of us who would like to penetrate particular aspects of independent fields without having to become experts on the fields first.

Who is the greatest scientist? (1)

antispam_ben (591349) | more than 5 years ago | (#27115659)

I'm just wonderin' ...

Re:Who is the greatest scientist? (1)

solafide (845228) | more than 5 years ago | (#27116007)

Wolfram, obviously. It's why he came up with A New Kind of Science [wikipedia.org] , and not anyone else 20 years earlier.

All the Wolfram promises (2, Insightful)

basementman (1475159) | more than 5 years ago | (#27115673)

All that Wolfarm has promised here is a wall of text full of buzzwords. Until I can actually test this it's just another cuil.

Circularity (1)

macraig (621737) | more than 5 years ago | (#27115683)

What happens if I try to ask it when it will be available to the rest of us mere mortals? Does the web site or my head asplode?

This technology sounds pretty Cuil (0, Offtopic)

pHatidic (163975) | more than 5 years ago | (#27115731)

Just saying. :-)

The Devil is in the Details (1)

Raystonn (1463901) | more than 5 years ago | (#27115807)

Please note: Wolfram did not promise computing that *correctly* answers questions. Tribute to Douglas Adams: Perhaps his next endeavor should involve providing the question that goes with the answer.

Re:The Devil is in the Details (1)

linhares (1241614) | more than 5 years ago | (#27116127)

Please note: Wolfram did not promise computing that *correctly* answers questions. Tribute to Douglas Adams: Perhaps his next endeavor should involve providing the question that goes with the answer.

Makes sense now. Thanks.

OK, I've got a question for it. (1)

ettlz (639203) | more than 5 years ago | (#27115809)

"Who will lead mankind to victory in the war against the machines?" Eh?! Just hope the thing doesn't answer

##1 &

Seen this before? (0)

Anonymous Coward | more than 5 years ago | (#27115833)

Wolfram's a bit late to the chase:
http://start.csail.mit.edu/

Just Words (3, Insightful)

prefec2 (875483) | more than 5 years ago | (#27115847)

As long as they are not showing the tool to the public, I do not believe they build a system which promises that. However, there have been lots of research in this area and there are methods to convert queries into horn-clauses so you can query knowledge bases. I designed a method in my master thesis which does similar things, however it was laid out to be performed by humans.

As ingredients for such a system you need
- a knowledge base filled with facts (you can use OWL for it if you want or a rule based approach)
- a reasoner (e.g. something like pellet)
- a rule engine (e.g. something like Jess)
- a method which understands simple English query sentences.

The really hard part is the knowledge base, because it is lots of work. And an automated approach which can understand written documents and classify them correctly would be great, but I doubt that they found a solution for this problem.

This problem includes:
- How to handle uncertainty?
- What to do with contradicting knowledge?
- What to do with temporal aspects in that knowledge?

However, if they built a tool which can answer question of one single domain of knowledge, this is nothing new. Such machines exist now for a long time. They can be helpful, but there is nothing exciting about them.

Oblig (1)

JustOK (667959) | more than 5 years ago | (#27115913)

What is the air-speed velocity of an unladen swallow?

True Knowledge (2, Interesting)

Sanity (1431) | more than 5 years ago | (#27115981)

True Knowledge [trueknowledge.com] have been doing this for over a year. Anyone can add facts to their database, and it will attempt to use those facts to infer answers to questions. Its actually very cool, although doesn't yet support such notions as uncertainty.

quizbot (1)

AeiwiMaster (20560) | more than 5 years ago | (#27116057)

Well, quizbot from trueknowledge already does what
wolfram alpha promise to do in May.

http://quizbot.trueknowledge.com/ [trueknowledge.com]

An artist's opinion (maybe) (1)

Markrian (931172) | more than 5 years ago | (#27116071)

"Computers are useless. They can only give you answers."
-- Pablo Picasso (unsourced)

http://en.wikiquote.org/wiki/Picasso [wikiquote.org]

Deducing (1)

Lobais (743851) | more than 5 years ago | (#27116089)

I wonder if it will use a knowledge base, or if it will be able to, just like another famous answering machine, deduce the existence of rice pudding.

Can't wait (1)

Bootle (816136) | more than 5 years ago | (#27116119)

until they hit beta!

I Already Know the Answer (1)

CodeBuster (516420) | more than 5 years ago | (#27116155)

Its 43.

I asked Google... (1)

gatkinso (15975) | more than 5 years ago | (#27116209)

...The question "how many bones are there in the hunan body?"

In a poorly formatted answer embedded in a preview above a URL was this text:

"there are 206 in adults and up to 350 for infants"

I did not have to click on anyting to read this text - it was just there.

Me thinks we are already there,

Other attempts (1)

404 Clue Not Found (763556) | more than 5 years ago | (#27116321)

Isn't this what Cyc [cyc.com] /OpenCyc tried to do a while back with an incredibly complicated syntax, and also what true knowledge [trueknowledge.com] is currently trying to do with the general public (public demo here [trueknowledge.com] )?

I don't know... (4, Funny)

Cylix (55374) | more than 5 years ago | (#27116325)

I'm not sure I really want to trust a product by Wolfram and Heart. Seems like there is a possibility of some soul loss.

Load More Comments
Slashdot Login

Need an Account?

Forgot your password?