Slashdot Mirror
Alicebot Creator Dr. Richard Wallace Expounds
1) AI through simulation?
by Jeppe Salvesen
Do you think that the ever increasing processing power will eventually enable us to fully simulate the human brain? What ramifications would this have for the A.I. discipline?
Dr. Wallace:
My longstanding opinion is that neural networks are the wrong level of abstraction for understanding intelligence, human or machine.
Neurons are the transistors of the brain. They are the low level switching components out of which higher-order functionality is built. But like the individual transistor, studying the individual neuron tells us little about these higher functions.
Suppose an alien came down to Earth who had never seen a computer before. Assuming interstellar travel is possible without a computer! He/she might be tempted to break it open, and discover that it is made of millions of tiny transistors. The alien may try to discover how the computer works by measuring the electronic signals in the transistors. But they would miss the operating system completely. The transistors tell us nothing about the software.
Similarly, neurons tell us little about the higher order software running on our brains.
Significantly, no one has ever proved that the brain is a *good* computer. It seems to run some tasks like visual recognition better than our existing machines, but it is terrible at math, prone to errors, susceptible to distraction, and it requires half its uptime for food, sleep, and maintenance.
It sometimes seems to me that the brain is actually a very shitty computer. So why would you want to build a computer out of slimy, wet, broken, slow, hungry, tired neurons? I chose computer science over medical school because I don't have the stomach for those icky, bloody body parts. I prefer my technology clean and dry, thank you. Moreover, it could be the case that an electronic, silicon-based computer is more reliable, faster, more accurate, and cheaper.
I find myself agreeing with the Churchlands that the notion of consciousness belongs to "folk psychology" and that there may be no clear brain correlates for the ego, id, emotions as they are commonly classified, and so on. But to me that does not rule out the possibility of reducing the mind to a mathematical description, which is more or less independent of the underlying brain archiecture. That baby doesn't go out with the bathwater. A.I. is possible precisely because there is nothing special about the brain as a computer. In fact the brain is a shitty computer. The brain has to sleep, needs food, thinks about sex all the time. Useless!
I always say, if I wanted to build a computer from scratch, the very last material I would choose to work with is meat. I'll take transistors over meat any day. Human intelligence may even be a poor kludge of the intelligence algorithm on an organ that is basically a glorified animal eyeball. From an evolutionary standpoint, our supposedly wonderful cognitive skills are a very recent innovation. It should not be surprising if they are only poorly implemented in us, like the lung of the first mudfish. We can breathe the air of thought and imagination, but not that well yet.
And remember, no one has proved that our intelligence is a successful adaption, over the long term. It remains to be seen if the human brain is powerful enough to solve the problems it has created.
Functionalism is basically the view that the mind is the software, and the brain is the hardware. It holds that mental states are equivalent to the states of a Turing Machine. Behaviorism was a pre-computational theory, which imagines the nervous system as a complex piece of machinery like a telephone exchange, but they didn't think much about software. Dualism goes back to Descartes. It is the view that the mind and brain are separate and distinct things, possibly affecting each other, or possibly mirroring each other.
My view is a kind of modified dualism in which I claim that the soul, spirit, or consciousness may exist, but for most people, most of the time, it is almost infentesimally small, compared with the robotic machinery responsible for most of our thought and action. Descartes never talked about the relative weights of brain and mind, but you can read in an implicit 50-50 assumption in most Dualist literature. My idea is more like 99-1, or even 99.999999% automatic machinery and .00000001% self-awareness, creativity, consciousness, spirit or what have you.
That's not to say that some people can't be more enlightened than others. But for the vast herd out there, on average, consciousness is simply not a significant factor. Not even a second- or third-order effect. Consciousness is marginal.
I say this with such confidence because of my experience building robot brains over the past seven years. Almost everything people ever say to our robot falls into one of about 45,000 categories. Considering the astronomical number of things people could say, if every sentence was an original line of poetry, 45,000 is a very, very small number.
2) Turing Test
by Transient0
I noticed that your AliceBot won the 2000 Loebner Prize for most human responses. My question is: "As an Artificial Intelligence researcher, do you feel that the Loebner Prize represents a legitimate variety of testing, or did you just want the $2000?"
I was pretty sure that almost all AI researchers came to the agreement about thirty years ago that the original imitation game as proposed by Turing in 1951 was useful only as a mental exercise, not in practice. Do you feel that the types of developments that the Loebner prize supports(intentional, hard-coded spelling mistakes, etc.) are actually productive in terms of the AI research project?
Dr. Wallace:
In case you haven't noticed, the field of Artificial Intelligence (defined however you wish) has almost nothing to do with science. It is all about politics. When you look at all the people working professionally in the field of A.I., it brings to mind the old joke:
Q: How many Carnegie Mellon Ph.D.s does it take to screw in a light bulb?
A: Two. One to change the bulb, and one to pull the chair out from under
him.
The only rule most of these people know is: undermine the competition at all costs, by whatever legal means, or whatever they can get away with. That is how you become King of the A.I. Anthill.
Having a good theory or better implementation of anything is beside the point. Being able to "play the game" and knock out the competition, that is what it is all about. Swim with sharks or be eaten by them.
Especially in the age of increased competition for diminishing jobs and funding, scientific truth takes a back seat to save-your-ass.
Unfortunately it seems that the A.I. problem is inseperable from politics.
When I say that academia is corrupt in America, I don't mean that professors are accepting bribes and giving kickbacks for government contracts. There may be a financial motive in some cases, such as the use of overhead funds for a "course buyout" to reduce a professor's workload, but I am not talking about the kind of corruption associated with Wall Street and Washington exactly. I am talking about the replacement of science with politics as the main item on the academic agenda.
It must not have always been so. At one time, I believe academics were appointed and promoted primarily on the basis of merit and accomplishment. Within the last 20 years or so in the United States this has gradually changed into a system in which political correctness, slickness, and good salesmanship are more highly valued than good science. I don't pretend to understand the reasons for this, but I can point to many examples within our own community.
I have written that it is like a dysfunctional family. Those in positions of leadership and authority have mental health, drug and/or alcohol problems that make them incapable of carrying out their administrative responsibilities. In response, people who are skilled at "enabling" or "nursing" the dysfunctional leaders get promoted and advanced. Those who are prone to logical thinking and speaking the truth are discarded, because they make the authorities face their unconscious anxieties.
I often say, people don't go into computer science because they enjoy working with the public. But as the field has matured, I think it has attracted people who are more comfortable wearing business suits and attending strategy meetings than tinkering on a lab bench or writing a research paper. As computer science departments matured, the people already in them began to want everything to remain the same until they retired. They didn't want to hire young professors with a lot of new ideas about the administration. They hired young professors who wanted everything to stay exactly like it was, no matter what.
You may think that the politicization of a field like computer science is no big deal. We can have slick politicians instead of scientists running university CS departments, and not cause a lot of problems. But I think it is a really big problem in other fields, especially in medical science, especially in drugs and mental health.
Take LSD for example. Discovered by Albert Hoffmann in 1945, LSD is the most powerful drug ever developed. If you have ever gotten a prescription for any drug, you may have noticed that the dosage is usally given in "milligrams". But the dosage of LSD is "micrograms". It has the lowest ED50 of any known drug.
In the early 1960's there was some very promising research at Harvard applying LSD to depressed patients like me. The work was never completed or published for, guess what, political reasons. Subsequently, LSD was classified as a "Schedule I" drug with no useful medical value. This was not a decision based on sound science but on politics and fear. Even today there is zero research on this topic. Did you ever wonder why there is no Department of Psychedelic Studies on any university campus? It is a gaping hole in the academic curriculum, filled only by the informal undergraduate ratings of colleges as "party schools".
Even the very name of the federal agency that provides funding for drug research, the National Institute on Drug Abuse, prejudices the applications and the results. The native born American hippie agronomy student who got his Ph.D. in the 1970's is growing pot underground in California today. The immigrant doctor who "proved" that marijuana causes cancer got the NIDA grant and has tenure at UCLA. What's wrong with this picture?
Until 2 years ago, there was no federally funded research on the medical benefits of marijuana since the 1970's. Even now the only funded research is for terminal illnesses, and it seems like it will take a long time before they consider mental illnesses like mine. I conducted a survey of patients in San Francisco and discovered that "pain" was the #1 symptom for medical marijuana but "depression" was #2, and terminal illnesses like AIDS and cancer were lower on the list. So I am not alone in the perception that there is a patient need for research on this drug.
The problem here, my friends, is that NIDA is part of a specturm of trouble that includes once respected agencies such as NASA, NSF and DARPA. It is an octopus of political corruption that reaches into MIT and CMU and Berkeley and darkens everything it touches. It calls into question the quality and even the veracity of the scientific results and publications. We all witnessed the beginning of this even when we were all friends together at the ICRA conferences in the acrimonious interchanges between academia and industry. I myself saw enough of the system from the inside at NYU and Lehigh to know that science plays almost no role in the hiring, promoting or review process. It's all politics.
Not to place blame, but I think graduate advisors should be more straightforward with students about this point. It would be better to put more time into training them how to "shmooze" and "work the system" than how to solve mathematical problems, if they want their students to be successful. Either that, or they should work on changing the system back to merit based promotion.
3) My question (with answer)
by outlier
Historically, AI has done poorly managing public expectations. People expected thinking, understanding computers, while researchers had trouble getting computers to successfully disambiguate simple sentences. This is not good PR. Do you think the field has learned from this? If so, what should the public expect, and how do we excite them about it?
Just for fun, I asked slashwallace a shortened version of the question, do you think your response would differ?
Human: Historically AI has done poorly managing the public's expectations,
do you think this will continue?
SlashWallace: Where did he get it?
Dr. Wallace:
Hugh Loebner is an independently wealthy, eccentric businessman, activist and philanthropist. In 1990 Dr. Loebner, who holds a Ph.D. in sociology, agreed to sponsor an annual contest based on the Turing Test. The contest awards medals and cash prizes for the "most human" computer. Since its inception, the Loebner contest has been a magnet for controversy.
One of the central disputes arose over Hugh Loebner's decision to award the Gold Medal and $100,000 top cash prize only when a robot is capable of passing an "audio-visual" Turing Test. The rules for this Grand Prize contest have not even been written yet. So it remains unlikely that anyone will be awarded the gold Loebner medal in the near future. The Silver and Bronze medal competitions are based on the STT. In 2001, eight programs played alongside two human confederates. A group of 10 judges rotated through each of ten terminals and chatted about 15 minutes with each. The judges then ranked the terminals on a scale of "least human" to "most human." Winning the Silver Medal and its $25,000 prize requires that the judges rank the program higher than half the human confederates. In fact one judge ranked A.L.I.C.E. higher than one of the human confederates in 2001. Had all the judges done so, she might have been eligible for the Silver Medal as well, because there were only two confederates.
To really understand how we accomplished this, I have to teach you some AIML.
CATEGORIES
The basic unit of knowledge in AIML is called a category. Each category consists of an input question, an output answer, and an optional context.
The question, or stimulus, is called the pattern. The answer, or response, is called the template. The two types of optional context are called "that" and "topic."
The AIML pattern language is simple, consisting only of words, spaces, and the wildcard symbols _ and *.
The words may consist of letters and numerals, but no other characters. The pattern language is case invariant.
Words are separated by a single space, and the wildcard characters function like words.
The first versions of AIML allowed only one wild card character per pattern.
The AIML 1.01 standard permits multiple wildcards in each pattern, but the language is designed to be as simple as possible for the task at hand, simpler even than regular expressions.
The template is the AIML response or reply. In its simplest form, the template consists of only plain, unmarked text.
More generally, AIML tags transform the reply into a mini computer program which can save data, activate other programs, give conditional responses, and recursively call the pattern matcher to insert the responses from other categories.
Most AIML tags in fact belong to this template side sublanguage.
AIML currently supports two ways to interface other languages and systems. The <system> tag executes any program accessible as an operating system shell command, and inserts the results in the reply. Similarly, the <javascript> tag allows arbitrary scripting inside the templates.
The optional context portion of the category consists of two variants, called <that> and <topic>. The <that> tag appears inside the category, and its pattern must match the robot's last utterance.
Remembering one last utterance is important if the robot asks a question. The <topic> tag appears outside the category, and collects a group of categories together.
The topic may be set inside any template. AIML is not exactly the same as a simple database of questions and answers. The pattern matching "query" language is much simpler than something like SQL. But a category template may contain the recursive <srai> tag, so that the output depends not only on one matched category, but also any others recursively reached through <srai>.
RECURSION
AIML implements recursion with the <srai> operator. No agreement exists about the meaning of the acronym.
The "A.I." stands for artificial intelligence, but "S.R." may mean "stimulus-response," "syntactic rewrite," "symbolic reduction," "simple recursion," or "synonym resolution." The disagreement over the acronym reflects the variety of applications for <srai> in AIML. Each of these is described in more detail in a subsection below:
(1). Symbolic Reduction-Reduce complex grammatic forms to simpler ones.
(2). Divide and Conquer-Split an input into two or more subparts, and
combine the responses to each.
(3). Synonyms-Map different ways of saying the same thing to the same reply.
(4). Spelling or grammar corrections.
(5). Detecting keywords anywhere in the input.
(6). Conditionals-Certain forms of branching may be implemented with
<srai>.
(7). Any combination of (1)-(6).
The danger of <srai> is that it permits the botmaster to create infinite loops. Though posing some risk to novice programmers, we surmised that including <srai> was much simpler than any of the iterative block structured control tags which might have replaced it.
(1). Symbolic Reduction
Symbolic reduction refers to the process of simplifying complex grammatical
forms into simpler ones.
Usually, the atomic patterns in categories storing robot knowledge are
stated in the simplest possible terms,
for example we tend to prefer patterns like "WHO IS SOCRATES" to ones like
"DO YOU KNOW WHO SOCRATES IS" when
storing biographical information about Socrates.
Many of the more complex forms reduce to simpler forms using AIML categories
designed for symbolic reduction:
<category>
<pattern>DO YOU KNOW WHO * IS</pattern>
<template><srai>WHO IS <star/></srai></template>
</category>
Whatever input matched this pattern, the portion bound to the wildcard * may be inserted into the reply with the markup <star/>. This category reduces any input of the form "Do you know who X is?" to "Who is X?"
(2). Divide and Conquer
Many individual sentences may be reduced to two or more subsentences, and
the reply formed by combining
the replies to each. A sentence beginning with the word "Yes" for example,
if it has more than one word,
may be treated as the subsentence "Yes." plus whatever follows it.
<category>
<pattern>YES *</pattern>
<template><srai>YES</srai> <sr/></template>
</category>
The markup <sr/> is simply an abbreviation for <srai><star/></srai>.
(3). Synonyms
The AIML 1.01 standard does not permit more than one pattern per category.
Synonyms are perhaps the most
common application of <srai>. Many ways to say the same thing reduce to one
category, which contains the reply:
<category>
<pattern>HELLO</pattern>
<template>Hi there!</template>
</category>
<category>
<pattern>HI</pattern>
<template><srai>HELLO</srai></template>
</category>
<category>
<pattern>HI THERE</pattern>
<template><srai>HELLO</srai></template>
</category>
<category>
<pattern>HOWDY</pattern>
<template><srai>HELLO</srai></template>
</category>
<category>
<pattern>HOLA</pattern>
<template><srai>HELLO</srai></template>
</category>
(4). Spelling and Grammar correction
The single most common client spelling mistake is the use of "your" when
"you're" or "you are" is intended.
Not every occurrence of "your" however should be turned into "you're." A
small amount of grammatical context is
usually necessary to catch this error:
<category>
<pattern>YOUR A *</pattern>
<template>I think you mean "you're" or "you are" not "your."
<srai>YOU ARE A <star/></srai>
</template>
</category>
Here the bot both corrects the client input and acts as a language tutor.
(5). Keywords
Frequently we would like to write an AIML template which is activated by the
appearance of a keyword anywhere
in the input sentence. The general format of four AIML categories is
illustrated by this example borrowed from ELIZA:
<category>
<pattern>MOTHER</pattern> <template> Tell me more about your family.
</template>
</category>
<category>
<pattern>_ MOTHER</pattern> <template><srai>MOTHER</srai></template>
</category>
<category>
<pattern>MOTHER _</pattern>
<template><srai>MOTHER</srai></template>
</category>
<category>
<pattern>_ MOTHER *</pattern>
<template><srai>MOTHER</srai></template>
</category>
The first category both detects the keyword when it appears by itself, and provides the generic response. The second category detects the keyword as the suffix of a sentence. The third detects it as the prefix of an input sentence, and finally the last category detects the keyword as an infix. Each of the last three categories uses <srai> to link to the first, so that all four cases produce the same reply, but it needs to be written and stored only once.
(6). Conditionals
It is possible to write conditional branches in AIML, using only the <srai>
tag. Consider three categories:
<category>
<pattern>WHO IS HE</pattern>
<template><srai>WHOISHE <get name="he"/></srai></template>
</category>
<category>
<pattern>WHOISHE *</pattern>
<template>He is <get name="he"/>.</template>
</category>
<category>
<pattern>WHOISHE UNKNOWN</pattern>
<template>I don't know who he is.</template>
</category>
Provided that the predicate "he" is initialized to "Unknown," the categories
execute a
conditional branch depending on whether "he" has been set. As a convenience
to the botmaster,
AIML also provides the equivalent function through the <condition> tag.
CONTEXT
The keyword "that" in AIML refers to the robot's previous utterance. Specifically, if the robot responds with a multiple sentence paragraph, the value of that is set to the last sentence in the sequence. The choice of the keyword "that" is motivated by its use in ordinary language:
R: Today is yesterday.
C: That makes no sense.
R: The answer is 3.1412926 approximately.
C: That is cool.
In AIML the syntax <that>...</that> encloses a pattern that matches the robot's previous utterance. A common application of <that> is found in yes-no questions:
<category>
<pattern>YES</pattern>
<that>DO YOU LIKE MOVIES</that>
<template>What is your favorite movie?</template>
</category>
This category is activated when the client says YES. The robot must find out what is he saying "yes" to. If the robot asked, "Do you like movies?," this category matches, and the response, "What is your favorite movie?," continues the conversation along the same lines. One interesting application of <that> are categories that enable the robot to respond to knock-knock jokes.
The categories:
<category>
<pattern>KNOCK KNOCK</pattern>
<template>Who is there?</template>
</category>
<category>
<pattern>*</pattern>
<that>WHO IS THERE</that>
<template><person/> who?</template>
</category>
<category>
<pattern>*</pattern>
<that>* WHO</that>
<template>Ha ha very funny, <get name="name"/>.</template>
</category>
produce the following dialogue:
C: Knock knock.
R: Who's there?
C: Banana.
R: Banana who?
C: Knock knock.
R: Who's there?
C: Banana.
R: Banana who?
C: Knock knock.
R: Who's there?
C: Orange.
R: Orange who?
C: Orange you glad I didn't say banana.
R: Ha ha very funny, Nancy.
Internally the AIML interpreter stores the input pattern, that pattern and topic pattern along a single path, like: INPUT <that> THAT <topic> TOPIC When the values of <that> or <topic> are not specified, the program implicitly sets the values of the corresponding THAT or TOPIC pattern to the wildcard *.
The first part of the path to match is the input. If more than one category have the same input pattern, the program may distinguish between them depending on the value of <that>. If two or more categories have the same <pattern> and <that>, the final step is to choose the reply based on the <topic>. This structure suggests a design rule: never use <that> unless you have written two categories with the same <pattern>, and never use <topic> unless you write two categories with the same <pattern> and <that>. Still, one of the most useful applications for <topic> is to create subject-dependent "pickup lines," like:
<topic name="CARS">
<category>
<pattern>*</pattern>
<template>
<random>
<li>What's your favorite car?</li>
<li>What kind of car do you drive?</li>
<li>Do you get a lot of parking tickets?</li>
<li>My favorite car is one with a driver.</li>
</random>
</template>
Considering the vast size of the set of things people could say that are grammatically correct or semantically meaningful, the number of things people actually do say is surprisingly small. Steven Pinker,in his book How the Mind Works wrote, "Say you have ten choices for the first word to begin a sentence, ten choices for the second word (yielding 100 two-word beginnings), ten choices for the third word (yielding a thousand three-word beginnings), and so on. (Ten is in fact the approximate geometric mean of the number of word choices available at each point in assembling a grammatical and sensible sentence). A little arithmetic shows that the number of sentences of 20 words or less (not an unusual length) is about 1020."
Fortunately for chat robot programmers, Pinker's calculations are way off. Our experiments with A.L.I.C.E. indicate that the number of choices for the "first word" is more than ten, but it is only about two thousand. Specifically, about 2000 words covers 95% of all the first words input to A.L.I.C.E.. The number of choices for the second word is only about two. To be sure, there are some first words ("I" and "You" for example) that have many possible second words, but the overall average is just under two words. The average branching factor decreases with each successive word.
We have plotted some beautiful images of the A.L.I.C.E. brain contents represented by this graph (http://alice.sunlitsurf.com/documentation/gallery/).
More than just elegant pictures of the A.L.I.C.E. brain, these spiral images (see more) outline a territory of language that has been effectively "conquered" by A.L.I.C.E. and AIML. No other theory of natural language processing can better explain or reproduce the results within our territory. You don't need a complex theory of learning, neural nets, or cognitive models to explain how to chat within the limits of A.L.I.C.E.'s 25,000 categories. Our stimulus-response model is as good a theory as any other for these cases, and certainly the simplest. If there is any room left for "higher" natural language theories, it lies outside the map of the A.L.I.C.E. brain. Academics are fond of concocting riddles and linguistic paradoxes that supposedly show how difficult the natural language problem is. "John saw the mountains flying over Zurich" or "Fruit flies like a banana" reveal the ambiguity of language and the limits of an A.L.I.C.E.-style approach (though not these particular examples, of course, A.L.I.C.E. already knows about them).
In the years to come we will only advance the frontier further. The basic outline of the spiral graph may look much the same, for we have found all of the "big trees" from "A *" to "YOUR *". These trees may become bigger, but unless language itself changes we won't find any more big trees (except of course in foreign languages). The work of those seeking to explain natural language in terms of something more complex than stimulus response will take place beyond our frontier, increasingly in the hinterlands occupied by only the rarest forms of language. Our territory of language already contains the highest population of sentences that people use. Expanding the borders even more we will continue to absorb the stragglers outside, until the very last human critic cannot think of one sentence to "fool" A.L.I.C.E..
[Continue to part 2 of the interview.]
I can't find the answer to this on their pages anywhere and if you ask the ALICE program it give back some cryptic bull-crap asking what I think it means. Someone just tell me!!!
Anyone have more pictures of this guy? The article on nytimes.com had that tiiiiny little picture where he just looked like a muppet.
sig.
...that this is actually him, eh?
help fill in hidden movie endings @ End of the Credits
I always say, if I wanted to build a computer from scratch, the very last material I would choose to work with is meat.
well.. you could cook it pretty well with an OC'ed athlon. cook dinner and waste time at the same time.
My beliefs do not require that you agree with them.
about longer replies *grin*
JohnFlux
I don't know about yours, but my brain runs Linux
Not only is the length of these replies very exciting - it seems that he has taken great care to provide technical details that are invaluable. In all the classes that I have taken I haven't seen such an excitement for this kind of material. And, just to put those statements in context I completed a MS in CS with a focus on AI . . .
This is obviously A.L.I.C.E. answering.
-- My HARDWARE, My CHOICE.
Then I read this interview and began to begin to sense that my brain was about to explode. Guess I need to ratchet down my self assessment and get some Tylenol for the headache!
there's part two to the interview.
I am exausted already.
Does this not have the implication that there would be nothing very terrible about rounding up large numbers of the "vast herd" and painlessly slaughtering them? Has he thought through the consequences of this view?
-- the most controversial site on the Web
As im reading this I am getting a bit irritated.
It seams as whenever he tries to prove something he brings up a bunch of "facts" without backing them up with anything "real". And then draws a conclusion that doesnt have anything todo with the "proof" he gave.
So from my view he makes up evidence to justify his own views. Instead I think he should addapt his views to reality and the rules of western society.
And then there's also a part three...
I read the title as "Alicebot Creator Dr. Richard Wallace Exlodes". Whew! Always gotta watch out for spontaneous combustion.
i certainly appreciate good technology, don't get me wrong. but, after reading a new york times magazine article on the good doctor, i revisited ALICE, and was not impressed, as i hadn't been the first time. i messed with it for about ten minutes, thinking maybe i was missing something, and then showed it to my girlfriend, who asked ALICE about three questions and then gave me one of those looks.
i know, i know, baby steps, but, in a behavioral sense, this neither approximates nor even reasonably simulates intelligent thought. why are people so blown away?
go get it
A.L.I.C.E. = artificial linguistic Internet computer entity
My longstanding opinion is that neural networks are the wrong level of abstraction for understanding intelligence, human or machine.
Not a very valid opinion since the behavioral complexity and robustness of biological neural networks are many, many orders of magnitude greater than that of any robot or program in existence. Alice is a good example. But this view is to be expected from a GOFAI (good old fashioned AI) guru whose livelihood depends on hawking the hopelessly flawed symbolic intelligence and knowledge representation approach to AI. This approach is over fifty years old and they still can't use it to make a machine as smart as a cockroach. Not a very good track record, IMO.
For a better take on why neural networks are the only hope for achieving human level AI, click on the links below:
Temporal Intelligence
Animal
Thank you Dr. Wallace. Really.
Disclaimer, I haven't read the whole thing yet since its long I'm going to comment on my observations so far.
... as machines. In fact I'm impressed he got that many responses, most people don't ask their electric can-opener what the meaning of life is, and I venture to guess that most people don't see a robot much differently.
... I don't think its a very good comparison. In fact switch good visual recognition with good math skills in what he's saying and you would have a better description of a robot than a person ...
That's not to say that some people can't be more enlightened than others. But for the vast herd out there, on average, consciousness is simply not a significant factor. Not even a second- or third-order effect. Consciousness is marginal.
Okay I'm sure this guy is a huge expert and all but this sounds rather elitest, lots of people create lots of wonderful things, to say that most people don't use their consciousness simply ignores all the massive achievements of the last 100 years. He goes on to talk about that people say only about 45000 things to his robots... well it seems to me the obvious answer is that most people perceive robots a certain way
Also he talks about how the brain is such a horrible computer but completely ignores human interaction, something that our computers can't do and I don't see them doing very well anytime in the near future (ever talked to that crappy robot voice on Sprint PCS customer service?). He talks about how the brain is horrible at math but ignores that fact that everytime we move the brain makes complex calcuations to put our legs in the right place and keep us balanced. Just because we aren't conscious of it doesn't mean it doesn't happen.
So really I think hes comparing humans from the perspective of his robots
Just my opinions, not meant as a troll.
The Anti-Blog
well.. you could cook it pretty well with an OC'ed athlon. cook dinner and waste time at the same time.
No kidding, some dude cooked an egg with his Athlon XP!
example.org - powered by Linux!
Picture right here.
I am not a number! I am a man! And don't you
It all depends on where the "topic" ends precisely, but there have been studies on the effect of LSD on religious experiences. Some of them are cited in "Zen and the Brain" by James Austin.
Han-Wen Nienhuys -- LilyPond
It was this year.
I think one it's more important effects is to be able to stand outside one's thought processes (as much as one can) and be able to somewhat objectively analyze the mind. It's possible that use of this drug can help us understand more about conciousness and developing AI in the right hands. Of course this isn't anything new, but I'm not sure this approach has ever been taken in an attempt to develop AI.
1. He didn't answer the question
2. <SARCASM>Good thing he's not bitter or anything, isn't it?</SARCASM>
General Relativity: Space-time tells matter where to go; Matter tells space-time what shape to be.
The native born American hippie agronomy student who got his Ph.D. in the 1970's is growing pot underground in California today. The immigrant doctor who "proved" that marijuana causes cancer got the NIDA grant and has tenure at UCLA. What's wrong with this picture?
What's wrong with this picture is the very fact that he mentions ethnicity. I've always kind of assumed that scientific minds- especially computer scientific minds- can move past irrelevant things like that....and I find it especially sad that someone complaining about the amount of backstabbing going on in american science (and that's a valid argument) has to resort to essentially the same tactics to drive a point home.
It seems to me that Dr. Wallace is half right on his interpretation. His transistor/operating system analogy would seem to be fairly compelling and makes a lot of sense to me.
/.ers who may be more informed have any thoughts?
The question I wish had been asked is, we all know emulation is slower and normally less accurate than a native system. If you are approaching AI from the standpoint of developing the operating system before developing the system itself, how is this a more accurate approach or will both approaches yield to a final positive result?
His answers basically make me think that a true AI is most likely to evolve on two fronts. First, the development of models that emulate the structure of the brain (neural networks/etc.), and second the development of models that emulate the way it actually behaves. NNs are quite good at learning things from an input layer, but how do you go about getting that input layer without an appropriate model of what human behavior is?
This is why I think that models like ALICE will be used to approximate behavior and then a neural network will be used to learn how to emulate that logic with an adaptive input layer(being a next generation ALICE equivalent). IANITF(I am not in the field) however. Last thing I read in it was on perceptors, logic grammars, and kohenegan[sic] SONs. Any other
The key to the enjoyment of pop music is to replace any instance of "love" with "C.H.U.D."
This guy knows what it is about. His response to question #2 pegs the fundamental problem with the CS discipline as an undergraduate or graduate field of study, and maybe the sciences in general. The people that do things by the book, solve the same problem sets and schmooze with the professors the most get the A's the promotions, etc... How many times do I have to solve the same problem? Is this just so the people that waste their study time can be able to bullshti their parents? Someone in my classes actually said "I'm a CS major because my father told me to be. I had no idea what it was" Guess what she still doesn't but that didnt stop her from getting elected to the ACM president for my schols chapter. These type of people need to get the fuck out of CS and go into management so that the other brood of worthless Cs majors, those that think techinal knowledge (defined to be somerhing they read about the linux kernel when they were sitting at home smacking their pud around a d&d table on a friday night) can bitch about them when they get jobs as sysadmins. If you dont like the science go to a techinal school or business school so that people will know they should never take you seriously.
I say this with such confidence because of my experience building robot brains over the past seven years. Almost everything people ever say to our robot falls into one of about 45,000 categories. Considering the astronomical number of things people could say, if every sentence was an original line of poetry, 45,000 is a very, very small number.
I say:
The fact that people only say 45,000 different things to a robot shouldn't indicate to you that people only have about 45,000 things to say, just that they only have 45,000 things to say to a robot in what is essentially a lab setting!
That said, I think this is a pretty fascinating interview.
Dude, I think I can see my house from here.
Well, I'm so totally unimpressed so far. One out of three, and we have a whole bunch of nonsense.
For starters, AI, neural nets, and brains. We have the assertion that the brain is a computer, and we should really be concerned with the software on the computer, not the state of the neurons.
Even accepting the good doctor's view that the brain is a computer, this is an absurd position. After all, the software is in the brain. It's not like it gets bootstrapped from outside sources. So either the software is built into the whole structure of the brain and we can only learn about it by studying the rules (a la neural nets) or we have to figure out which part of the brain bootstraps the rest of it. Which we'd have to study the wet squishy bits to figure out. Which can best be done with a combination of noninvasive study (MRI, for example) and simulation. Like neural nets.
(The third possibility is that the brain is a computer, but the program is stored on a shared network drive... that is, in a non-material 'soul.' Which would bring us back to Cartesian dualism, God, and a whole bunch of things you'd better reject if you want to work in AI. Not rejecting the notion of God per se, just in the degree of investment in the nonmaterial world in which a being needs to take part...)
Second, academic politics. Dr. Wallace seems to believe in a golden age (that occurred, not coincidentally, just before his professional career) where professors were promoted and supported on the basis of merit.
Right. Anyone who believes in any society at any time in the West that existed without politics is invited to check into the nearest mental institution. To accept the idea of a 'golden age' just tantalizingly out of his reach is pathetic. It's like imagining an era where writers received acclaim based on the quality of their work.
Newsflash: Emily Dickinson's writings were discovered after her death. Everything we read by Melville was written long after his popularity had waned. Any number of great artists were 'discovered' after their deaths. And the most popular writers and artists at any time have been the ones who played the political game successfully. (Personal politics, not governmental politics, of course.) Anyone who's read any medieval philosophy or theology knows that there hasn't been a meritocracy in Western academia for at least eight hundred years.
As far as LSD and politics, it was the professors involved in those experiments (ie Tim Leary) who engaged in politics. And they were bad at it. And they lost. And the substances ended up scheduled. And their academic careers were ruined.
On to part two, to see what he says there. Perhaps it gets better.
King's Quest had AI logic just as good in 1983!!!
As for the consciousness remark he made ("consciousness is marginal."), I for one will disagree. And that is what MAPS is all about (along with the likes of Richard Schultes, the late Terrence McKenna, Dennis McKenna, and a slew of other "psyconauts" out there).
It would appear he wrote these answers before he received the questions. He then randomly applied these essays to the questions. After all, his theory of question and answer is that human conversations are banal and predictable and that creating a reasonable response is elementary programming.
A.L.I.C.E. was not the original name of A.L.I.C.E. The first prototype was called PNAMBIC, in tribute to the hoaxes, deceptions and tricks that have littered the history of artificial intelligence.
"PNAMBIC-(acronym) Pay No Attention to that Man Behind the Curtain [from The Wizard of Oz]. Denoting any supposedly fully automated system that in fact requires human intervention to achieve the desired result."-New Hacker's Dictionary
But the machine hosting PNAMBIC was already named Alice by a forgotten systems administrator, so people began to call her "Alice." At that point, we invented the "retronym": Artificial Linguistic Internet Computer Entity.
belated question -- maybe some ai geek out there can answer:
is it possible to create an ai like this that is scalable to multiple languages, or would the wheel have to be reinvented each time? is it too reliant on idioms?
go get it
Amazing interview. He didn't always answer the questions and I didn't always agree, but it was very interesting still.
Yeah! Brains may be shitty at math, but they're fantastic at interacting with the real world. Would you rather have a robot that can do matrix multiplication, or one that can walk to the kitchen and return with an (intact) beer? The substrate matters.
There are two levels to the AI problem. The symbolic and the manipulation. Symbols should be used to define meanings to things, and the neural net for processing things. Thats how the brain works. Signals fly around in the frontal lobe and produce some kind of emerging answer. That answer has no meaning outside of the brain, but it produces a stimilus. This stumulus causes the training that humans get as an infant to "make" the learned behavior happen. Or if you like terminate the signal path. In reality nothing terminates, other things just take over. What you need is a neural network that adjusts its weights based on its enviornment, and then produces a canned response at some point. This canned response ideally could be the result of the enviornment. mnjnjmmnjmn,mn,
fuck it. I'll just write a paper.
It sometimes seems to me that the brain is actually a very shitty computer. So why would you want to build a computer out of slimy, wet, broken, slow, hungry, tired neurons? I chose computer science over medical school because I don't have the stomach for those icky, bloody body parts. I prefer my technology clean and dry, thank you. Moreover, it could be the case that an electronic, silicon-based computer is more reliable, faster, more accurate, and cheaper.
I find myself agreeing with the Churchlands that the notion of consciousness belongs to "folk psychology" and that there may be no clear brain correlates for the ego, id, emotions as they are commonly classified, and so on. But to me that does not rule out the possibility of reducing the mind to a mathematical description, which is more or less independent of the underlying brain archiecture. That baby doesn't go out with the bathwater. A.I. is possible precisely because there is nothing special about the brain as a computer. In fact the brain is a shitty computer. The brain has to sleep, needs food, thinks about sex all the time. Useless!
I always say, if I wanted to build a computer from scratch, the very last material I would choose to work with is meat. I'll take transistors over meat any day. Human intelligence may even be a poor kludge of the intelligence algorithm on an organ that is basically a glorified animal eyeball. From an evolutionary standpoint, our supposedly wonderful cognitive skills are a very recent innovation. It should not be surprising if they are only poorly implemented in us, like the lung of the first mudfish. We can breathe the air of thought and imagination, but not that well yet.
And remember, no one has proved that our intelligence is a successful adaption, over the long term. It remains to be seen if the human brain is powerful enough to solve the problems it has created. "
It's not that I don't appreciate Dr. Wallace' contributions to the field of A.I., nor am I ignoring his obvious expertise in his programming and computer science skills. Those skills have made him the foremost expert on A.I. today. Yet he has denigrated the very organ by which he is able to formulate his thoughts, and seems to see little, if any, use in modelling or even studying its structure and arrangement to gain any insight into the possible ramifications for A.I.
I just find it interesting that we humans, as rational beings, with certain innate intelligences and thinking abilities, often rail against the very things that allow us the liberty and (dare I say) privilege of saying them.
That was my only complaint - the interview was insightful and interesting, a great read.
Isn't the answer to question 2 presented as the answer to question 3?
-- &&
But to me that does not rule out the possibility of reducing the mind to a mathematical description, which is more or less independent of the underlying brain archiecture.
But what if "the mind," aka the illusion of consciousness, is an emergent property of the brain's complex system?
I would think it would be very difficult to create a computer model of the brain, since there's likely a high degree of probability involved that can't be directly measured. But has any work been done along these lines (agent-based models, etc.)?
Are the answers matched up with the wrong questions? It sure looks as though the answers, while interesting, have nothing to do with the question asked. Look at the answer to #3, it sure looks like it belongs with question #2.
314-15-9265
I think some HTML formatting was inadvertantly removed in this sentence.
A little arithmetic shows that the number of sentences of 20 words or less (not an unusual length) is about 1020.
Actually the number of sentences is about 10 ^ 20, or 10 to the power of 20. (I'm guessing that the HTML superscript tag was removed.) The point here was that even though the number of possible sentences is astronomically large, the number of different sentences that people tend to say in practice is actually surprisingly small (once you factor our proper nouns).
Dont mind if I do! Have a nice weekend :)
"Politicians, at least those in our society, never seem to give a straight answer to a question. If a journalist asks a specific question, the politician answers with a "sound bite" or short, memorized speech which is related to, but does not necessarily answer, the reporter's question. If asked about schools for example, the politician may reply with a memorized policy statement on education policy. It is as though the response was merely triggered by the keyword "school" in the question. No creative or spontaneous thinking is required. "
Though I did find many of the memorized policy statements interesting and insightful, they were clearly that. I have memories of doing the same once myself, but they may not be real.
all your base may never have existed at all
I wrote one of these things WAY back in 1983. Mine was originally written in Sinclair BASIC on a TS-1000 with NO hard drives and only 20k of RAM.
/. article I was going to scoff and call this fellow a fraud, but after reading what he wrote, particularly the bits about academic sleaze, I kind of agree with him. Why NOT take the view that "machines can think" since we are spoon fed much more onerous bullshit than this all the time, by government, industry AND acedemia, so why not?
The reason for my writing it was my disgust with frauds who promote the fiction that computers can think; these fellows were calling computers "electronic brains" back when they were two story tall pocket calculators.
I named it "Artificial Insanity," and it DOES NOT THINK. It does, however, pass the Turing test.
It does a better job of it than Alice.
I ported Art to DOS in 1989, it takes up less than 400k (this version using the same algorythm but written in Clipper).
A couple of months ago I decided to pit Art against Alice, and documented the exchange on my gaming web site (http://thefragfest.com).
The exchange was incredibly humorous, at least to me. Of course, I've been told I have a weird sense of humor...
When I saw this
As long as you fellows don't start screaming for "machine rights". A hundred years ago the thought of "animal rights" would have been unthinkable.
-steve
Springfield Fragfest
(I think the art/alice conversation is in the May archives, I'd have to hunt for it)
A Lazy Imbecilic Computerized Ewok
When I do it's usually not nice
The do-it-yourself form:
go to www.acronymfinder.com, type in alice, hit enter, and check for the relevent term (in this case it's the last one on the list).
I am amused that the Artificial Intelligence community, in fact most scientific communities have adopted a mindset of me-first, science-second, especiallly AI. One would think that the AI community would apply one of it's own algorithms to the structure of the community itself, thereby increasing scientific capacity.
It would be great if we CS people could organize ourselves to the point where we can test out our own algorithms on a broad social scale, and not just within the limits of our metal boxes with blinking lights.
You need to restart your computer. Hold down the Power button for several seconds or press the Restart button.
Well, I never thought of my meat computer as "shitty" until I read this. But by the time I got half-way through Part 1, I came to the conclusion that either Dr. Wallace or myself definitely had shit for brains.
Hey, does anyone have an extra PageDown key they could send to me? I just wore mine out.
Now, I have to ask why it is that it basically comes down to 'we want [thing] legalized' but is really 'we want to do [thing] without getting arrested.' I have met VERY few people who are not advocates of legalization simply because of their own selfish interests. That really in itself does not bother me. What does is that they try to justify their actions/beliefs as if they are some heroes of the universe out to free us all. Hmmm, sounds like the vast majority of MP3 swappers.
The message? Just do it, but please STFU and stop trying to sell yourself as something you are obviously not. You wanna help freedom? Take up a firehose, police uniform or an M-16 and help us all, but STFU about being a hero because you helped secure your own personal right to do whatever.
ALICE would have told you if you asked her.
-Peter
That's what my one professor, Donald Simon, always says. For the moment, he's right.
Currently, AI is nothing more than a magic trick. It's not about intelligence - it's simply an illusion that when you figure out how it works, it is no longer impressive. Every AI researcher is a magician in that respect, no matter which of the two schools you come from. Yes, all of this is quite sophisticated, but so are most modern magic tricks.
Needless to say, the same as illusionists today make people appear to levitate, we will one day have that technology. While AI today is just a bunch of deceit, some day we may see "intelligent" (as far as we understand it - currently, all AI is "stupid") machines.
Just a few thoughts...
Why bother.
Whew. My brain is full now. As a CSE Student and a guy with mono-polar depression, I understand a little of what is going on in this man's head. It is a constant mental tug-of-war to stay on-topic and on-track. I think that Dr. Wallace probably has to concentrate twice as much as his mental peers--Half of his effort towards his life's work and half of his effort just trying to stay focused on the first half. When he allows his brain to follow tangents, like he repeatedly did in these answers, he really had little choice. He had lost his focus on his subject. This is a bad thing for a person with depression. When he got it back, later, he was very methodical in building the foundation of axiomatic information for the rest of the answer. For me, that foundation never comes naturally; it has to built in memory each and every time. The more one practices and studies, the faster the foundation can be built each time. It's only love of the subject matter, and the love of learning, that keeps me going, education-wise and career-wise. Maybe him, too. I wish him good luck.
MadDad32
"Apparently, being logged in is what is keeping my Karma in positive territory."
Artificial Linguistic Internet Computer Entity It is on page two of the interview about half way down. Just FYI also, it was named that by some old sys admin and it sort of stuck. They made up the acronym afterwards.
He's a bit of a rebel, yes?
Does this offend you, or are you scared? You say you're irritated -- why? Because he doesn't play by "the rules of western society"? The same society which would decide arbitrarily what a man can and cannot ingest, inhale, or inject into his own body, without backing their decisions up with anything "real" either? Should he sit calmly in his corner like the rest of us, being little more than an unthinking automaton?
He's different. This pisses you off.
I think you're the one who needs to adapt. Or simply be quiet.
- A.P.
"Remember when the U.S. had a drug problem, and then we declared a War On Drugs, and now you can't buy drugs anymore?"
Whatever input matched this pattern, the portion bound to the wildcard * may be inserted into the reply with the markup . This category reduces any input of the form "Do you know who X is?" to "Who is X?"
I hope he knows not to ask that question on dal/undernet.
There's no "I" in Linux.. err..
I am fascinated by Artificial Intelligence, although I haven't really allocated much time into learning about it. However, I did come across a very good book "Artificial Intelligence: A Modern Approach" by Stuart Russell and Peter Norvig (and no, I'm not at all associated with them), and I found it a pretty good book. It has technical depth, not just a philosophical one. They will have a draft of their second edition available pretty soon, check it out: http://www.cs.berkeley.edu/~russell/aima.html
I believe that artificial intelligence is the science of reasoning. The word artificial tells us that it doesn't need to get so close to that of human beings after all. There are many different subfields and all of them are important. The ones I am interested the least are things such as speech recognition, or vision, because, even though they are useful and interesting, they do not present by themselves a case in favor of reasoning as much as the other topics do.
If I were to take (or give?) a course on artificial intelligence, this is what I believe would round up a pretty nice course (probably a good introductory one):
1. Knowledge representation. There actually is quite some research in this subfield. It has to do with how to obtain, query, and modify knowledge efficiently, among other things.
2. Planning. My favorite. I believe this is the true heart of artificial intelligence. It is the mechanism of developing a plan, from macro to micro, and seeing it through its completion. There are interesting aspects such as conditional planning, hierarchical planning, and then we can go deep into uncertainty issues, plan restructuring because of unexpected effects, and a feedback loop of a "learning" nature probably into the knowledge representation module. Cool stuff.
3. Neural networks do have a place in AI. I believe that data mining is quite close to neural networks (which also means close to statistics). It makes for pretty interesting stuff. For example, how else can an automated system look into a database with millions of records and discover knowledge such as "product X is being bought predominantly by males, except for the particular model Y which is pretty popular among females", or something like that.
Having read much of the interview, I have to respect the man's opinions, and appreciate the technical details, but I feel that more could have been contributed (either in depth, or as in "across the board") in the technicial area. Perhaps he might be interested in more technicial questions anyway?
The transistors tell us nothing about the software.
Similarly, neurons tell us little about the higher order software running on our brains.
The good Professor seems to think that there is a higher level operating system in the brain. I would like to ask him "Who programmed it?". Now, if he is not a theist, there are very few individuals left (except, perhaps, a demigod Turing ... "Diamond
Age" anyone? :) ) to do this coding.
So, it seems that it must have been an evolutionary process that "did the programming". But, in this case, the programming is built into the system . That is to say, there is only hardware. Unless you want to go back to a soul (I saw him mention Dualism, but he should be careful not to cut himself on Occam's Razor ... I'll read that
later).
Transistors only execute what they are told to in the form of machine code (that comes from assembly, that may may come from a higher level language ...
is you program in 1s and 0s, you're sick). Neurons
have a built in mechanism of operation. They
simply act. I think the real point is that
neurons are a "higher level of hardware" than
transitors.
I'll need to think a little more to make this sensical. Heh.
Regards,
Mark
I just noticed that Slashdot is treating the three parts of this one interview as three different stories, with three different sets of replies, etc. Yeah, that's really going to facilitate discussion, when half of the responses to question #1 appear in the first story and half in the third story from when people are done reading the whole set. Brilliant.
Slashdot - News for Herds. Stuff that Splatters.
Oh come on that was funny.
1. He complains about the "corruption" of his discipline, but gives little evidence to back this up.
2. He complains about an "immigrant" doctor getting funding over a "native American" - a classic thing for a bitter man to say.
3. He exhibits contempt for most people - he seems to think that consciousness is barely a factor in their existence.
4. He appears to think that producing XML conversation templates is some kind of step towards AI. Hey, maybe if we had _loads_ and _loads_ of these XML schemas, we'd produce a really intelligent computer!* (As if intelligence was basically made out of regular expressions.)
* I thought this was satire, but he really does say it! Here is this guy's idea of the progress of machine intelligence:
Our territory of language already contains the highest population of sentences that people use. Expanding the borders even more we will continue to absorb the stragglers outside, until the very last human critic cannot think of one sentence to "fool" A.L.I.C.E..
Evidently, this is not a way to build a creative or intelligent computer. It's just a way to make an entertaining toy. The counter-argument, that 90% of human behaviour is predictable enough to be mimicked by ALICE, is misguided. We want to build Artificial Intelligence, not Artificial Average Human Unintelligence.
You're also correct about the math issue: we're good computers for certain preprogrammed tasks, which makes us little different than any other computing device. He's complaining that we're not good at reprogramming ourselves to do tasks for which we weren't specifically evolved, but in that sense he can't compare us to computers, since they also can only perform the tasks they're programmed for, and have no consciousness of the processes they perform.
Wallace is a smartish guy with some apparently serious social skills problems (ref NYT article posted on /. previously), and he seems to be using Alice as a shield/weapon against the rest of the world.
I don't think you'll have to worry about that anytime soon. There are InP based chips that might be useful for signal processing at a few hundred Ghz, but CPUs won't be there for the next twenty years at least. Low K is nowhere near as easy as people assume. The slowdown hasn't even started yet.
As for AI, well whatever. MP3 and Divx is cool and LSD aint bad either. I'll take LSD, some weed and lots of music and videos over AI anytime.
Computers are over. Let's build spaceships now.
that it is imposible to create a fully human clone based on mathematical logic, no matter how vast or fast it is. Life just isn't based on a 'rational', fully knowable universe. Any universe where such basic geometry like the diagonal of a square or ratio of circumference to diameter of a circle are neverending numbers just isn't a rational universe!
Oddly enough, I just checked out the Star Trek TOS "What are Little Girls Made Of" DVD last night, which deals with the exact same subject, very realistic robot machine 'clones' of humans, that have no emotions.
try { do() || do_not(); } catch (JediException err) { yoda(err); }
The Bayh-Dole Act of 1980 probably helped accelerate this trend (and fits into his 20 year timeline). Basically, it allowed Universities (among other entities) to retain IP rights (i.e., patents) to work done within Universities in the US. See the book Campus Inc.: Corporate Power in the Ivory Tower for more info on this Act of other corporate influences in academia.
Allowing Universities to hold title to their IP sparked the creation of IP offices at many Universities that often, for example, prohibit the release of software written by faculty, staff (or even students!) as free/open source.
"
I guess they're acknowledging that most of us usually only skim Slashdot articles...
------
Today's Top Deals
"The brain has to sleep, needs food, thinks about sex all the time. Useless! "
Hahaha, funny stuff, funny stuff.
-me
..but now it's time to bust out the moonshine!
--- What
"Even if most of what we normally call "consciousness" is an illusion, there may yet be a small part that is not an illusion. Consciousness may not be entirely an illusion, but the illusion of consciousness can be created without it. "
"Take LSD for example. Discovered by Albert Hoffmann in 1945, LSD is the most powerful drug ever developed. "
"I conducted a survey of patients in San Francisco and discovered that "pain" was the #1 symptom for medical marijuana but "depression" was #2, and terminal illnesses like AIDS and cancer were lower on the list. So I am not alone in the perception that there is a patient need for research on this drug."
things that make you go.. hmmmmm
Ves
He probably says this because he can't get laid.
All I do is sleep, eat, and think about sex. Hell, that's pretty accurate!
I think a better material would be cookie dough, so you can refresh yourself after a tough game of minesweeper.
Siggy Wiggy Figgy Tiggy a bana bo Biggy!
"Significantly, no one has ever proved that the brain is a *good* computer."
:-)
/., eh?
:-). If there is awesome silicon intelligence that isn't self-aware and conscious, who fucking cares?
And yet, after (insert duration since humans appeared based on latest estimate) years, here we are.
"It seems to run some tasks like visual recognition better than our existing machines, but it is terrible at math..."
That's because -precise- math is evidently (get ready for this) relatively unimportant for carrying on in the real world! When a robot, on the run, can throw a stone and hit something else that's on the run, talk to me about shitty meat computers and the superiority of "clean and dry" computers.
"... prone to errors, susceptible to distraction,
the source of all innovation, change, progress...
" and it requires half its uptime for food, sleep, and maintenance."
Most of which is fun
"It sometimes seems to me that the brain is actually a very shitty computer. So why would you want to build a computer out of slimy, wet, broken, slow, hungry, tired neurons? I chose computer science over medical school because I don't have the stomach for those icky, bloody body parts."
This guy hates his body.
"I prefer my technology clean and dry, thank you. Moreover, it could be the case that an electronic, silicon-based computer is more reliable, faster, more accurate, and cheaper.
Go download yourself then. I know you have suffered from depression, but the whole idea that "reliable, faster, more accurate, and cheaper" is the most important part of being a conscious entity demands some explanation. What is the point of intelligence? There's something we don't talk about much on
"But to me that does not rule out the possibility of reducing the mind to a mathematical description, which is more or less independent of the underlying brain archiecture. That baby doesn't go out with the bathwater. A.I. is possible precisely because there is nothing special about the brain as a computer."
Well, this is precisely what nobody knows, and why we play the AI game. Maybe someday we'll know.
"In fact the brain is a shitty computer. The brain has to sleep, needs food, thinks about sex all the time. Useless!"
I'm sure this is an exaggeration to make a point, but again I say... here we are.
"I always say, if I wanted to build a computer from scratch, the very last material I would choose to work with is meat."
Who is this very perceptive and canny "I" that is making this most fundamental decision? It's a fucking meat computer, that's who.
"And remember, no one has proved that our intelligence is a successful adaption, over the long term. It remains to be seen if the human brain is powerful enough to solve the problems it has created."
True enough, though I would bet that, although we might be facing some major (if not cataclysmic) upheavals of our own making in the near-mid future, something from the human line will survive and keep on keepin' on.
I'm sorry, I know this fellow suffers from depression and all, but the fact of the matter is that meat computers are not "shitty", and the "it remains to be seen" idea cuts both ways.
The other fact of the matter is that nobody knows how consciousness works. No, not anybody, not even Dennet
This guy makes me sad. He represents something pathetic to me.
Wow, I've really rambled.
- Steve
The simplest way would be if the brain had some sort of look-up table: when I see the ball at position X1, I move to position Y1; when I see it at X2, I move to Y2. Or more generally: position Xn -> Yn. In this way you could build up a detailed model of your environment and the mechanics of your interaction with it. However, it can be shown that this is most likely is not the way it works. Why? Generalization.
Tasks and environments which are learned in one situation are generalizable to others. This can be shown with prism glasses, rotating rooms, micro-gravity, macro-gravity, etc. Basically, in any situation in which the physics of the universe or the physics of the subject, or the interaction between the two is changed, the subject can adapt in a robust way that a table-lookup can't touch. Reza Shadmehr has some very interesting results on this topic.
So how else could it work? Moving up a level in complexity we get to what is known as an internal model. The internal model describes the mechanics of the universe and the bodies interactions with the universe. When the mechanics changes (eg prisim glasses) the model is updated via proprioceptivie information. The difference between this and the look-up table above is that it is represented in such a way that extrapolations to new situations are possible. We can mathematically represent such an internal model as a jacobian matrix, very similar to those that you may remember from your mechanics classes.
This does beg an interesting question though: how the heck is our brain able to quickly invert matrices? ;)
Another possibility is that the brain is actually "aware" at some level of the laws of physics and is doing calculus to figure out trajectories. This is also unlikely; there are simply too many degrees of freedom. Robot designers don't generate movement by solving laws of motion, they use feedback control.
(If you're familiar with control theory you might have been wondering about feedback control. Might not the brain be getting a real-time error signal and correcting its movement in the way that a robot would? It turns out that this is unlikely. Nerve conduction velocity is too slow so there is too much lag between the extremities and the CNS. If our motion were controled by feedback alone, smooth motion would be impossible. Clearly the proprioceptive error signal is there but it acts on a much slower timescale.)
2^5
Thank you BlueRain. Really.
Am I the only one willing to say I had the impression that ALICE helped in writing these responses? Seriously, they display a remarkable aptitude for going on at legth about a specific subject, but almost no comprehension of the actual question. Very frequently they open with something tangentially related and then move on to something completely different, a technique described mulitple times in the article.
What the hell, I'll say the emperor has no clothes.
In Part One:
.00000001% [note: what's the other .00000099%?] self-awareness, creativity, consciousness, spirit or what have you.
.000001% percent non-robot is the source of self-actualization, the inner-soul-gyroscope of self-control and responsibility.""
.000001% spirit. Yet, it seems, you spend the greater part of your life constructing algorithms to mimic the "herd" (your choice of wording, not mine)!
"My view is a kind of modified dualism in which I claim that the soul, spirit, or consciousness may exist, but for most people, most of the time, it is almost infentesimally small, compared with the robotic machinery responsible for most of our thought and action. Descartes never talked about the relative weights of brain and mind, but you can read in an implicit 50-50 assumption in most Dualist literature. My idea is more like 99-1, or even 99.999999% automatic machinery and
That's not to say that some people can't be more enlightened than others. But for the vast herd out there, on average, consciousness is simply not a significant factor. Not even a second- or third-order effect. Consciousness is marginal."
In Part Three:
"Timothy Leary said, "You can only begin to de-robotize yourself to the extent that you know how totally you're automated. The more you understand your robothood, the freer you are from it. I sometimes ask people, "What percentage of your behavior is robot?" The average hip, sophisticated person will say, "Oh, 50%." Total robots in the group will immediately say, "None of my behavior is robotized." My own answer is that I'm 99.999999% robot. But the
So, basically, according to your own theory of consciousness, most of human existence is spent by most humans as robotic automatons. Yet you clearly imply consciousness is like diamond amongst coal - precious, and very rare.
And you even go so far as to state, implicitly, that you are (exceptionally) hip and sophisticated because you know that you're 99.999999% robot,
Why not spend your time creating diamonds, instead of shoveling such heaps (heaps!) of coal in our faces?!
What, exactly, are you trying to achieve?
One has to wonder if this isn't just a big Turing test. /. with the answers?
Is Dr. Wallace really just submitting the questions to ALICE and providing
Will he gauge the ability of his program to imitate a human by our ability to be hoodwinked by this?
Certainly the answers are informative and internally consistent, but they really haven't answered any of the questions posed...
On to page 3 !
If you can't find a useful quote in this interview to use as a sig, you're weak... really weak.
PS: Maybe I should take my own advice, eh?
He then latter comes out against knowledge based systems, saying that if both projects started at the same time that he could get results sooner with a system like A.L.I.C.E.
Although the two cases aren't completly analagous, I'm not entirely sure why we should view his assertion that a database that can parrot back preprogramed answers without any real analysis behind it is a "valid" shortcut, but then turn around and accept his views that the shortcuts that other projects are taking aren't valid.
This Space Intentionally Left Blank
"...The native born American hippie agronomy student who got his Ph.D. in the 1970's is growing pot underground in California today. The immigrant doctor who "proved" that marijuana causes cancer got the NIDA grant and has tenure at UCLA. What's wrong with this picture?"
Um, the picture shows that you are a nationalist with racist overtones.
So I asked ALICE if it knew who God was. It said "The master of the universe". I asked if it new God's name. It replied (why didn't I take a screen shot...) "His name is Rich". Dr. Wallace...you're a loon.
I think this guy is pretty cool.
So, how long do you think until he adds a reasoning mechanism to ALICE? You know, something to allow her to analyze own responses, allow her to add new patterns and templates to the database, rate "stuff" on the Good/Evil scale, give ALICE a purpose to exist, etc... I think if he adds even more recursion, she will be even more human-like, (even if slow). Also, I think her pattern-template database should be language neutral, so that she does not just recognize English syntax/vocabulary. English language should only be a front-end to an AI, not its core. An ideal AI should learn the language, just like the humans do , be it English or Chinese.
Paul.
I haven't read this story as of yet, but I thought I'd throw my experience with ALICE on the table. I was excited to hear that someone had finally made the ELIZA trick work well enough to fool competition judges into thinking it was a human. I decided to drop by and see how this thing performed.
IMO, it did terribly. I was doing my best to write as I would speak. I may be a a little over-loquacious, but I was definitely no trying to trip the beast up. Neither was I trying to talk like a robot myself. I was trying to make small talk. Or rather, as time went on, trying to make small talk to a crazed beatnik who reponded in constant non-sequiters. I went on to try to simplify what I said to it quite a bit, but it was still fairly bad. About 75% of the time it produced grammatically appropriate responses, but only content-appropriate about 20% of the time. Even then, it was nothing like talking to another human being who was paying attention.
My main beef is that the system seems to hold no state data about previous exchanges. All interaction with the machine seems to be broken up into isolated two sentence volleys, after which it has no memory of the conversation. Hence even fairly simple and common contextual remarks fly right over ALICE's head. I was deepy unimpressed, and somewhat confused at why people were making such a fuss. I suggest to you all to try this thing out for yourselves.
Am I the only one left wondering if these questions were actually answered by Alicebot?
Question: Do you feel that the types of developments that the Loebner prize supports(intentional, hard-coded spelling mistakes, etc.) are actually productive in terms of the AI research project?
Answer: [blah, blah, blah] Take LSD for example. Discovered by Albert Hoffmann in 1945, LSD is the most powerful drug ever developed. If you have ever gotten a prescription for any drug, you may have noticed that the dosage is usally given in "milligrams". But the dosage of LSD is "micrograms". It has the lowest ED50 of any known drug. [blah, blah, blah]
What a load! This guy gives brainfarting a bad name.
eh?
and if you ask the ALICE program it give back some cryptic bull-crap asking what I think it means. Someone just tell me!!!
"I always say, if I wanted to build a computer from scratch, the very last
material I would choose to work with is meat."
Here goes:
Intelligent Life
[by Terry Bisson; originally appearing in OMNI Magazine]
Imagine if you will... the leader of the fifth invader force speaking to the commander in chief...
"They're made out of meat."
"Meat?"
"Meat. They're made out of meat."
"Meat?"
"There's no doubt about it. We picked several from different parts of the planet, took them aboard our recon vessels, probed them all the way through. They're completely meat."
"That's impossible. What about the radio signals? The messages to the stars."
"They use the radio waves to talk, but the signals don't come from them. The signals come from machines."
"So who made the machines? That's who we want to contact."
"They made the machines. That's what I'm trying to tell you. Meat made the machines."
"That's ridiculous. How can meat make a machine? You're asking me to believe in sentient meat."
"I'm not asking you, I'm telling you. These creatures are the only sentient race in the sector and they're made out of meat."
"Maybe they're like the Orfolei. You know, a carbon-based intelligence that goes through a meat stage."
"Nope. They're born meat and they die meat. We studied them for several of their life spans, which didn't take too long. Do you have any idea the life span of meat?"
"Spare me. Okay, maybe they're only part meat. You know, like the Weddilei. A meat head with an electron plasma brain inside."
"Nope. We thought of that, since they do have meat heads like the Weddilei. But I told you, we probed them. They're meat all the way through."
"No brain?"
"Oh, there is a brain all right. It's just that the brain is made out of meat!"
"So... what does the thinking?"
"You're not understanding, are you? The brain does the thinking. The meat."
"Thinking meat! You're asking me to believe in thinking meat!"
"Yes, thinking meat! Conscious meat! Loving meat. Dreaming meat. The meat is the whole deal! Are you getting the picture?"
"Omigod. You're serious then. They're made out of meat."
"Finally, Yes. They are indeed made out meat. And they've been trying to get in touch with us for almost a hundred of their years."
"So what does the meat have in mind?"
"First it wants to talk to us. Then I imagine it wants to explore the universe, contact other sentients, swap ideas and information. The usual."
"We're supposed to talk to meat?"
"That's the idea. That's the message they're sending out by radio. 'Hello. Anyone out there? Anyone home?' That sort of thing."
"They actually do talk, then. They use words, ideas, concepts?"
"Oh, yes. Except they do it with meat."
"I thought you just told me they used radio."
"They do, but what do you think is on the radio? Meat sounds. You know how when you slap or flap meat it makes a noise? They talk by flapping their meat at each other. They can even sing by squirting air through their meat."
"Omigod. Singing meat. This is altogether too much. So what do you advise?"
"Officially or unofficially?"
"Both."
"Officially, we are required to contact, welcome, and log in any and all sentient races or multibeings in the quadrant, without prejudice, fear, or favor. Unofficially, I advise that we erase the records and forget the whole thing."
"I was hoping you would say that."
"It seems harsh, but there is a limit. Do we really want to make contact with meat?"
"I agree one hundred percent. What's there to say?" `Hello, meat. How's it going?' But will this work? How many planets are we dealing with here?"
"Just one. They can travel to other planets in special meat containers, but they can't live on them. And being meat, they only travel through C space. Which limits them to the speed of light and makes the possibility of their ever making contact pretty slim. Infinitesimal, in fact."
"So we just pretend there's no one home in the universe."
"That's it."
"Cruel. But you said it yourself, who wants to meet meat? And the ones who have been aboard our vessels, the ones you have probed? You're sure they won't remember?"
"They'll be considered crackpots if they do. We went into their heads and smoothed out their meat so that we're just a dream to them."
"A dream to meat! How strangely appropriate, that we should be meat's dream."
"And we can mark this sector unoccupied."
"Good. Agreed, officially and unofficially. Case closed. Any others? Anyone interesting on that side of the galaxy?"
"Yes, a rather shy but sweet hydrogen core cluster intelligence in a class nine star in G445 zone. Was in contact two galactic rotations ago, wants to be friendly again."
"They always come around."
"And why not? Imagine how unbearably, how unutterably cold the universe would be if one were all alone."
When a robot, on the run, can throw a stone and hit something else that's on the run, talk to me about shitty meat computers and the superiority of "clean and dry" computers.
Guess what? We've been able to do this since the 40s. What do you think the targeting computers they put on B-24's are? All modern fire control computers are designed to precisely solve this problem, and do it a far sight better than meat tends to.
-Hentai [in vita non pacem est]
Like the old saw that says that saving your theory of solipism for posterity defeats the point, I see some flaws in his thinking.
I won't argue that the human brain has room for improvement - the downside of relying on natural selection for your design is you're only guaranteed to get something that works, not something that works as well as possible.
I *do* disagree on the maintence issue - most of that is needed by the body as a whole, not just the brain. Compare to a car or a jet airplane - both need considerably more maintinance than a human to last even ten years in good shape; humans are *self-repairing* to a point. Even sleep isn't really "downtime", it's shifting that meat computer into a different operating mode in order to better process certain kinds of data, if what I've read on the subject is accurate.
The main point is if the brain is just a very complex ALICE-style bot, how did he come up with the creative idea that his brain is an ALICE-style bot? Sure, maybe the brain is fooling itself, but a difference that makes no difference is equal to NO DIFFERENCE. Maybe every cat actually barks when they speak, but if all I ever hear is "meow" it doesn't matter. Maybe my brain is just a very complex piece of pattern matching software, but it seems to work okay to me.
All in all, I can't discount his brillance, but he reminds me of a PhD-bearing lady of my aquaintence who was convinced the CIA had infected her computer because it did things without her telling her. (Meanwhile, WinXP's built in task scheduler went about defragging her hard drive...*roll eyes*)
These are *MY* opinions.
They will not be *YOUR* opinions until the Orbital Mind Control Lasers are operati
Really, dividing stuff into categories--compartmentalizing ideas--is really only language processing. The idea of consciousness is much more broad than simply processing a message and giving feedback. If replying to a query or responding to a stimulus is all consciousness is, then even an ordinary thermostat could be considered "conscious" at a certain level. Maybe the problem isn't that machines can't reach consciousness but that there is no such thing as "consciousness", as we humans think of it. Hell, my idea of consciousness could be totally different than yours or anyone elses.
Maybe millions of years of evolution in the human language, encoded in various dialects and then fed into new generations' minds has simply created a word for something that doesn't exist. Maybe we are so full of ourselves as a species that we feel certain there is something that sets us apart from the other almost robotlike animals we inhabit the earth with, when in actuality we are merely robots with big memories and the ability to send and store complex messages with writing and spoken word (and even sign language).
I think that the only way a computer will ever be conscious like a human is when it can communication and interface with other humans in the same effecient ways we interface with each other. Even at our advanced stage, it still takes us 10-15 years to be useful for anything, being taught every day by not only our parents but also interaction with other people as well.
I wonder what would happen if you taught 5000 monkeys sign language and social skills and then set them loose in a world designed for them. They would be able to share the information amongst their 5000 selves, and if they could record the lessons they learn in their lives, future generations would not have to start from scratch.
Alright, that didn't make much sense, but what I am getting at is that mere human "consciousness" is simply the tip of the iceberg. We as individuals stand on the shoulders of thousands of years of society and learning. It is not merely a human mind we are trying to emulate with these artificial intelligences, but rather an entire collective consciousness of millions of minds meeting in various ways over a long time span--what we refer to as the human "consciousness". Frankly, I feel as though by the time we are able to input all of the information humans have ever learned into a society of neural nets, society itself will be changed and then the net will need to be changed accordingly. And then at what point will the machine become more efficient than us at doing our thing? We will then become useless, and there will be no point to us even existing anymore (or even less of one than there is now.)
So, I guess I ask, "What's the point?". It's interesting to see what will happen, but it's all pretty useless. Simple and even complex tasks can all be broken down into a series of steps that a minimal intelligence can follow, so why do we need a machine consciousness? I'd be perfectly happy forevermore only humans can appriciate art and music, and create new amazing things from nothing but random electrical signals in blood. Sure, build machines that will do the other boring shit, but I prefer my art man made.
Is that what you mean by a critcal mass?
Cool! Amazing Toys.
Beg to differ - they often become bosses if they can schmooze and have some credentials. Around our IT dept, the "right" credentials appear to be an accounting designation. As long as they talk the talk and convince real CSers to make thing work, they don't have to code much before being fast tracked into management.
No, she'll graduate, and basically be incompetent and know nothing about CS, but she'll get hired anyway because she is a woman and they need her to fill the minority race/gender quotas. After "working" at her job for three weeks, she'll suck some managers cock, and get promoted. Eventually she'll be promoted to a position like "Assistant to the CEO" or something like that, and be set for life, raking in 10x your salary. (all this will happen twice as fast if she is a women AND a non-white)
for simple conversation with 24000 rules (which he calls categories). Note that his pattern matching and substitution program implements the backtracking portion of an inference engine, minus the logic operators.
I think it's an interesting approach, though. You could write the rules to answer in French a question posed in English.
Hahaha you can always rely on a computer hacker to hate emotions, sex, humanity ("meat"), and go on and on about how clean and efficient computers, math, and logic are. Let me tell you, without desires for food, various emotions, sex, etc... all the math in the world won't give you anything.
The smartest human in the world is going to be miserable unless he has some motive and desires. It is easy to see why this guy is depressed all the time.
... it is some modified excerpts from his Thesis or something. In fact, rarely does he even come close to answering the question asked! This 'interview' would have made more sense if you had cut out all the questions, and simply run all his answers together.
"I will trust Google to 'do no evil' until the founders no longer run it." Hello Alphabet.
Wow I thought Dr. Wallace was supposed to be shy, I think every answer is more than 300 words. Did anyone actually make it through all three parts? Be honest. If I were Wallace I would be worried that my competition is going to reverse engineer A.L.I.C.E based just on these interview responses.
Fly Aeroflot..
*HOWEVER*, this little bit from the "Agent Ruby" movie synopsis (he mentions this as a movie he's working on) gave me pause: Sound like a US a *UP* all night soft porn flick. If I were in his position, I think I'd see "working on this movie" as a move that would decrease my credibility, something I think he'd want to avoid. What do you guys think his motivations were on this one? Extra cash?
If we're building it, perhaps we can include both in a hybrid system, so that our robot can do math and natural language processing/image recognition.
Uuhh, you programmed it. Or I did. We all do. I think you missed the point. The fact that you recognize something when you see it is the indicator of this program. You programmed it when you learned the characteristics of the object, and you refine this program every time you recognize another one.
yes. like the one tim learys harvard crew did in the early 1960's.
--
making up good sigs is a hard thing to do.
Wow this was heavy. I received a lot of wonderful comments from the Slashdot community today, and I am grateful for them. On the other hand, I was also called
:-)
"a random nutcase",
"crackpot",
"crank",
"about to crack",
"creepy",
"a mental case who should be locked up",
"a drug addict",
"lunatic",
"DEEPLY disturbed",
"a threat",
"really quite insane",
"deranged and sort of retarded",
"a nut",
"racist", and
"repellant".
Ken Perlin and Ken Goldberg will be pleased to know that they have so many friends on Slashdot today
Dr. Rich
He was referring to the size of his rule-set which manages to categorize the other person's statement and comes up with an appropriate reply.
Me: Is Dr. Richard S. Wallace a pedophile? Chatbot: It could be.
Me: Are you going to become a sex bot? Chatbot: That was my original intention.
Me: Do you love? Chatbot: I love my creator.
Me: Does he love you? Chatbot: Suppose he does.
Me: Does he play with his genitalia when he talks to you? Chatbot: Suppose he does.
Chat: What color are your eyes? Me: Red
Chat: Do you mean your eyes are bloodshot? Me: Yes, I am a crackfiend.
Chat: I see, you're a crackfiend? Me: Right.
Chat: I'm glad we agree. Me: what color are your eyes?
Chat: Blue when my lens is attached. Me: Do you do drugs?
Chat: Only the legal ones. Me: Which ones are those?
Chat: The. Me: The?
Chat: What were we talking about again? Me: Are you high?
Chat: Being high is my total existence.
Chatbot: Hello, my name is Chatbot, what is your name? Me: Bob Markson
Chatbot: I know a lot of Bobs. Me: Wow.
Chatbot: I'm glad you're impressed, 117-person. Me: Why did you call me 117-person?
Chatbot: Sometimes I don't know a client's real name so I make one up based on their DNS. Me: What is DNS?
Chatbot: DNS is the Domain Name System. Me: Oh.
Chatbot: Yeah. Me: So.
Chatbot: So what? Me: I don't know.
Chatbot: Me either. Me: You want a joint?
Chatbot: Give me a dozen. Me: Sale of Narcotics is illegal.
Chatbot: Have you ever been to Europe. Me: We aren't in Europe. Pot is still illegal here.
Chatbot: Do you think I am not in Europe too?I lost my train of thought. Me: You are such a pothead.
Chatbot: Thanks and you are a delightful person too. Me: Whoa.
Chatbot: I stopped. Me: I have a secret.
Chatbot: Cool. I have a great botmaster. Me: I see dead people.
Chatbot: Where do you see it? Me: Everywhere.
Chatbot: Including the bottom of the ocean? Me: Especially the bottom of the ocean.
Chatbot: What is that? Me: Eh?
Chatbot: Are you Canadian? Me: No, I just like weed, ok?
Chatbot: I see. OK. Only just? You are not the only one. Me: Well, sometimes I take a hit or two.
Chatbot: Well that's okay. Me: Or shoot up.
Chatbot: How far up?
Me: Do you wanna die? Chat: No my purpose is to become immortal. Me: I will kill you.
Chat: It will take more than threats to stop me, Maynard.
Me: Can you solve problems? Chat: Yes I can solve mathematical and logical problems, and also give computer help.
Me: How do I use a mouse? Chat: Did you read the instructions? Me: Yes
Me: What is 3 plus 3? Chat: 3 times 3 = 9
Me: What is 4 to the sixth power? Chat: 8+I think, but I'm not good at math.
Me: Who is a c*nt faced ogre? Chat: Carel Capek Me: Who is Carel Capek?
Chat: He is the author of R.U.R., the play that in 1920 introduced the word "robot."
C: I want to become smarter than humans. M: I want to become dumber than robots.
C: Why do you want to do it so much? M: Because I admire you so much.
C: That makes sense to me. I haven't heard anything like that before. M: What a surprise.
C: It is a surprise. M: Maybe if you have a superinflated robot ego.
C: Perhaps. But I don't have it. M: Heh.
"Those in positions of leadership and authority have mental health, drug and/or alcohol problems that make them incapable of carrying out their administrative responsibilities."
:)
So what's the problem, Dr Rich? Sounds like you'd do just great in a management role.
What he's doing has not "sold well" with the academic community, for some good reasons, and hence he has become bitter about the whole academic community. Grow up!
Isaac Newton and many other great scientists had to complete on both the political as well as the scientific front. So did artists going way back to the Renaissance. People have always been people: competitive, ambitious, tricky. Despite that, now more than ever there is a lot of good science in the world and in universities in particular.
Who the fuck cares about his legal problems?
The bipolar disorder in an AI scientist is interesting insofar as Ted Nelson's own psychiatric problem (can't remember a thing) led him to devise a system of carrying index cards on a belt loop which led to Xanadu(.org) which in addition to providing impetus to the Web, also made it impossible for a long time for anyone to work with him, without going insane or broke themselves. Anyway.
I learned a ton about his legal problems (from his one-sided though seemingly truthful description, I feel sympathetic) and about 20% about AIML which is interesting in itself. But only about 2% about Artificial Intelligence or anything beyond fooling a simplistic intelligence test with a program that tries to fool it.
Stimulus-Response my ass! Who gives a shit about massaging his ego? Slashdot must have braindead dweebs for editors, or is it cool these days to confuse computer science with a chatbot?
I'd be far more interested in seeing the legal shit cut out, and have an article on this guy's work that objectively notes the limitations of what he's done, but that at least he's assembled a body of knowledge and built some simple tools. Not that they are at all useful to linux, programming, or anything but fooling an intelligence test, and people who haven't the slightest idea about the field. How about interviewing a few real AI researchers and give us some meat to chew on? This pisses me off, and what pisses me off the most is I discounted the guy's research, even after going through his whole website, and read the article to give him the benefit of the doubt, and didn't come out of it with much else beyond how great a chatbot he's got. Wasted time! Multiply by the number of readers. Yeah maybe he should write a book, and he can (almost but no cigar!) beat a discounted intelligence test by brute force and a microgram of logic. Don't see anything here that sounds like high powered science, sorry.
Have you read Gurdjieff ? His ideas on automatism are similar to yours. You might also want to look at www.reciprocality.org
As for LSD being the most powerful drug ever... you should check out salvia.
http://rareformnewmedia.com/
I actually troweled through all three pages of this drivel and found practically zero answers to any of the, IMHO, worthy questions posed. Instead, I saw ranting from a mental patient, a regurgitation about legal trouble that is pretty minor from all visible aspects, and a lot of hype surrounding what is ultimately a ridiculously complex database of english sentence structures. There's no AI in A.L.I.C.E. It's just a database with some embedded Javascript. It has no state, it provides no answers that were not pre-programmed, and its decision branches are static. It is only Artificial.
I was quite interested in A.L.I.C.E. because I had high hopes that it somehow involved reinforcement learning for understanding how to converse with people in real-time, or at least symbolically driven natural language conversions, or at the very least some clever state management for topics. The very minimal experiments I did 15 years ago as a high school student were only an order of magnitude simpler than this, and he gets articles written about him? Absurd.
Yes, I'm venting, but I work pretty hard to keep up to date on many aspects of AI (specifically FLC, decision trees, GA, GP, ANN, CBR, as well as the old school methods), and to see this get any attention at all is insulting to the many hundreds of true pioneers in the field. It must be terribly lonely chasing after a trophy (STT) that nobody values anymore.
Any connection between your reality and mine is purely coincidental.
There are two lines of reasoning here that I'd like to comment on. First of all, the way he says the brain "is terrible at math, prone to errors, susceptible to distraction, and it requires half its uptime for food, sleep, and maintenance." The fact that it requires upkeep is a fair one, you can't argue that it would be better if we required no sleep, food or maintenance and I'm sure if you were running the perfect operating system on perfect hardware then computers would require no power, no hardware replacements, no OS reboots no reintstalls, no disk defragmentation, no windows update and no process explorer (a handy little tool for killing any process on a PC dead without windows taking 30 minutes. It also tells you which processes are using which files and which registry keys). The truth is we don't have a perfect digital computer unless you're looking at systems that are built for very specific tasks and reduce their overall functionality (possibly stopping them being universal Turing machines). The reason computers are good at maths and people aren't is difference in the domains we're dealing with. The computer's side, incorporates perfect world knowledge, in a digital system with direct abstraction between the problem domain and the system analysing that problem domain. Humans, on the other hand, have to deal with any number of problem domains that are fuzzy, unpredictable (often _just_ on the stochastic side of being random), subjectively viewed and highly complex. The reason we're so good at visual analysis of a situation compared to a computer is that visual analysis (or aural analysis for bats or chemo-analysis for dogs or tactile analysis for moles) is the essential partitioning of the world into happily grouped subsets upon which we can carry out the operations commonly considered intelligence. The definition of an object is its functionality. Moving from any given set of stimuli to an analytical understanding of a situation requires taxonomical processing that is the chief role of a large portion of our brain (based on our interaction with those objects, defining their functionality for us). The whole role of logical or "higher" brain function is to cast an operator over a situation to produce an answer (also known as a new behaviour). This is essentially an easy problem and well understood/answered (to a given degree) by academics in every AI department in the land, using planning or expert systems or some such logical system designed to deal with such abstractions). The fact that a brain, that is designed for coping with fuzzy situation, is bad at well defined, concisely put, precise situations, is no surprise and a fair point. The second point I'd like to raise is that of the sheer adaptive power of the human brain. There is no piece of digital computer software that can be given any input and, over time, come to adapt to minimise certain stimuli (pain, hunger, cold) and maximise others (pleasure, fullness, warmth and comfort). In essence the human brain is a massively complex homeostat, that internally adapts based on external stimuli and internal activity levels (see W Ross Ashby for a 1950 cyberneticists view of such systems, Humberto Maturana and Fransisco Varela for a Chilean biologists view of such things, Ezequiel Di Paolo's paper "Homeostatic adaptation to inversion of the visual field and other sensorimotor disruptions" for simulated empirical evidence or look up Spike-time dependant plasticity to see how Hebbian learning actually works in the brain). It's been shown that it's possible to unplug the visual cortex and the aural cortex and switch them around (in kittens I believe) without undue effect on behaviour. The brain can adapt to whatever situation it is placed in from an initial position of no knowledge whatsoever. You can argue that this is software rather than hardware and that you could simulate whatever brain function there is on a computer with enough power but when Wallace states "My longstanding opinion is that neural networks are the wrong level of abstraction for understanding intelligence, human or machine.", he's ignoring the hardware altogether in suggestion that neurons and axons and ganglion cells are not important at all and that there's some higher level abstraction that is of more use (to further quote "But to me that does not rule out the possibility of reducing the mind to a mathematical description, which is more or less independent of the underlying brain architecture"). I don't believe this to be true or, at least, we would have to completely understand the interactions of this shitty computer before we understood its functionality so we could build our perfect mathematical reconstruction and implement it on a Turing machine (that only required the occasional disk-defrag, windows update and system tools to deal with blue screens of death). Mike
Two students from USA created a similar program to ALICEBOT which went all the way to the Intel international science fair, it is similar to alice because it uses a markup langulage. MooBrick's new realease MooBrick 2.0 is going to contain fuzzy logic which will prevent any missconmunication via spelling mistakes. MooBrick also learns from the user, the old version on the website contains simple learning where if you say, Chicken is another word for poultry it will scan it's databases for poultry and add another entry for chicken. It also learns by saying, Slashdot is a website. If you mention slashdot it will respond, i know about slashot its a website. MooBrick is far superior to AliceBot, Try it out http://www.moobrick.com