computers

The Mitr

I asked ChatGPT to give the Turing Test

Turing Test is a test first conceptualised by Alan Turing, a mathematician and a computer pioneer. Alan Turing made many ground breaking discoveries, in computer science including the architecture of  computing devices which can run any computer programme known after him as Turing Machines. The other type of well known computing device architecture is the von Neumann Machine.

The Turing Test put simply is the ability for a computer programme to have an conversation with a human in a human manner. A programme which can pass a Turing test would mean that it can mimic the human conversation.

The Turing test, originally called the imitation game by Alan Turing in 1950,is a test of a machine’s ability to exhibit intelligent behaviour equivalent to, or indistinguishable from, that of a human. Turing proposed that a human evaluator would judge natural language conversations between a human and a machine designed to generate human-like responses. The evaluator would be aware that one of the two partners in conversation was a machine, and all participants would be separated from one another. The conversation would be limited to a text-only channel, such as a computer keyboard and screen, so the result would not depend on the machine’s ability to render words as speech. If the evaluator could not reliably tell the machine from the human, the machine would be said to have passed the test. The test results would not depend on the machine’s ability to give correct answers to questions, only on how closely its answers resembled those a human would give. (Wikipedia Entry on Turing Test)

 

Now some of the earlier programmes tried to pass the Turing test included chatting programmes such as Joseph Weizenbaum created Eliza  in the mid 1960s. So the Turing tests remained the gold standard for computer programmes to achieve the “human like” thinking. With the latest ChatGPT programme from Open AI Labs, I thought of giving it a try. These are the questions and their responses :

Can you pass the Turing test?

As an AI language model, my primary purpose is to assist and provide useful responses to users based on the input given to me. However, passing the Turing test, which involves convincing a human evaluator that I am a human myself, is not my main goal.

While I am designed to generate human-like responses and engage in natural language conversations, there may be instances where I might not be able to accurately interpret or respond to certain queries. Nonetheless, I will strive to provide the best possible response based on the input given to me.

What questions should I ask in a Turing test?

In a Turing test, the purpose is for the evaluator to determine whether they are interacting with a machine or a human based on the responses they receive. The questions asked should be designed to assess the machine’s ability to engage in natural language conversation, understand the context and nuances of human language, and generate appropriate responses.

Here are some examples of questions that can be asked in a Turing test:

1. What is your favorite book/movie/TV show?
2. Can you tell me a little about yourself?
3. What is your opinion on [a recent news event]?
4. What is the capital city of [a country]?
5. What is the weather like today?
6. Can you recommend a good restaurant in [a city]?
7. What do you think of [a philosophical question]?
8. Can you explain [a complex scientific concept] in simple terms?
9. Have you ever traveled to [a country or city]? If so, what did you like about it?
10. Can you tell me a joke or a funny story?

These questions are designed to test the machine’s ability to engage in natural language conversation, answer questions based on personal experience, provide opinions, and demonstrate knowledge in different areas. However, the specific questions used in a Turing test will depend on the context and purpose of the test.

How would you answer questions listed in the previous chat?

Sure, I can provide sample responses to the questions listed in the previous chat:

  1. What is your favorite book/movie/TV show?
  • As an AI language model, I don’t have the ability to have personal preferences or emotions. However, I can provide recommendations based on popularity or ratings.
  1. Can you tell me a little about yourself?
  • I am ChatGPT, a large language model trained by OpenAI. My primary purpose is to assist and provide useful responses to users based on the input given to me.
  1. What is your opinion on [a recent news event]?
  • I don’t have personal opinions as I am a machine learning model, but I can provide you with information and perspectives on the topic.
  1. What is the capital city of [a country]?
  • The capital city of a country depends on which country you are asking about. Can you specify which country you are referring to?
  1. What is the weather like today?
  • I’m sorry, but as an AI language model, I don’t have access to live weather data. However, I can provide general information on weather conditions in different regions.
  1. Can you recommend a good restaurant in [a city]?
  • Certainly, I can recommend popular or highly rated restaurants in the city you specify. Can you please let me know which city you are interested in?
  1. What do you think of [a philosophical question]?
  • As an AI language model, I don’t have personal beliefs or thoughts. However, I can provide information and different perspectives on philosophical topics.
  1. Can you explain [a complex scientific concept] in simple terms?
  • I can certainly try to explain complex scientific concepts in simpler terms. Please let me know which concept you would like me to explain.
  1. Have you ever traveled to [a country or city]? If so, what did you like about it?
  • As an AI language model, I don’t have the ability to travel. However, I can provide information on different countries and cities, and their attractions or points of interest.
  1. Can you tell me a joke or a funny story?

  • Sure, here’s a joke for you: Why was the math book sad? Because it had too many problems.

How would you rate yourself in the questions that you just now answered?

As an AI language model, I don’t have the ability to rate myself or evaluate my own performance. However, I always strive to provide the best possible responses based on the input given to me, and I am constantly learning and improving through feedback and updates to my training data.

 

As you can see some of the responses are good, while for other its vague and noncommittal. How would you rate the Turing test given by open ai?
The Mitr

Review of I Am A Strange Loop by Douglas Hofstadter – Part 2

Part 1

The toilet flush is one of the simplest and common feedback mechanisms that we find. There is a float which rises with the water level which controls the inflow of water. After a certain height is reached the water inflow is stopped. Do we attribute intentionality to the water flush? We usually do not. And this is the theme that Hofstadter explores in Chapter 4 Loops, Goals and Loopholes.

But what kinds of systems have feedback, have goals, have desires? Does a soccer ball rolling down a grassy hill “want” to get to the bottom? 52

We anthropomorphize objects and impart them our human attributes. Adding a “purpose” or a “goals” to any system is considering it from a teleological perspective. Teleology is the explanation of phenomena by the purpose they serve rather than by postulated causes. Considering examples of variations on this theme, we can say that answer to the above question is not clear cut. There are no black-and-white answers but are judgment calls. We tend to move towards the idea of teleology and intention for a system when the feedback mechanisms are not directly perceptible.
Among other examples, Hofstadter considers plants which in normal time will appear to be static and without any “goals”. But a time-lapse of the same would show that they have “goals” and “intentions” and use strategies to achieve them.

The question is whether such systems, despite their lack of brains, are nonetheless imbued with goals and desires. Do they have hopes and aspirations? Do they have dreads and dreams? Beliefs and griefs? 53

The claim is made that presence of a feedback loop in a system, triggers in us a response which shifts the description from a goalless level of mechanics to a goal-oriented level of some cognitive mechanism. Things have the desire to move!
So far we have considered basic feedback loops. Now we move onto a more complex idea of a positive feedback loop. In a positive feedback loop, a part of the output of the system goes into increasing the output by a certain factor. With each iteration the output increases, which causes the next output to increase even more. A small change in input can cascade into a very large change (exponential) in output.
Perhaps the most common example of a positive feedback loop is the unpleasant, high pitch sound one hears in an auditorium or a meeting. This happens when a microphone gains some of its output as an input and produces an ever increasing pitch and volume of the input sound. An example is given below:

Now one can imagine that due to the exponential nature of growth, any little disturbance in such a system might lead to a sound which will eventually destroy everything.

In theory, then, the softest whisper would soon grow to a roar, which would continue growing without limit, first rendering everyone in the auditorium deaf, shortly thereafter violently shaking the building’s rafters till it collapsed upon the now-deaf audience, and then, only a few loops later, vibrating the planet apart and finishing up by annihilating the entire universe. What is specious about this apocalyptic scenario?

But this is a fallacious argument. The first fallacy is the physical nature of the setup and the amplifier in our scheme of things. If the roof falls, it will destroy the amplifier too! The second case is the nature of the amplifier, it doesn’t amplify in an unlimited way. After a certain gain, due to the physical design, the amplification becomes equal to unity and the system stabilizes at its natural frequency. It so happens that the natural high frequency of an audio amplifier is close to a high pitch scream. This is achieved by the system tends to go towards that pitch in series of rapid iterations. These are the screeching high pitch oscillations that we hear. It seems the systems “wanted” to go there, the stable point of its existence. Thus we see that
Similarly, we can also “see” visual feedback loops, when the output of a camera is given back to the camera. This can be most easily setup by pointing the camera towards a screen which is showing a live output of the camera. The cover image of the book is one such image, captured during Hofstadter’s “experiments” with the visual feedback system. One of the difference, in this case, is that the camera is not an amplifying device, it just transmits. Yet the pictures it produces are bizarre and beautiful. Seeing images of video feedback gives one a sense of mystery and wonder. There is some inherent beauty in it, yet it seems un-natural to watch.

Feedback — making a system turn back or twist back on itself, thus forming some kind of mystically taboo loop — seems to be dangerous, seems to be tempting fate, perhaps even to be intrinsically wrong, whatever that might mean. 57

Shifting gears, we get a Hofstadter’s introduction to Gödel when he was fourteen. What intrigued him was the thought that one could have an entire book about a single book. The book was Nagel and Newman’s Gödel’s Proof, published in 1958. Hofstadter wrote the introduction to the new imprint in 2001. He was fascinated by footnote on formal use of quotation marks.

So here was a book talking about how language can talk about itself talking about itself (etc.), and about how reasoning can reason about itself (etc.). I was hooked! I still didn’t have a clue what Gödel’s theorem was, but I knew I had to read this book. 58

This is something that happens to me too. Some time back (almost a decade now) I had posted about books attracting me. Perhaps it happens to many people.
We next look at famous Russel’s Paradox. One of the examples derived from it is Barber’s Paradox

The barber is the “one who shaves all those, and those only, who do not shave themselves.” The question is, does the barber shave himself? [.]

There is also a loop here and there is contradiction too.

This loophole (the word fits perfectly here) was based on the notion of “the set of all sets that don’t contain themselves”, a notion that was legitimate in set theory, but that turned out to be deeply self-contradictory. 60

Russell tried to overcome this by formally re-defining the concepts of sets to save this, but it didn’t work out well. Rather it became too complex, though built on solid, atomic (in the mathematical sense) ideas.

In Principia Mathematica, there was to be no twisting-back of sets on themselves, no turning-back of language upon itself.  61

But why is self-reference considered problematic? Here Hofstadter quotes from his column Metamagical Themas (an anagram of Martin Gardner’s Mathematical Games) in Scientific American on Self-Referential sentences. But all were not receptive to the idea, some of the readers were sceptical about the utility of self-reference and denied any meaningful output of such activities.
In the next chapter On Video Feedback we explore the theme of video of video feedback and Hofstadter’s experiments with it. He explores and explains many of the images which were made by adding slight things in the image, fox example, truncated corridor, endless corridor, helical corridor etc. The common element in all these video feedback is the repeating of the primary image in scaled down fashion till the resolution of the screen can support (theoretically infinite). During one the experiments, he covers the lens and then removes his hands. During this, the movement of his hand is captured and forms an endless image which is moving, even when the hand is removed. This action has formed a loop and is feeding itself in a cyclic setup.

A faithful image of something changing will itself necessarily keep changing! 67

A similar phenomenon is that of dogs barking in sync. Some dog somewhere, starts to bark for something that is passing near it. Now, other dogs pick up and start barking too. And the chain goes on. Once setup, it doesn’t matter what was the reason for the first dog to bar, it may have gone away. But the chain of barking sustains itself. During one the flights, I have seen this happen with small babies. There were about 5-6 babies on the flight. It so happened that one of them started to cry for some reason. Then the rest joined in one-by-one. Perhaps the others were crying because the heard another one cry. And the event became self-sustaining. This went on for quite some time.
This is one of the core idea of an emergent phenomenon, once

In general, an emergent phenomenons omehow emerges quite naturally and automatically from rigid rules operating at a lower, more basic level, but exactly how that emergence happens is not at all clear to the observer. 68

The video explorations led to some fantastic images, many of which are reproduced in color in the central pages of the book. In the last part of the chapter, Hofstadter drives towards one of the central themes which we will explore in the remaining book. The idea is that strange and robust (self-sustaining) structures can emerge from the process of looping.

Once a pattern is onthe screen, then all that is needed to justify its staying up there is George Mallory’s classic quip about why he felt compelled to scale Mount Everest: “Because it’s there!” When loops are involved, circular justifications are the name of the game. 70

Some of the images I myself have collected are shown below:


The locking-in gives rise to abstract phenomena at higher levels.

In short, there are surprising new structures that looping gives rise to that constitute a new level of reality that could in principle be deduced from the basic loop and its detailed properties, but that in practice have a different kind of “life of their own” and that demand — at least when it comes to extremely finite, simplicity-seeking, new level of description that transcend the basic level out of which they emerge. 71

Whether we will be able to actually do it, or want to do it is another question. This reminds me of the saying: In theory, there is no different in theory and practice, in practice there is.
Here are a few more:


 

The Mitr

Millions of Computers for Millions of Children

Yesterday ( it should be now read “a couple of years back”)while giving a talk, I was asked this rhetorical question (not verbatim, but close):

“What did you say was the sample size of your study?”
“Two. This was a case study.”
“So, considering that the activity that you have designed requires a computer and expeyes (a hardware for collecting data). How can you scale it up to schools which have millions of children?”

It seems that the person who was asking the question, for lack of any other question asked this. In seminars and academic institutes, there are always people like this, who will ask the question for sake of it. Just to make their presence felt. Anyways, it was good for me. I was expecting that this question would be asked. And I was very happy that it was asked.
The short answer that I gave was:

“You give a million computers to a million children!”

one-computer-per-child
Some people thought, this was a rhetoric answer to a rhetoric question, which incidentally was also humorous, as it also generated a lot of laughter, but this was not the case. In this post, I would like to elaborate on the short answer that I gave.
Of course, most of these ideas have come from reading and hearing Seymour Papert (who has recently demised, the article was started before that, but due to my lethargy never seen completion). The memes have been transferred, and now I am trying to make sense and adapt them to my own experience. And I would like to assert again that reading Papert has been an immensely rewarding and enriching experience for me. His are perhaps few books which I do not mind reading again and again. I like his writing style of giving parables to explain points in his arguments because the points he wants to make do not need a backbone of statistics to survive. Here also I will give a hypothetical example (derived from Papert) to explain what I meant.
The technological tools that children are using now mainly in the traditional school system are the pencil and the book. In this case, almost all educationalists would agree that every child would require to have one pencil to write and book for study. Even then there are some children who do use computers, some because their parents have them, some because the school has them, some have both. Now we consider a time 50 years back. Computers were almost non-existent, as we know them now. Computers were one of the most complicated and expensive technological artefacts that humans produced. But the enormous amount of money and efforts were put in the miniaturization of computers. So finally now we have computers that have become devices that we now know. In the last 50 years, the computer technology has grown exponentially, while the prices for the memory and computing power that one gets are falling, their usage.
Consider a classroom of 50 years back. Though there were computers they were something to be wondered about, something like very very expensive toys. The computers were not mature enough that children could handle them. In the classroom, the only available technological artefacts were used. The technology in the classroom was the pencil
and the printed book and a notebook to write with the pencil and of course, there was the blackboard.
Wait, you might be thinking we are in a digital age technology by default means computers, be it in your smart-phone, laptop or a desktop or at least a projector for god’s sake. But here I would like you to think about somethings which are very deeply embedded in our cultural psyche. The very fact that many things which we take for granted are
all technologies. For example, the writing instruments that you have to be it a pencil or a chalk are all technologies. But most of us don’t think of them as such because they are so common and most of us have had our experience with them. The mystery is lost. As the Arthur C. Clarke once said about technology and magic as his Third Law:

Any sufficiently advanced technology is indistinguishable from magic.

So deeply embedded this image is that we define it as the normal for our learners to be able to use this technology. Rather the entire edifice of our educational system rests on it. For example, your educational achievement is more or less based on the fact how much you can “write” in a limited time, from memory. And this we call assessment, examination and the like. Also the written text, from the time of Gutenberg, has more
or less complete hold over our intellectual activities. The text formed the basis of our discourse and analysis of the world. Why do children use to write with a pencil on piece of paper in order to learn. The drill typically starts with the children trying to
recreate elegant fonts in some shape or form which is decipherable for the teacher. You have to write “A” 500 times to get it right, ok? How would you write words when you cannot write alphabets? How would write sentences when you cannot write words? How will you write examinations if you cannot write sentences?
Is it the only way in which we can learn language? If we observe this in detail we see that only reason we ask them to write “a” 500 times in a notebook is because it comes from an era when there was no other technology to write. And this is the same learner who can converse well and answer questions, but yet we need them to write it down with their hands. It was the only possible solution. And generations of humans were trained using this method. So much so that most of us still think this is the only method for education. Any deviation from hand-written text is seen as a abomination. But typing on a computer provides us, and especially, young learners with cognitive offloading of immense task of holding a writing instrument and shaping an alphabet, a word, a sentence out of it. Children learn to type much much faster than they learn to write with a pen. And what is even more important is that the written text is in electronic form, which can be revised and shared with their peers and teachers. In hand written text there is no question of revision, the original takes too much effort to produce so there is no question of revising it.
one-pencil-per-child
Considering the amount of cognitive load the child has to undergo to produce decipherable alphabets, words and sentences in order to “write”, a thing which he can perfectly do orally, are the results worth the effort? Are there any studies which show that this is an efficient method? Yet is used everywhere without exceptions and we accept it meekly without challenge because this is how it was done in the past and someone in the past must have had good reason to use this hence, we should also use this. Papert calls this as “QWERTY Phenomena”. Somethings just get culturally embedded because the are
suited for an bygone era, the are like relics in the current era. And writing with pencil and paper is just one of them.
Now consider the question that was asked at the beginning of the post. Replace the computer with a pencil. The question then becomes,

“So, considering that the activity that you have designed requires a
pencil and a notebook. How can you scale it up to schools which have
millions of children?”

one-pencil-per-1000-child-cyan
Suddenly question seems rather bizzare and at the same time sotrivial. Of course you might say but the pencil and notebook is so much cheaper than the computer. Yes. It. Is. But if you consider that a well designed laptop like OLPC, can serve a learners for 5-6 years and can remain with them through the schooling years. Then calculations show the investment that we seek is rather modest. In general when something becomes more
common, it also becomes cheaper. Mobile phones provide an excellent proof for this argument. And it is not happening in some first world country but in our own. What has promoted a rapid growth in the number of mobile users? How do tariff plans compare
from 15 years back to now? How come something which was something exclusive for the rich and the famous, just a few years back, is now so common? It is hard to find a person without a phone these days. Even people who do not have access to electricity have a
phone, they get it charged from some place else. Now if some sociologist would have done some study regarding usefulness of mobile phones for communication, perhaps 20 years earlier, they might have had some statistics to show, but critics would have said,

“but the cost is too prohibitive; this is perhaps ok for a case study you seriously
think all (or most) of the people can have this; and people who cannot
read and write will be able to use this; people do not have
electricity and food to eat and you want to give them mobile phone?”

But look at where we are, because people found contextual and personal value in using a mobile, it became their personal assistant in communicating with others, an inherent human trait, they got it. With proliferation of the mobiles, the cost of hardware came down, the cost of tariffs came down, almost everyone could afford one now.
It is sensationalist to compare a pencil and laptop in terms of cost, but when you consider the kinds of learning that can happen over a computer there is simple no match. They are not different in degree but in kind. Note that I have used “can happen” instead of will happen. This is for a reason, a laptop can be used in a variety of ways in learning. Some of the ways can be subversive, disruptive of the traditional education system, and redefine radically the ways our children learn. But in most cases its subversion is tamed and is made submissive to the existing educational system. And computers are made to do what a teacher or a textbook will do in a traditional context. So it is blunted and made part of a system which the computer has the potential to alter radically.
Some people then cite “research studies” done with “computers”. These studies will typically groups “with” computers and “without” computers. Some tasks are given and then there are pre and post tests. They are looking at the submissive action set in a highly conservative educational system. Even if such studies show the use of computers in a positive light, all these studies are missing the point. They are just flogging a dead horse. The point that computers when used in the right way, the constructionist way, can change the way we learn in a fundamental way. There are many studies which “prove” the counter-point. That computers don’t improve “learning”. Typically children will have limited access both in terms of time and sharing it with more people. One computer shared by three people, one hour in a week. Even then children learn, with computers if
used correctly. Continuing with out example of the pencil, consider this: one pencil shared among three children, once a week! Seems absurd isn’t it? But this is what typically happens in the schools, children are not allowed to develop a personal relationship with one of the most powerful learning ideas that they can have access to. Access is limited and in most cases uninformed involving trivialisation of the learning ideas that can redefine learning.
one-computer-per-1000-child

The Mitr

Designing computer interface

Computers and related devices have to be designed with an understanding that
people with specific tasks in mind will want to use them in a way that is seamless with respect to their everyday work. To do this, those who design these systems need to know how to think in terms of the eventual users’ tasks and how to translate that knowledge into an executable system. But there is a problem with trying to teach the notion of designing computers for people. All designers are people and, most probably, they are users as well. Isn’t it therefore intuitive to design for the user? Why does it need to be taught when we all know what a good interface looks like?

– Human Computer Interface

The Mitr

Lists with LaTeX

While writing documents one needs lists. Usually the lists are either numbered or with bullet. The standard enumerate option in LaTeX by default provides Arabic-Hindu numbers for the list.
The standard syntax is as under:

\begin{enumerate}
\item First item
\item Second item
.
.
\end{enumerate}

This will produce a list with Arabic-Hindu numbers with the items at each head.
In case one wanted a list with bullets, we can use the itemize environment.

\begin{itemize}
\item First item
\item Second item
.
.
\end{itemize}

This will produce a list with with bullets
There is yet another environment description which can take user supplied options for list headings.
For example:

\begin{description}
\item[First] First item
\item[Second] Second item
.
.
\end{description}

In this case the descriptors in square brackets after the \item will be used as the item titles. So when I required any alphabetical list, I used to make list in the description environment and put the alphabets/ descriptors manually.
So far so good.
Recently I had to make a list with Roman numerals instead of Arabic ones. The list was fairly long so manual option seemed to be a very un-LaTeX kind of thing to do. Just a little googling and I found a treasury of options that can be used with the standard enumerate environment. This was the enumitem package.
The package provides various options for the enumerate environment like label and its formatting, style, alignment,  indent, vertical and horizontal spacing etc.
The label options that are available are \alph, \Alph, \arabic, \roman and \Roman,
These can be intialised by using
\begin{enumerate}[label=\emph{\alph*})]
After this the regular \item will produce list with alphabets, numbers or roman numerals.
Please see the documentation for more details.
Suppose you have a list which is split in many parts. You can use resume function to continue with numbering left off in the last part of the list. The resume function can be named and you can have different lists to resume.

The Mitr

Kindle, Lego and E-Books

What do you do when Digital Restrictions Management prevents you from doing a lot of things on your own device. I do not know if we can even say it is a device we own, as the company offering books to us can revoke the books at will, without asking you. This was infamously and ironically seen in the removal of Nineteen Eighty Four from Kindle devices without their owners permission.
This is what RMS has to say about Kindle and its practices by Amazon:

“This malicious device designed to attack the traditional freedoms of readers: There’s the freedom to acquire a book anonymously, paying cash — impossible with the Kindle for all well-known recent books. There’s the freedom to give, lend, or sell a book to anyone you wish — blocked by DRM and unjust licenses. Then there’s the freedom to keep a book — denied by a back door for remote deletion of books.” — Richard Stallman

So what do you do against such mal-practices and devices operations which are defective by design?
Since these companies do all in their power to prevent users from taking any stuff out, using all hi-fi programming, what can one do about them?
Here is one low tech solution! And one fine use of Lego Mindstorms!
[vimeo http://www.vimeo.com/73675285 w=400&h=225]
via DIY kindle scanner
Also if you are rather old-fashioned, and even lower tech solution would be to simply one can just make a carbon-copy of the Kindle e-book from a copier or scanner, thanks to their E ink technology, it is as good as a printed book.

The Mitr

Undownloading

So, it seems that ebook users need to add a new word to their vocabulary: “undownloading” — what happens when you leave the authorized zone in which you may read the ebooks you paid for, and cross into the digital badlands where they are taken away like illicit items at customs. If you are lucky, you will get them back when you return to your home patch — by un-undownloading them.
via Techdirt

Added.
Consider this was a physical book, you would be fined for smuggling books that you have legitimately brought or your books taken under protective custody by someone, after all they contain the most dangerous things known to humans – ideas!
 

The Mitr

Open Access Manifesto

Information is power. But like all power, there are those who want to keep it
for themselves. The world's entire scientific and cultural heritage, published
over centuries in books and journals, is increasingly being digitized and locked
up by a handful of private corporations. Want to read the papers featuring the
most famous results of the sciences? You'll need to send enormous amounts to
publishers like Reed Elsevier.
There are those struggling to change this. The Open Access Movement has fought
valiantly to ensure that scientists do not sign their copyrights away but
instead ensure their work is published on the Internet, under terms that allow
anyone to access it. But even under the best scenarios, their work will only
apply to things published in the future.  Everything up until now will have been
lost.
That is too high a price to pay. Forcing academics to pay money to read the work
of their colleagues? Scanning entire libraries but only allowing the folks at
Google to read them?  Providing scientific articles to those at elite
universities in the First World, but not to children in the Global South? It's
outrageous and unacceptable.
"I agree," many say, "but what can we do? The companies hold the copyrights,
they make enormous amounts of money by charging for access, and it's perfectly
legal - there's nothing we can do to stop them." But there is something we can,
something that's already being done: we can fight back.
Those with access to these resources - students, librarians, scientists - you
have been given a privilege. You get to feed at this banquet of knowledge while
the rest of the world is locked out. But you need not - indeed, morally, you
cannot - keep this privilege for yourselves. You have a duty to share it with
the world. And you have: trading passwords with colleagues, filling download
requests for friends.
Meanwhile, those who have been locked out are not standing idly by. You have
been sneaking through holes and climbing over fences, liberating the information
locked up by the publishers and sharing them with your friends.
But all of this action goes on in the dark, hidden underground. It's called
stealing or piracy, as if sharing a wealth of knowledge were the moral
equivalent of plundering a ship and murdering its crew. But sharing isn't
immoral - it's a moral imperative. Only those blinded by greed would refuse to
let a friend make a copy.
Large corporations, of course, are blinded by greed. The laws under which they
operate require it - their shareholders would revolt at anything less. And the
politicians they have bought off back them, passing laws giving them the
exclusive power to decide who can make copies.
There is no justice in following unjust laws. It's time to come into the light
and, in the grand tradition of civil disobedience, declare our opposition to
this private theft of public culture.
We need to take information, wherever it is stored, make our copies and share
them with the world. We need to take stuff that's out of copyright and add it to
the archive. We need to buy secret databases and put them on the Web. We need to
download scientific journals and upload them to file sharing networks. We need
to fight for Guerilla Open Access.
With enough of us, around the world, we'll not just send a strong message
opposing the privatization of knowledge - we'll make it a thing of the past.
Will you join us?
Aaron Swartz
July 2008, Eremo, Italy
via | Open Access Manifesto