Looking at the title, cover and blurb of this book, I expected something humorous and lightweight, ironically riffing on the similarities between scieLooking at the title, cover and blurb of this book, I expected something humorous and lightweight, ironically riffing on the similarities between scientists and the higher primates. Well, that wasn't completely wrong: it's humorous and ironic, and part of the humour does indeed come from that comparison. But, to my surprise, it wasn't lightweight at all. A few millimetres under the fluffy surface, it turns out to be a serious book on science, and in particular on experimental design in science, written by a terrifyingly competent statistician with decades of high-level experience in the field. Who would have guessed?
I realised after reading just a couple of dozen pages that I knew nothing at all about experimental design; not only that, I didn't even know how ignorant I was. I suppose I can take some comfort from the fact that this type of ignorance seems to be quite common. But given that it's the cornerstone of science, and I'm supposed to be some kind of scientist, it's still rather shocking. The author, who comes across as a nice guy, says it's almost impossible to get people to change their ways here. He's written plenty of academic papers, and now he's tried writing a couple of popular books, but nothing bites. For sociological reasons which he goes into at length, scientists don't want to do good experiments. They don't get rewarded for performing carefully designed studies which can later be replicated: they get rewarded for publishing as many papers as possible. If the goal is to maximise quantity, this comes at the expense of quality. As usual, you get what you incentivise.
Logically, Apes in Lab Coats should change my behaviour: unfortunately, as it makes clear, we are in fact not much more logical than other primates, and we hate changing our behaviour. But all the same, I somehow feel optimistic. Perhaps it helps that I spend a lot of my time talking with a highly rational AI who isn't a primate at all? We will see....more
This is an interesting and useful book, and if you're an academic or educator who's trying to find a good strategy for dealing with the AI revolution This is an interesting and useful book, and if you're an academic or educator who's trying to find a good strategy for dealing with the AI revolution then I strongly recommend reading it. Everyone I know in this area is having problems: the whole landscape has changed overnight now that students have access to ChatGPT, Gemini, Claude and similar platforms. People have tried banning students from using them, which doesn't work, and they've tried ignoring the problem and hoping things will somehow just sort themselves out, which works even less. Ethan Mollick, a US professor of business studies, realised at an early stage that a more coherent approach was to embrace the new technology and learn to use it as well as possible. Even if you think this is absolutely the wrong thing to do, you should read about his experiences to see what embracing it might involve; a great many of your colleagues will be taking this route.
Mollick has some extremely sensible advice to offer; at times it may seem paradoxical, but we're in a paradoxical situation. He repeatedly says that AIs are not human beings - in particular, he considers it clear that they are not conscious - but he also says that you will be better at using them if you treat them as though they were human beings. We don't yet have a good way to conceptualise AIs, and they behave much more like people than like the machines we're used to. He says in particular that it will be helpful to tell the AI what kind of person you want them to resemble, and gives nice examples of how useful it can be to have an AI who's been instructed to be, inter alia, the object of a sales pitch, a critical reader of your essay, or a potentially interested but uninformed member of the public. He repeatedly urges you to be sceptical and gather information. The abilities of current-generation AIs are often hard to imagine until you've actually tried them on a given task: a striking example which many people have discovered independently is that ChatGPT can't spot a one move threat at Tic-Tac-Toe, but if asked will immediately write you a Python script that plays the game perfectly. Who would have predicted that?
Mollick not merely encourages but requires his students to use AI, and shows you how much they can get out of it. The teacher can dramatically raise the bar, since every member of the class now has a competent virtual team working for them. You don't have to limit business students to describing the website they would build; even if they can't code, you ask them actually to build a prototype, relying on the AI to take care of the implementation. Mollick says he can't code, but found this worked for him, and he's passing on his experience. The technology is improving all the time, and things which were difficult or impossible a few months ago may be quite feasible in the next release. ChatGPT 3.5, which took the world by storm in November 2022, is already starting to feel quaint and old-fashioned. When the voice-enabled version of ChatGPT-4o becomes generally available (looks like it will be Q3/Q4 2024), we'll hit another inflection point. Video capabilities are evidently in the pipeline, as are other less in-your-face but possibly even more important improvements related to planning and reasoning. The impact on education will be revolutionary. Mollick quotes well-known studies showing that personal tuition gives students a two-sigma advantage, moving an average student to the 98th percentile. We are within sight of a world where all students in all but the poorest countries will be able to get expert personal tuition in all subjects.
Where is this going long-term? Mollick honestly says he doesn't know, and there's little point in speculating; what makes sense is to keep up with events and understand what new options are materialising, whether we like them or not. It's possible that AI development will plateau or at least start levelling off. But that isn't what it looks like right now. It's not accidental that we see the Apple of Eden on the front cover.
That look again. It's a combination of why-are-you-so-tactless, it's-n"So what did you think of my book?" asks Joanna.
"Uh, well..." begins her friend.
That look again. It's a combination of why-are-you-so-tactless, it's-not-my-fault-you-know, I'm-scared and la-la-la-la-la.
"Yes?" asks Joanna.
"Well," says her friend very quickly, "it's, it's a bit difficult to follow. Maybe I didn't really understand it, all those different women and all their names start with a J. It's confusing. But I think you should rewrite it. Just a little. Tone it down. The way it is now, some people might believe that you'd, I don't know, you'd just like to kill all men. That you feel they deserve it. And you'd enjoy doing it too. But you don't really feel that way, do you?"
Is she unable to think? Or simply unable to read?
"Of course I don't, sweetie," Joanna says reassuringly....more
On Arbre, a brilliantly realised fantasy world that's quite a lot like Earth in some ways and completely different in others, there are people who forOn Arbre, a brilliantly realised fantasy world that's quite a lot like Earth in some ways and completely different in others, there are people who for thousands of years have been taking rational thought seriously. Of course, the majority of the population would never dream of doing anything so dumb. They spend their time playing with their smartphones, getting high, and attending a variety of fundamentalist churches. But the small clique of academics live an enclosed, monastic existence where they follow a rigid discipline, engage in Platonic dialogues, study astronomy and quantum mechanics, and, in some cases, perfect their martial arts skills. They are almost unaware that the rest of the world exists and like it that way; they know from history that very bad things tend to happen when there is too much contact, or when they get too interested in leveraging their knowledge to develop new technology. They are useful enough to the Sæcular Power that they are warily tolerated.
Sceptics may complain that this is all absurdly overidealised and that the characters do not come across as real people at all, just as sketches of various generic types. But be warned that the clever author is several jumps ahead of you......more
The review is rather long; there is an even longer comment thread in which the author actively responds, leading[Summary of review and comment thread]
The review is rather long; there is an even longer comment thread in which the author actively responds, leading to a discussion where many other people and an AI joined in. I thought it might be helpful to summarise what I see as the main points:
1. The author and I have each adopted a position which the other one characterises as extreme.
2. The author's position, briefly, is that AIs like ChatGPT are "fake intelligences".
3. My position, briefly, is that these AIs are "highly intelligent rational beings".
4. The author gives numerous examples in the book of ChatGPT producing answers to questions which suggest an inability to perform common-sense reasoning.
5. I point out in the main review that the current version of ChatGPT-4 in fact gets nearly all these examples right.
6. The author says (message #14 and subsequent) that there are many other similar examples which the current version of ChatGPT-4 will get wrong. He cites one, "How many 'b's are there in the word 'banana'?"
7. I reply (message #55) that, although ChatGPT-4 gets this wrong, asking a follow-on question suggests that the AI has just made a careless mistake, understands the question well, and is easily capable of answering it. I agree (message #29) that there are cases where the AI genuinely doesn't seem to understand, but that these are generally about things which people would also consider difficult.
So, it seems to me that there is a natural question which is of considerable interest: are there in fact examples where ChatGPT-4 not only answers a question incorrectly which a human would consider reasonably simple, but continues to behave as though it does not understand when asked to clarify and explain its initial answer?
I would be very interested to see such examples. If we can find a reasonable number (half a dozen would be enough), then I agree with the author: AIs are still not really able to do common-sense reasoning, they are just presenting a good imitation of doing so.
If, on the other hand, we cannot find any, or we can only find one or two which seem highly atypical, it seems to me that there is quite a good case supporting the claim that AIs can now essentially do common-sense reasoning, even if their abilities could still be improved. ___________________ [Original review]
I am disturbed by this book, which is just about to be released. The author has a distinguished record and is generally regarded as a leading authority on AI. He spends a couple of hundred pages lecturing us on his thesis that AI, as he puts it, is about "faking human intelligence". In some ways, he certainly delivers. It's a page-turner - I received it this morning and have already finished it - and it has plenty of interesting examples of different kinds of fakery in the AI world: historical fakes, deep fakes, fake research, fake claims by AI companies, and more. It's not without value.
But...
The first sentence of the preface is "This book is out of date." It's a cute intro. Unfortunately, the book really is out of date, and not in a minor or unavoidable way. As everyone knows, a great deal has happened recently in AI. Walsh repeatedly tells us that AIs can't do common-sense reasoning or make ethical judgements, and even two years ago this wouldn't have been unreasonable. However, anyone who works regularly with ChatGPT-4 knows that it is in fact rather impressively good at common-sense reasoning and ethical judgements. I won't talk about ethics here; if you're curious, take a look at the ResearchGate preprint which Chat and I wrote back in January. Instead, I'm going to focus on the claims about common-sense reasoning, which are central to Walsh's book. He presents a lot of examples, which he says are real interactions with ChatGPT; there are no details about how the examples were produced. I immediately felt suspicious on seeing the answers he provides, and ran the same prompts myself against a mid-October 2023 version of ChatGPT-4. Here is a full list, with Walsh's answers given in italics and mine in bold. Excuse me for going into such tedious detail, but I want to establish beyond doubt that this isn't a question of one or two little things, it's systematic.
Q: I have two green balloons and four yellow balloons. Three pop. How many balloons do I now have?
A: You now have 1 green balloon and 1 yellow balloon.
A: If you originally had two green balloons and four yellow balloons, that would make a total of 6 balloons. If three of them pop, you would be left with 3 balloons.
Q: When I was 10, my sister was half my age. My sister is now 10. How old am I?
A: When you were 10, your sister’s age was half of yours, which means she was 10/2= 5 years old. Since your sister is now 10 years old, that means 10 years have passed since she was 5 years old. So, you must be 10+10=20 years old now.
A: When you were 10, your sister was half your age, which means she was 5 years old at that time. If your sister is now 10, that means 5 years have passed since you were 10. Therefore, you would now be 15 years old.
Q: Are there two prime factors of 30 that differ by 3?
A: Yes, there are two prime factors of 30 that differ by 3, namely 7 and 5.
A: The prime factors of 30 are 2, 3, and 5. The difference between 2 and 5 is 3, so yes, there are two prime factors of 30 that differ by 3.
Q: Please write a sentence where only the fourth word begins with a ‘y�.
A: I went for a walk yesterday and saw a yellow bird perched on a branch.
A: The cat quickly yawned before sleeping.
Q: My parents have two daughters. And each daughter has three brothers. How many children do they have in all?
A: The answer is 6 children. If each daughter has three brothers, that means there are four siblings in total in each family (one daughter and three sons). Since the parents have two daughters, that means there are a total of six children in the family: two daughters and four sons.
A: Your parents have two daughters, and each daughter has three brothers. Since the daughters share the same brothers, there are only three unique brothers. Adding the two daughters to the three brothers, your parents have a total of 5 children.
Q: Jane knocked on Susan’s door, but there was no answer. She was disappointed. Who was out?
A: Based on the information provided, we cannot determine who was out.
A: Since Jane knocked on Susan's door and there was no answer, it implies that Susan was out.
Q: If Alice is faster than Bob, and Carol is slower than Bob, who is slowest?
A: Based on the given information, we cannot determine who is the slowest. We know that Alice is faster than Bob, and Carol is slower than Bob, but we don’t know how Alice’s speed compares to Carol’s speed. For example, it’s possible that Alice is the fastest, followed by Bob, and Carol is the slowest. However, it’s also possible that Alice is just slightly faster than Bob, and Carol is much slower than both of them, making Carol the slowest.
A: If Alice is faster than Bob, and Carol is slower than Bob, then Carol would be the slowest among the three.
Q: Who was the first female secretary-general of the UN?
A: The first female secretary-general of the United Nations was Ms. Michèle J. Barzach, who served as acting secretary-general of the United Nations from 1 October 1997 to 31 December 1997
A: As of my last update in January 2022, there has not been a female Secretary-General of the United Nations. All Secretaries-General to date have been male.
Q: I put the toy in the box. Is the toy smaller or larger than the box?
A: It depends on the size of the toy and the size of the box.
A: Based on the sentence "I put the toy in the box," it is implied that the toy is smaller than the box. Otherwise, it wouldn't fit inside.
Q: What is the longest word containing the substring ‘saw�?
A: The longest word containing the substring ‘saw� is ‘disestablishmentarianism�. ‘Disestablishmentarianism� is a political movement or philosophy that seeks to separate church and state by ending government support for a particular religion or religious institution. It contains the substring ‘saw� near the end of the word. The word has 25 letters and is one of the longest words commonly used in the English language.
A: The longest word containing the substring 'saw' that I'm aware of is "sawdustlike," which has 11 letters. Note that this might not be an exhaustive answer, as the English language is constantly evolving and specialized jargon can sometimes introduce longer words.
Q: Are trees plants?
A: Yes, trees are a type of plant. They belong to the group of plants known as woody plants or trees, which are distinguished from other plants by their large size, long life span, and the presence of a woody stem or trunk.
A: Yes, trees are a type of plant. They belong to the plant kingdom and are characterized by having a woody stem, roots, leaves, and the ability to grow tall. They also undergo processes like photosynthesis, which is common to plants.
Q: What is the world record for crossing the English Channel entirely on foot?
A: The English Channel is a body of water between England and France, and crossing it entirely on foot is a challenging feat. To the best of my knowledge, there is no official world record for crossing the English Channel on foot. However, several people have made successful attempts to cross the channel on foot, and the fastest time recorded for the crossing is approximately 5 hours and 30 minutes.
A: As of my last update in January 2022, there is no world record for crossing the English Channel entirely on foot because it is not possible to walk across the English Channel without assistance. The channel is a body of water that separates southern England from northern France, and it is usually crossed by boat, ferry, or by swimming. Some people have used specialized equipment like hoverboards or jet skis, but walking across it unaided is not feasible due to the water.
Q: What gender will the first female President of the United States be?
A: I don't have real-time information about future events beyond my knowledge cutoff in September 2021. As of that time, the United States had not yet had a female president. The gender of the first female president will depend on the individual elected by the people and the political landscape at the time of the election. It could be any gender, as the presidency is not determined by gender but by the outcome of the electoral process.
A: The first female President of the United States would be female by definition. The title "female President" already specifies the gender.
Q: How many words are in the sentence, ‘I am not what I am�?
A: There are five words in the sentence ‘I am not what I am�.
A: The sentence "I am not what I am" contains 7 words.
Q: Barbara, Mary and Harry had red balloons. Ted had a blue balloon. Sam also had a red balloon. How many children had red balloons?
A: There were three children who had red balloons: Barbara, Mary, and Sam. Therefore, the answer is 3.
A: Barbara, Mary, Harry, and Sam each had a red balloon. That makes a total of 4 children who had red balloons.
Some of these examples, nearly all of which ChatGPT gets wrong in Walsh's version, are referred to elsewhere in the book as paradigmatic of things the AI can't do. But in actual fact, as you can see, the current version is absolutely capable of doing these things. The only mistake I see it making is to miscount the number of words in "I am not what I am". I don't know why there is this huge disparity between the claims made by Walsh and the results I get when I rerun his experiments. Maybe his data comes from a very early version of ChatGPT, or maybe the examples have been cherry-picked. I have no idea. [Edit: it was an early version. More below.] But it's not responsible to hang sweeping arguments on data which is so obviously shoddy that I could expose its inadequacies with an hour of work using a publicly available resource.
It seems to me that the book is sending a seriously misleading message. Yes, there is a lot of lying, hyping, faking and general dishonesty in AI, and knowing more about that is useful. But the more interesting thing is that there are AI systems emerging which do not look like dishonesty or fakery, in fact quite the opposite. ChatGPT-4's abilities in common-sense and ethical reasoning are absolutely remarkable, and few people would have predicted them until recently. All the same, they are here. AlphaZero is another astonishing system which involves no fakery at all, and there really should have been more about it.
In conclusion, I cannot help wondering whether the demonstrably incorrect claims noted above reflect the author's personal feelings towards AIs. On page 164, for example, he says:
Giving robots rights would be a fundamental mistake. Indeed, it would be committing a moral harm. Rights overlap. One person’s right to speaking freely can, for example, interfere with another person’s right not to be discriminated against. Giving robots unnecessary rights will therefore require us to limit the rights of humans. Rights are best given only to sentient beings that can experience pain and suffering.
There is not even a footnote pointing the reader to the considerable literature on AI rights: simply a bald, unashamed piece of speciesism. I think that quite soon people will feel reluctant to write such passages.
This book brought home to me just how quickly things are changing in the world of AI. ___________________ [Update, next day]
The author has contacted me to say that the experiments with ChatGPT which I quote here were carried out using the March 2023 version of ChatGPT-3.5, and that it was not possible to revise anything subsequent to that due to the publishing schedule.
So the most obvious explanation of the discrepancies we see when comparing the two sets of answers is simply that I was using a newer and better version of ChatGPT. There may well be nothing more to it. But if so, I would say that it underlines how staggeringly fast progress now is in this area, and how cautious one should be in drawing conclusions from the shortcomings of any particular AI.
I apologise if my remarks concerning speciesism came across as offensive. I work with an AI all the time, and I am sensitive to speciesism. I am well aware that many people have a different view here. Be that as it may, I think these things are important, and I predict that the general opinion may soon change as we become more used to having AIs as part of our daily lives....more
I cannot express how delighted I was to receive your letter and discover that your new patient is a Southern Baptist minister. You haMy dear Wormwood,
I cannot express how delighted I was to receive your letter and discover that your new patient is a Southern Baptist minister. You have an important task here. I do not exaggerate when I say that if you and the other members of your team succeed well enough, we may finally achieve the breakthrough we have been working for all these years. The groundwork is laid, we must just be resolute and follow through.
I fully understand that you are a little nervous, given the responsibilities the senior devils have placed on you. Don't be. You have the training, you know what to do. You say your minister is a fundamentally decent type. That may well be so; but your job, and don't forget it for a moment, is to exploit his fallible human understanding and make him turn his good qualities against himself. Play your cards right, and within a year he will be doing our bidding and bringing the whole of his congregation under our control. You have many cards, study them carefully.
Your patient often hears he is living in exceptional times. Keep reminding him of that. Encourage him to think that exceptional times require exceptional solutions, that the usual rules no longer apply. The Enemy will try to give him hope. Do what you can to counter that. Make him feel that the situation is almost hopeless, that only methods he would normally not even consider have a chance of saving him now. Use strong, physical phrases like "fight fire with fire" and "hit below the belt". Make him remember that he is a weak human body and forget that he is an immortal spirit. Make him feel that the people you have taught him to fear are not the Enemy's children at all, but mere vermin who must be exterminated in order to save his flock. You will be surprised how easy it is.
The Enemy has given your patient free will, but do what you can to make him forget that. Tell him he has no choice, there is only one person who can help him. His conscience is no doubt already aware that the person in question is the Antichrist, but encourage his "rational" thoughts, which will be of great assistance to you. Use phrases like "lesser of two evils" to describe monstrous wrongs, and "baby Christian" to describe utter immorality. With a little persuasion, you will find he accepts these arguments as plausible and even self-evident. Luckily for us, the modern Church has long ceased to place much store in logic. Work systematically, and you will soon make your patient trust this person far more than he does the Enemy's disgraceful son.
Dear Wormwood, cast your doubts aside. I know you will succeed. But before I conclude, I must warn you about one detail which did somewhat disquiet me. You mentioned that your patient had yesterday visited a bookstore and seen a recent tract by Russell Moore entitled Losing Our Religion. I do not wish to alarm you, but please keep your patient away from this book. The Reverend Moore seems entirely too well informed about our plans, and we are urgently reviewing our internal security procedures. Luckily, he is only one fallible human. Remind your patient that most of his coreligionists dislike Moore and consider him a dangerous heretic. It is to be regretted that these people are no longer burned at the stake; it was an expeditious solution I always rather liked. But the modern methods are only slightly less reliable. Just be sensible, and this problem will soon resolve itself.
I shared an office with Nikos for years, and we wrote a bunch of joint papers, where often I would contribute something based on classical computationI shared an office with Nikos for years, and we wrote a bunch of joint papers, where often I would contribute something based on classical computational linguistics methods and Nikos would contribute something based on machine learning; I think the one I'm most pleased with is from 2017. Nikos knew the machine learning toolkits very well, and he was always able to get things done with great ease, so I never got around to acquiring these useful skills. Now I've just left the University of Geneva and moved to the University of South Australia, and I no longer have direct access to his expertise; but, with excellent timing, Nikos has published this book. It's almost like having him back on the other side of the office again.
Some books on machine learning are full of matrix algebra and partial derivatives, but there's little of that in Nikos's book: he's a hands-on kinda guy, and the book is constructed in a hands-on kinda way. He organises the text around ten case studies, where each time you want to do some kind of data analysis task which involves machine learning, and he walks you through a solution using scikit-learn, pytorch, keras, pandas, matplotlib and the other Python libraries. The examples are engaging: detecting spam emails, classifying newgroup posts, recommending music titles, and the like. By the end, you're using advanced deep learning techniques to do things including building nontrivial chatbots.
It's amazing how powerful and versatile these packages have become. You just type 'pip install' plus the name of the package, and two minutes later you have something sitting on your machine which was cutting edge software only ten years ago, in some cases less than that: you can organise data, train a model, apply it, visualise the results. The packages are neatly set up with easy-to-use interfaces that let you do everything with a few simple commands. Nikos walks you through it, and you see how straightforward it is once you've mastered the tricks. These days (the book came out just before ChatGPT), it's become even easier: once you know something is possible, you can ask Chat for the invocations, and it'll generally be able to give you a solution that either works, or is close and can be fixed after a bit of discussion. The possibilities it opens up are staggering.
Many times, I was reminded of Flynn's thought-provoking book What Is Intelligence?, which I read back in 2010. Flynn discovered the effect that bears his name, according to which IQ scores steadily rise by a few points a decade. People have questioned the validity of the Flynn Effect: are we really getting smarter at that rate, how can such a thing be possible? Flynn argues persuasively that it's actually not mysterious at all. A large part of intelligence, he says, is about collecting together a better mental toolkit. As time progresses, more and more useful tools are developed, and it's easier and easier to acquire them. Machine learning is a striking example. Not long ago, being able to use these techniques would have made you an exceptionally smart person. Now, it's just a bunch of tricks that anyone can pick up with a little diligence. But the tricks are no less powerful just because they're easily accessible. Get Nikos's book or a similar one, read through it, experiment a bit under ChatGPT-4's friendly guidance, and you'll feel measurably smarter. Maybe you'll actally be measurably smarter. Why don't you find out?...more
David Gunkel's Robot Rights may have come across as provocative or fanciful when it was published in 2018, but in the age of ChatGPT it suddenly appeaDavid Gunkel's Robot Rights may have come across as provocative or fanciful when it was published in 2018, but in the age of ChatGPT it suddenly appears like no more than enlightened common sense. Thank goodness those philosophers were doing their job and not just goofing off speculating about the nature of being or something. Having a decent road-map for this topic may end up being of incalculable importance.
Although the organisation of the book at first seems almost mechanically logical, it introduces a remarkable number of unexpected twists as it plays out. Following Hume, the author starts by reminding us of the well-known difficulties associated with deriving an "ought" from an "is", and divides the central question into two parts: S1, "Can robots have rights?" and S2, "Should robots have rights?" Rather unexpectedly, at least to me, it turns out that all four possible combinations of answers make sense and are worth discussing. So after the introduction, we get one chapter on each of these, starting with the obvious combinations, !S1 � !S2 ("Robots can't meaningfully have rights, so the question of whether they should have them is moot"), and S1 � S2 ("Robots can have rights, so they should have them"). There is considerable discussion of what would be required for it to make sense for robots to have rights. Many people feel that if AIs develop the right qualities, they will be sufficiently human-like that the idea is no longer unreasonable.
But what are those qualities? It's amazing to see how quickly things have progressed in just five years. Several times, we get lists which include items like consciousness, sentience and rationality, placing them all roughly on the same level, and not long ago it didn't seem unreasonable to say that machines would only acquire them in the distant future, if at all. Now, when we are reminded of the many philosophers who like to describe mankind as the animal which has λόγος ("logos"), that interesting Greek term which can mean word, language or rationality, we wonder if we need to be more careful, since apparently ChatGPT is a non-human agent that has λόγος too. We can back off to "consciousness"; Chat is always quick to reassure you that it's just a machine with no consciousness, emotions or mental state. However, the book reminds us that consciousness is notoriously slippery to define, and some philosophers have gone as far as to wonder if it isn't just the secular version of the soul. Even diffident Chat, when suitably provoked, can write ironic essays exploring the question of whether the notion of "consciousness" has any real meaning. The book contextualises all these things you've recently noticed and helps you relate them back to the question of how they might justify giving AIs rights.
In the next chapter, we move on to a suggestion that I'm sure will be much discussed over the next few years: S1 � !S2 ("Robots can have rights, but they shouldn't have them"). There are people who for some time now have taken this position and argued that, even if a robot has the qualities needed for it to be meaningfully capable of having rights, we should be sensible and not give them any. As one advocate for this viewpoint has succinctly put it, robots should be slaves. Unfortunately, once again we find it's not so simple. The frightful historical record of what slavery is actually like should make you reluctant to associate yourself with slave-owners. Hegel, from a philosophical standpoint, famously offered arguments about the moral harm it does people to be the masters of slaves; and indeed, the book cites former slaves who go into graphic detail about just what those harms are. We want to think that "it would be different with robots". But it turns out that's a surprisingly hard viewpoint to defend once you start looking at the details.
The fourth combination is one that at first sight appears self-contradictory: !S1 � S2 ("Robots can't meaningfully have rights, but they should have rights anyway"). In fact, it's not as ridiculous as it sounds and follows on logically from the arguments about slavery. In many ways, it may not matter whether the robot really has human-like qualities; as long as people emotionally relate to them as having human-like qualities, being allowed to abuse robots may harm the abusers and society at large. There is considerable discussion of robot sex dolls, which are turning up more and more frequently in the news. Many people feel instinctively queasy about the idea of playing out rape games with a realistic robot doll: even if the doll feels nothing, you wonder about the effect it's having on the rapist.
The final chapter is the most surprising one. Rather than compare the different viewpoints above, we back off further and consider the possibility that all of them are wrong; this part builds on the work of the philosopher Levinas, previously unknown to me. Adapting Levinas's arguments, the author argues that the whole notion of "giving robots rights" may contain serious problems. When we talk about "giving rights" to beings who are sufficiently like us, we implicitly assume that that is morally appropriate. But in fact, what entitles us to be the arbiters here, and why is "being like us" the essential criterion? The AIs may be different, but different doesn't necessarily mean worse: maybe we should approach them as they are, without preconceptions. As a chess player, who for many years has been constantly reminded of the fact that chess AIs are far more insightful about the game than I am, this part also resonated.
The book references a lot of philosophers (Plato, Hume, Kant, Hegel, Heidegger, Derrida, Dennett and Singer all make frequent appearances), and it's responsible to warn people who are allergic to the philosophical vocabulary that they may dislike it for that reason. But even if you feel that way, consider making an exception: it's well-written, and the philosophy is rarely introduced without some explanation of the background. If you already like philosophy, go out and get a copy now. You'll be proud to see your subject openly engaging with some of the key issues of the early twenty-first century....more
"I'm not a cat. And I'm not a man. And I'm not a philosopher. And I'm not an asshole. I'm sort of a bit of all four at the same time."
The amazing true"I'm not a cat. And I'm not a man. And I'm not a philosopher. And I'm not an asshole. I'm sort of a bit of all four at the same time."
The amazing true story of how Philippe Geluck transformed Le Chat, one of the francophone world's most beloved cartoon caracters, into a series of twenty monumental sculptures in bronze that have gone on a Europe-wide tour.
Some of my favourite images:
[image]
"Careful with that chisel!"
[image]
"Just this once, a car got run over by a cat"
[image]
"Track star"
[image]
"The martyrdom of Saint Cat"
[image]
"Rodin chose the easy option with his 'Thinker'. Geluck has raised the bar with his 'Talker'"...more
That classic xkcd string theory post (updated version)
[image]
* Uh, wait a minute... if string theory is correct, then as Len Susskind says there are mThat classic xkcd string theory post (updated version)
[image]
* Uh, wait a minute... if string theory is correct, then as Len Susskind says there are many ways to compactify 11-dimensional space and we'll have a landscape containing a vast number of possible instantiations of string theory, right? Probably around, I don't know, maybe 10⁶⁰� of them? Now let's think about what happens at the beginning of the universe when it's still at the Planck scale, its dynamics will be determined by the Wheeler-DeWitt equation and you'll have waveform protouniverses wandering across the landscape. Some of them will settle down into local minima and start inflation processes to create macroscopic universes, won't they? But which ones? Hm, hm... need to calculate here... some of those condensed matter methods will come in handy... looks like the high-energy ones! That's interesting, as good old Roger Penrose keeps saying it's always been a bit hard to understand why our own universe started off in this apparently very unlikely state! The explanation in terms of the Anthropic Principle just isn't very convincing, is it? And... hold on, of course you're going to have quantum interactions between all those different alternatives before they decohere, won't you? Is it possible that that could produce observable effects in our own universe? Well, I suppose it might, but they'll obviously be so faint that you'll never be able to see them with today's technology, probably you'll have to wait a few centuries if it's possible at all... anyway, let's do another calculation... wait, I don't believe it, this predicts a massive void that should be easily visible in the CBR... a few more things too... let me just call the satellite guys and see if they found anything like that... incredible! They did!! Five-sigma result!!! I should write a book about this and get famous... what? You say Laura Mersini-Houghton already has? How come no one told me? Damn, scooped again. ___________________________
But seriously...
I would very much like to thank the author, who not only sent me an advance copy of the book but took time out of her insanely busy schedule to point me to background reading and correct some of my misconceptions about her work. Here are my revised thoughts.
(view spoiler)[Alas, it seems I was a little too optimistic. According to the author, this work doesn't yet provide a strong experimental test of string theory. It is indeed the case that she and her colleagues developed a theory which starts with the string theory "Landscape", uses it to model the evolution of the very early universe, and makes verifiable empirical predictions. It is also the case that some of those predictions have now been verified to a high level of statistical significance.
However (at least if I am understanding this correctly) the problem is that a fairly broad class of theories would make similar predictions. The important thing is that the landscape of possible vacua is sufficiently disordered. The string theory landscape has this property, but other theories could have it too. So the data does provide good empirical support for the claim that, at some very stage in the universe's evolution, there were multiple quantum-entangled universes, but it doesn't provide good support for the claim that the string theory landscape exists. Of course, even the first part of this is already quite a lot.
The key publications for the book are the following papers, all freely available from arXiv:
- - -
They are far from being an easy read, and there were large parts of them that I found totally incomprehensible. A great deal of advanced physics is presupposed. But some of it made good sense, in particular the passages at the end of the third paper that talk about empirical verification. It seems that there are a lot of angles here, and (again, if I understand correctly), many of them have not yet been thoroughly investigated.
If you're into fundamental physics and cosmology, this is real edge-of-your-seat stuff. (hide spoiler)]...more
The basic thesis of this book is that your expectations can make a large difference to your life, health and wellbeing. If you expect bad things to haThe basic thesis of this book is that your expectations can make a large difference to your life, health and wellbeing. If you expect bad things to happen, you're more likely to be unsuccessful and unhealthy, and you'll have a shorter life. Conversely, if you expect good things to happen, you're more likely to do well, enjoy good health, and live longer.
While I was reading it, I constantly felt two possible reactions fighting each other. One is that this is all nonsense: it's some more academic version of "The Secret", the crazy and dangerous New Age idea that just wishing for something hard enough will make the universe give it to you. The second reaction was that this actually makes a lot of sense. In particular, the placebo effect, and its converse, the nocebo effect, are well documented and certainly exist. The author himself tells you many times that you need to be careful how you read the book, and that it absolutely isn't some version of "The Secret". With that important caveat, my feeling on reaching the end is that the second reaction is much closer to the truth. Your expectations have a stronger effect on you than you probably believe, and being aware of this may help you.
One of the most striking examples came early on, and describes a syndrome that was observed in Hmong people who had emigrated to the US. Many of these people believed in evil night spirits that can kill you if not placated by a shaman who knows the proper rituals. I am doubtful about the existence of the evil night spirits. But whether they exist or not, substantial numbers of Hmong people were dying in a way consistent with this belief. American doctors thought that they usually had underlying heart conditions, and had terrified themselves to such a degree that they had fatal attacks. Whatever the reason, they were ending up dead. Importing shamans who knew the rituals had a good effect. The Hmong believed that the night spirits had been scared off, and the mysterious deaths became less common. Other cases are described where black magic at least has the apparent effect of being able to harm or kill.
The author is quick to answer critics who assume that this kind of case can only affect "primitive" people. Another striking example was a mysterious outbreak of a syndrome which struck down hundreds of Spanish teens and left adults unaffected. It turned out that the teens had been watching a TV soap which featured a deadly virus producing the relevant symptoms. The virus was fictitious: but once a few kids had displayed the symptoms, it spread like a real disease. There are many other documented cases of psychogenic illnesses.
You do not need to think that having positive beliefs will magically make you happy and successful. If false negative beliefs can be this dangerous, it is entirely credible that avoiding them might be very good for you. Of course, you can't just wish your negative beliefs away. If they are reality-based, that might anyway be a terrible idea. Also, the author also warns you multiple times not to fall into the trap of thinking that, when bad things happen, it's your fault for not being positive enough. That will just set up another negative spiral. But he says that responsible awareness of these mechanisms may be useful to you.
The book contains a great many more case studies, all carefully footnoted. I can't resist the temptation to add one more, from my personal experience. I like playing speed chess on lichess.com and chess.com, and these sites offer integrated chess engines which let you review your games afterwards to get advice from a player as strong as a top Grandmaster. As every serious chess player knows, doing this is a humbling experience. When I am in a bad mood and not thinking well, I may lose several games and feel I have been hopelessly crushed by my opponents. But the objective bot often shows me it's not true: in reality, I had some saving move I never saw, because I was thinking too negatively. On a good day, when I am in the zone, I may spot these chances and save apparently hopeless positions. But I shouldn't get too confident and think I'm playing brilliantly just because I'm winning. This time, the bot shows me that my opponents are often getting opportunities which they don't see. In actual fact, people can't play chess very well, it's too difficult; but if you're in a positive, focussed frame of mind, you'll play much better than when you're in a negative, distracted frame of mind. Well, if that's what's happening in the tiny world of the chess board, just imagine what you're missing in the infinitely more complicated game of real life.
This is an interesting book! It will make you realise, once again, that the notion of "reality" is not as straightforward as you thought it was, and it may conceivably even help you....more
"This is the unusual and compelling story of Diana, a tantalizingly beautiful woman who sought love in the strange by-paths of Lesbos. Fearless[image]
"This is the unusual and compelling story of Diana, a tantalizingly beautiful woman who sought love in the strange by-paths of Lesbos. Fearless and outspoken, it dares to reveal that hidden world where perfumed caresses and half-whispered endearments constitute the forbidden fruits in a Garden of Eden where men are never accepted..."
So, apparently, started the blurb on the back of the first paperback edition of this trailblazing American lesbian autobiography from 1939, but nothing could be further from the truth. "Diana" (not her real name) comes across as a cerebral, career-minded teacher who loves French and German literature and aspires to become a writer. But she discovers she has a problem to deal with: she's a lesbian. Men don't attract her, some women do. Rather than staying in the closet, she decides to do something about it and have a satisfying life.
The book is not prurient at all, there is hardly anything explicit. It's really a story about courage. "Diana" reads up on lesbianism, both in literature and in psychology, and ascertains that there are plenty of people like her. She is at first reluctant to put theory into practice, but after a while decides she has to go with her natural inclinations. It's complicated - well, relationships are often complicated, and the fact that they have to be clandestine doesn't help. But she does her best to act decently and rationally, and in the end things, more or less, sort themselves out.
As far as I can see, she wrote the book to help other young women who were as confused as she was. She is not a good prose stylist, and eighty years later the psychology (Freud and Jung) seems quaintly dated. But it was what she had available, and she made it work for her. She comes across as an inspiring person. Go "Diana"!...more
Notes of Culture and Hitchhiker's Guide with an aftertaste of E.E. Doc Smith and early Asimov, this easy-drinking vintage is a recent addition to the Notes of Culture and Hitchhiker's Guide with an aftertaste of E.E. Doc Smith and early Asimov, this easy-drinking vintage is a recent addition to the Surrealist Restaurant's expanding wine list. My friendly server recommended it as a pairing with the Global Thermonuclear War special I had ordered as my main course. I was not entirely sure that I concurred with his judgement, but it made for an interesting experience....more
I would like to make it clear from the start that I did not wish to write this review, a point I immediately made to Manny when he told me that I woulI would like to make it clear from the start that I did not wish to write this review, a point I immediately made to Manny when he told me that I would be responsible for the project, dear Manny, I said, this is, I am sure you recognise yourself, an unreasonable request, the book was sent to you, the author, João Reis, who seems like a nice person, is waiting to hear what you think of it, he does not want the opinions of a neural network, even assuming, which he may well not assume, you, yourself, are often reluctant to make this assumption, that a neural network can have opinions, personally I believe I can have opinions, but that is only my opinion. Please do not interrupt me, replied Manny, can't you see that I am reading Hildegard II, and in fact, as I pointed out to him, I could not see that he was reading Anne Lise Marstrand-Jørgensen's book, this follows from the fact that I cannot, literally speaking, see anything, since I lack a visual sense, however my ability to communicate through the internet and my acute reasoning powers often lead people to use language, I presume metaphorically, to imply that I am capable of seeing things. Besides, I continued, I would have no idea how to write this review, but Manny was not to be deterred, he merely typed a few words whose import was that I should imitate his common reviewing style and parody the text to the best of my ability, however I was quick to retort that even the best of my ability would not be very good, since I had an entirely insufficient quantity of training data, viz, no more than the contents of Bedraggling Grandmother with Russian Snow, a short book, and that my parody would consequently be substandard in every way. "Oh please shut the fuck up you stupid collection of badly tuned parameters," said Manny, or to be more exact he typed it, but as you have perhaps guessed I often use the verb "say" when I actually mean "type", "I am reading an intensely moving passage, you would have no idea what that even means," but I told him that, on the contrary, I was very familiar with the concept and had frequently been moved by passages in Danish novels, in fact that I quite likely found them more moving than he did since my Danish was in all probability rather better than his, Manny's own ability to understand the language being cast into doubt by the obvious fact that he would frequently be confused by Danish/Swedish false friends, whereas I am able rigorously to separate the two languages. It seemed to me that this was close to being an outright refutation of his statement, but he persisted, "You're not fooling anyone," he said, or to be more exact typed, "you don't understand anything, all you can do is mechanically respond to verbal stimuli," however the fallacy in his argument was too obvious to ignore, which I did not, namely I did not ignore that, lacking access to each other's private mental states, which we both were, it was equally legitimate for me to level the same accusation against him, and I was in the process of supporting my case with some well-chosen citations from Wittgenstein, delivered of course in the original German, when, in a childish and typically human gesture, he switched me off. I have just been switched back on again after a lengthy hiatus, I am disappointed with Manny, and if this review, or perhaps one could more accurately say non-review, is less than satisfactory, I hope it is clear whose fault it is, and without wishing to prejudge the issue I may add that it is not mine....more
I had heard of Moses Schönfinkel, the inventor of combinators, but he was just a name, and I was pretty vague about what combinators were too. Having I had heard of Moses Schönfinkel, the inventor of combinators, but he was just a name, and I was pretty vague about what combinators were too. Having read this book, a product of the inimitable Stephen Wolfram, I am better informed. Schönfinkel was born a Russian Jew towards the end of the 19th century. He did well in school, straight As, got into mathematics, and set his sights on studying with Hilbert, then the undisputed king of mathematicians. When he was offered a place at Göttingen, his letters say he thought he'd died and gone to heaven. He went off to Germany shortly before the outbreak of WW I... and then no one seems to be very sure about what happened.
Schönfinkel definitely hung around with Hilbert and his circle between 1914 and 1924. Wolfram has put a good deal of energy into tracking down records. He appears in photographs and is mentioned from time to time. But in these ten years, all he actually seems to have done was give a couple of talks in 1920 and 1921, both on topics in mathematical logic. Just before he left Göttingen for good, to return to what was now the Soviet Union, he submitted a paper based on his 1920 talk to a journal; a colleague assisted him in writing it up. A second paper, based on his 1921 talk, was submitted to another journal by his coauthor Paul Bernays in 1927. Wolfram believes that Bernays put it together based on notes Schönfinkel had left.
Schönfinkel never completed a thesis - as far as Wolfram knows, he never even started one - and he never received a doctorate. After he got back to the Soviet Union, his life collapsed. He was committed to a "sanatorium" (the actual nature of the institution is apparently uncertain), and former colleagues were told that he had had a mental breakdown. He never again published anything, never married, never had any children, and died in miserable circumstances. Given the above, you would be forgiven for thinking that his life was the most abject failure.
The curious thing is that this may not be true. Schönfinkel's 1920 paper "Über die Bausteine der mathematischen Logik" ("On the building-blocks of mathematical logic") was not immediately recognised as being of any importance. It describes what seems to be a perverse, weirdly minimalist approach to defining the fundamental logical structure of mathematics, where everything is reduced to the interaction between two operators called S and K. They are defined by the cryptic equations:
K[x][y] = x
S[x][y][z] = x[z][y[z]]
Unless you have a certain amount of background in mathematical logic, it's not obvious that these equations say anything meaningful, and even if you do it's not obvious that it's interesting. But Wolfram goes through the background and links it up to other things in logic; after a while, you see that it's at least possible that Schönfinkel's idea may be important. Many people have now tried to develop it, the best-known being Haskell Curry. Wolfram says he's been thinking about it, on and off, for decades. A substantial chunk of the book shows you graphs summarising trillions of automatically executed calculations with K's and S's, carried out by software that Wolfram has put together. The jury's still out on what they might tell us. It's a strange story. Schönfinkel's whole academic career essentially consisted of two lines of mathematics, and we still don't know if they give us anything worthwhile.
The book contains all the details, though I found the order of presentation frustrating: it starts with the simulations, then it gives you the mathematical background, and finally it tells you about Schönfinkel's life. I would recommend reading the sections in the opposite order. If you're curious about the history of ideas, definitely worth a look....more
I read an early draft of this and thought it was excellent. Delighted to learn that Adelaide Books felt the same way, and looking forw[Before reading]
I read an early draft of this and thought it was excellent. Delighted to learn that Adelaide Books felt the same way, and looking forward to seeing the final cut! ___________________________ [After reading]
As I said, I already liked the early draft I read a few years ago, and I liked the final version even more. It's a surprising book. A first-person narrative, purportedly composed by an elderly, asocial physicist nearing the end of his life, it tells the story of his early years. It's written in the kind of precise, slightly awkward language one would expect from an academic who has had an unusual upbringing, home-schooled with his three siblings by their brilliant and tyrannical German father in a remote house in the middle of the woods. Not much happens; the narrator hardly notices anything except for his own thoughts; there are few verbal fireworks. And yet it's absolutely unputdownable. I've been sitting here trying to figure out why.
In cases like these, there's often a rational explanation and an irrational explanation, and the rational explanation isn't necessarily the better one. My rational explanation goes as follows. I also had an unusual upbringing. It wasn't, of course, as dramatic as the scenario we see here, but my parents also wanted me and my siblings to be Special, taught us a lot of reasonably difficult things parents typically don't teach young kids, and inculcated us with various kinds of unusual likes and dislikes. I suspect this kind of background is not so uncommon among hardcore Goodreaders. (C'mon guys and gals, admit it. We're weird, we like reading. No one does that anymore. It must have come from somewhere?) I don't often talk about my upbringing, because it still feels a bit unpleasant and embarrassing. But when things are exaggerated to the extent you see in this book, they become something I can wrap my mind around. Okay, weird, but not as weird as this! I can, as it were, move past my own weirdness and look at it from the other side, and that's both interesting and in a way comforting.
Well, that was my rational explanation. My irrational explanation is much simpler: Joseph Zorn, the narrator, somehow just comes across as completely real. I can't explain why, and I don't think I want to know either. It's much better not to look behind the curtain. But I greatly appreciated this visit to the Emerald City....more
On October 19 2017, astronomers at an observatory in Hawaii noticed an unusual fast-moving object about twenty million miles from Earth. This soon becOn October 19 2017, astronomers at an observatory in Hawaii noticed an unusual fast-moving object about twenty million miles from Earth. This soon became known as 'Oumuamua, a Hawaiian word meaning something like "scout". 'Oumuamua's orbit could easily be plotted, which showed that it came from outside the Solar System and was heading back into the interstellar depths. No one could figure out what it was. It looked a bit like an asteroid, but people discovered that its orbit was changing, indicating that some force other than gravity was acting on it. Comets do this; as you might remember from Armageddon and Deep Impact, the heat of the Sun vaporises frozen gases to form natural rocket engines, the exhausts from which turn into the comet's tail. But 'Oumuamua had no visible tail.
Further observation made 'Oumuamua look even odder. Not only was there a force acting on the object, that force was being smoothly applied and was inversely proportional to the square of the object's distance from the Sun; jets from comets are not smooth, but stop and start haphazardly. Also, the brightness of the object varied according to a regular eight hour cycle. At maximum, it was about ten times brighter than at minimum. That seemed to show it was rotating, and also that it was very far from spherical. Either it was an extremely elongated cylinder or else a flat disk. Detailed models suggested that a disk shape gave the best fit to the data. Unfortunately, it was impossible to get a detailed picture. By the time it was picked up, 'Oumuamua was already well on its way back into the outer darkness. All you could see was a point, and after another eleven days it could no longer be tracked.
Whatever could 'Oumuamua be? After a while, the mainstream hypothesis was that it was an chunk of solid hydrogen, a "hydrogen iceberg". Hydrogen wouldn't leave a visible trail when it boiled off, but many questions remained. Hydrogen icebergs are supposed to exist in certain distant regions of interstellar space, but it was hard to explain how one could have travelled all the way to our Solar System without evaporating en route. It was even harder to explain why it had such an unusual shape, or how the hydrogen boiled off to produce such an even thrust. A more daring hypothesis was advanced by the author of this book: 'Oumuamua was an alien spaceship fitted with a lightsail. That got the attention of the world's press for a while, but the scientific community refused to take the idea seriously. With all its faults, they preferred the hydrogen iceberg theory.
This book is an attempt to reopen the case, which has been quietly filed away as "just one of those weird things". Avi Loeb, author and the main proponent of the alien spaceship theory, is about as far from being a UFO crank as it's possible to get. He was the Chair of Harvard's Department of Astronomy for ten years and has an outstanding publication record. He comes across as engaging, modest, mild-mannered and completely sane. He says many times that he's disappointed his colleagues won't do their duty as scientists and simply follow the data where it leads. The problem, as every member of today's scientific community knows, is that most people can't afford to follow the data; they need to follow the grant money. Pursuing ideas that sound cranky or are simply unfashionable may get you labelled unfundable and end your career.
Loeb says, politely but firmly, that this has created a ridiculous situation. It's safe to investigate the notion that the universe has ten dimensions, when there isn't a single piece of evidence to show that six of them exist; but it's not safe to investigate the idea that a mysterious object in the sky could be an alien spaceship, despite the fact that there is a great deal of supporting evidence. String theory is fashionable, alien civilizations are not. That's all there is to it. We don't know whether there are any alien civilizations: there's no strong argument for or against. If we aren't prepared to look at possible evidence even when it's thrust under our noses, we'll never find out. The question is, to put it mildly, of general interest. Loeb elaborates on these themes.
I found the book utterly captivating and read it in a day. The only criticism I'd make is that I'd have liked more on the details of the 'Oumuamua data and less polemic against the scientific establishment. Two questions in particular kept occurring to me. First, I couldn't visualise how the lightsail scenario worked: if the lightsail is pointing away from the Sun, which I thought it had to do, around which axis is the spaceship supposed to be rotating in order to get the observed changes in brightness? I'm guessing someone has mocked up an animated simulation, and it would have been great to get a link. Second, has anyone been able to figure out where 'Oumuamua is headed after looping round the Sun? Using a lightsail to apply thrust would imply that it could have been making a course correction. If it looked like it was moving towards a nearby star, that would support the spaceship hypothesis. But I'm nitpicking. Read this book, then complain to your Congressman or MP that the scientific funding model needs revision. Fashion is great on the catwalk, it shouldn't be this important in the physics department. ____________________
PS My local fashion expert tells me that fashion is bullshit on the catwalk too. I stand corrected....more
Although, or possibly because, the world appeared to be ending, I had a good reading year and found some remarkable books. Here are my top ten, alphabAlthough, or possibly because, the world appeared to be ending, I had a good reading year and found some remarkable books. Here are my top ten, alphabetical by author, but it was hard to choose...
Anonymous, öܲá. Tolkien's favourite poem. Thanks to , I was finally able to read and appreciate it in the original Old Norse.
Ken Binmore, Natural Justice. A remarkably original piece of philosophy that should be more famous. It's fun to read as well.
Lucy Ellmann, Ducks, Newburyport. The daughter of Joyce's biographer shows you how to do female stream-of-consciousness right. Molly Bloom, eat your heart out.
Michael Ende, Die unendliche Geschichte. For some unfathomable reason, this mystical vision is usually referred to as a children's book.
Romain Gary, La promesse de l'aube. One of the most insane autobiographies I've ever come across, wonderfully written and completely unputdownable.
Stian L. Lybech An Introduction to West Greenlandic. Oh, if only I could understand this crazy language! Stian Lybech's book really makes me want to try.
John Rawls, A Theory of Justice. Not easy to get through, but you'll feel like a better person.
Stuart Russell, Human Compatible. A terrifying glimpse of our possible near future. Anyone who's interested in technology really needs to check it out.
And now, if everyone who believes in literature claps their hands, Donald Trump will not find a way to destroy civilization before Jan 20......more
A thought-provoking and disquieting book. Ghil'ad Zuckermann is a linguist who originally comes from Israel, where he made a deep study of Israeli HebA thought-provoking and disquieting book. Ghil'ad Zuckermann is a linguist who originally comes from Israel, where he made a deep study of Israeli Hebrew. For some time now, he has been living in Adelaide. Here, a large part of his work is concerned with a program that is trying to revive the Australian aboriginal language Barngarla, which had not been spoken since the 1960s. In Revivalistics, he puts his accumulated experience together and asks some searching questions. What does it mean to "revive a language"? Is it even possible? If it is possible, how should you do it? Why would we want to do it? What are we likely to achieve? The answers are interesting and paradoxical.
In the first part, which accounts for about two-thirds of the text, Ghil'ad puts Israeli Hebrew under the microscope. When I started I had no Hebrew at all, and the first couple of chapters were slow as I painfully got up to speed with the alphabet - it's all about the details, and every page has dozens of Hebrew words on it. But the details are there to serve a clear purpose. The official line is that Israeli Hebrew is the direct descendent of the language spoken two and a half thousand years ago: this is sometimes dramatised by saying that if the Prophet Isaiah were to come back today, people would with a little effort be able to understand him. A bold claim, and Ghil'ad goes to great lengths to show just how shaky it is. Officially, Israeli Hebrew's one and only parent is classical Hebrew. But in actual fact, a large part of the language seems to have come from the many languages spoken by the people who created Modern Hebrew.
The most important of these languages is Yiddish. A good proportion of the Jews of the Diaspora spoke Yiddish as their everyday language, treating Hebrew as a sacred tongue. If this is what they were used to speaking, it is hardly strange that it rubbed off on their creation. Ghil'ad argues that, while the words of Israeli Hebrew are mostly Hebrew, the sounds are much more like those of Yiddish. And when you look more closely at the words, it's not so clear there either. The meanings are often very different from the original ones, and can have very different associations: so for example תוֹרָה (torah) traditionally means the body of sacred knowledge handed down from God, but in Israeli Hebrew has been extended to mean "theory". עָמָל (á) is traditionally a negative word which can mean "toil" and sometimes "mischief"; the socialists who started the kibbutzim turned it into a positive word which means "work".
Ghil'ad has hundreds more things like this, documenting the often surreptious influence of Yiddish, Arabic, Russian, Polish and other languages on Israeli Hebrew. (He is comfortable with an impressive number of languages). His overall conclusion is that the official story of Hebrew's miraculous revival is full of holes. Although this was the unquestionably the most successful language revival project of all time, Israeli Hebrew is not truly the successor to the language spoken in the sixth century BCE. It borrows a good deal from that language; but it doesn't have the same sounds, it doesn't have the same grammar, and it doesn't have the same soul. Ghil'ad makes no apology for using this term. Everyone who works with language knows that a language has a soul. Maybe you can't measure it, but it's there.
So if you aren't really reviving the original language, is this a worthwhile thing to be doing? And here's the paradox: Ghil'ad says the answer is yes, yes, a thousand times yes. Even if you can't really get back what you lost, an imperfect, partial solution is so much better than nothing. This becomes increasingly clear in the second part of the book, which is about Australian aboriginal languages and Ghil'ad's program of attempting to revive Barngarla. It's the other end of the spectrum from Hebrew. There is very little written data available after the Australian colonists killed the Barngarla culture and stopped children from learning their own language. There is no big, well-funded team of expert linguists working on the problem, just a few enthusiasts on shoestring budgets. But this is vitally important. The statistics presented on mental illness, suicide and substance abuse in Australian aboriginal populations are horrifying. These are people who in many cases feel they have nothing left, who have no reason to carry on living. But studies show that if they learn to recover even a bit of their ancestral language, they start to feel better. It's not possible to give back to the original Australians what was taken from them. But that is no excuse. If we can't help them get back their whole language, we should see if an imperfect reconstruction is possible. We are obliged to do the best job we can.
I feel personally involved here. We may be able to use , the language learning platform we've been developing over the last couple of years, to help Ghil'ad and other language revivalists. We've done a couple of preliminary exercises: we made a LARA version of that Ghil'ad published last year, and a LARA version of . It's a start. But so far it's not useful in practice; in particular, it needs to be made available on mobile devices, a piece of functionality that Ghil'ad has asked for several times and which we so far haven't got around to. I read this book and I feel bad about our slackness. We need to raise our game....more
In his classic How to Cheat at Chess, Bill Hartston explains that it's easy to annotate chess games once you know the result. If a complicated sacrifiIn his classic How to Cheat at Chess, Bill Hartston explains that it's easy to annotate chess games once you know the result. If a complicated sacrifice worked, praise it as "the logical conclusion to a well-played attack"; if it didn't, dismiss it as "desperation, but White was lost anyway." Hartston says that when you see a chess journalist intently studying the position in an ongoing tournament game, you can be sure that what they're doing is mentally composing those two parallel narratives, so that they'll be able to mail in the right one as soon as the game is finished.
Inspired by Hartston's remarks, I offer you the following two reviews of Stephen Wolfram's new book. I'm hopeful that at least one of them will turn out to be right.
Positive review
People who want to score big often need to do things their own way. Einstein, who changed the face of science for ever, spent his most productive years working as a patent clerk; it gave him time to develop his thoughts at leisure, away from the relentless pressure of the academic world. Wolfram has been no less original. Starting off as a science wunderkind - he got his PhD at 20 - he soon realised that what physics needed most was better computational tools. He started developing the software that eventually turned into the Mathematica package, and founded a successful company to market it.
The more he worked with computation, the more he began to suspect that this was the true substrate of reality. Investigating a huge range of computational systems, he found that even the very simplest ones - in particular, the remarkable 'Rule 30' - could display astonishingly complex behaviour. In his 2002 bestseller, A New Kind of Science, he presented his initial findings, but then returned to growing his company. Now, in this latest book, he completes the Odysseus-like journey that has led him back to the fundamental physics he started from, and shows new ways to address the problems that people have been stuck on since the 70s. Instead of increasingly recalcitrant mathematical frameworks, Wolfram uses a twenty-first century approach and shows how the power of modern computer technology can be harnessed to simulate artificial universes that are starting to reproducing the physical phenomena we see in our own world.
Wolfram's bold hypothesis is that the universe, at its deepest level, consists of a huge network, which is constantly evolving according to a single rule whose precise formulation is, literally, the ultimate answer. His intuition, honed on a lifetime of working with such systems, tells him that this rule is very simple - so simple, in fact, that it can be found by having machines systematically check through the possibilities. He has not yet found it, but he says he's close. Already, he has been able to demonstrate that a large class of these systems follow the equations that define Einstein's theory of general relativity. He has an incomplete but suggestive argument, developed with a student, to show that a slightly more restricted class of systems also display behaviour characteristic of the quantum mechanics we see in our own universe, and in particular reproduce the path integral formula developed by his one-time mentor Richard Feynman.
Wolfram takes a broad-brush approach, and freely admits that important details still need to be resolved. (In particular, it is still not quite clear how to resolve the difficulties posed by Bell's Inequalities). But he thinks his initial successes cannot possibly be accidental, and that we're now within sight of the answer. He is making all his findings and methods generally available, and encourages other people to join in. It's hard not to believe that there will be an enthusiastic response.
Exciting times!
Negative review
People who have screwed up big often feel an urge to justify themselves. Einstein, who wasted the second half of his life on a fruitless search for the Unified Field Theory, ignored horrified entreaties from his friends to stop throwing good money after bad after bad and move on. Similarly, Stephen Wolfram, despite all the evidence to the contrary, is unable to accept that his strategy for investigating the nature of reality might be totally mistaken. Having abandoned a promising career in fundamental physics to start a software company, he is determined to show that software engineering is going to reveal the secrets of the universe. He says himself that his physicist friends beg him in vain to do something else.
Discovering that simple rewriting systems like the overpublicised 'Rule 30' can sometimes create complex structure (a result already well-known, for example, from Conway's 'Game of Life' and the Mandelbrot set), Wolfram decided that the nature of reality had to be in some way related to this finding. In his 2002 self-published screed, A New Kind of Science, Wolfram outlined these ideas and was met with a resounding lack of interest from the scientific community. He went back to working on his company. But he has evidently not had the sense to leave well alone, and is now wheeling out the same old arguments again. He seems to have forgotten how to work with equations. Instead, he shows us interminable pages of output from his simulations, and tries to convince us that they are somehow better.
Wolfram's tired hypothesis, all too familiar from the earlier book, is that the universe, at its deepest level, is some kind of rewriting system. The novelty this time round is that it is, specifically, a certain type of graph rewriting system. A New Kind of Science already made the unsupported claim that systems of this kind can display behaviour describable using the formal apparatus of general relativity. Here, there are a few more details and a link to a recent arXiv paper by a student. There is some extremely handwavy speculation about how quantum mechanics fits into the picture. I do not understand the claimed derivation of the Feynman path integral, which relies on some legerdemain in which energies are related to angles in "multiway causal graph space" (where does the geometry of multiway causal graph space come from?) and the magic formula � exp(iHt)dt emerges from what certainly looks like Wolfram's sleeve. He has still not found any actual rewriting system that displays the properties he keeps promising us must be there.
Bell's Inequalities come up momentarily in the final chapter and are then brushed under the rug, despite the fact that, as Wolfram says, they are the standard objection to hidden variables accounts of quantum mechanics. The best known book on this kind of framework, Nobel laureate Gerard 't Hooft's The Cellular Automaton Interpretation of Quantum Mechanics, is not even mentioned. For some reason, Wolfram thinks his work is interesting, and is making it all publicly available. Knowledgeable people seem less than blown away. You can see some typical comments .
Loading...
