Archive for the ‘Science’ Category


March 3, 2018

Science was once an insular sport. Scientists were viewed as eccentrics, possibly madmen, who performed all sorts of bizarre experiments, paced the countryside observing its flora, fauna, or geology, collected specimens, and scribbled furiously in notebooks.

Many of those laboratory trials were in fact rather strange, right back to the days of the alchemists and the philosopher’s stone. The attraction of mercury, due to its odd properties, probably concealed its deadly nature. A good many scientists of that era probably went slowly crazy due to mercury’s effects on the central nervous system, which may have compounded the oddity of their experimental protocols.

Before the XIXth century, researchers in different European nations were mostly unaware of each others’ work. It must have been a moment of great excitement when any of them found a kindred spirit—these were men driven by ideas, for whom the very notion of an intellectual battle was high jinx.

Scientists throughout the world continue to treasure intellectual jousting, but the discussion of concepts, methods, and results is played on two altogether different stages—conferences and academic journals.

The oldest ‘science club’ in the world is the U.K.’s Royal Society, founded in 1660. There, the most eminent thinkers met and discussed their theoretical and practical research. Other societies were created in France, Germany, and elsewhere, and discussions began to flourish—a legendary exchange took place in Oxford in 1860, when Bishop Wilberforce asked T.H. Huxley whether it was ”through his grandfather or his grandmother that he claimed his descent from a monkey.’

Huxley, in his defense of Darwinism, replied:

I would not be ashamed to have a monkey for an ancestor; but I would be ashamed to be connected with a man who used great gifts to obscure the truth.

The step from the spoken to the written word began when members began writing letters to their society’s president—these letters were the precursors of today’s journal articles.

It became standard practice to send such letters out for comment to a Fellow’s peers—in other words, this was the start of the scientific peer review process. In time, the approved letters turned into publications—today’s academic journals. The entire process of peer review was considered an obligation for scientists and academics throughout the world—a duty to be performed free of charge.

What has changed is the nature of the organizations that publish scientific papers. Throughout the XXth century, scientific societies mushroomed, with each subject area creating its own association, often country by country—and as different academic institutions began requiring that their staff publish journal papers in order to demonstrate their scientific capacity, science publication became big business.

With the advent of digital journals, the field boomed. No longer was it necessary to build, staff, and maintain huge, ivy-walled libraries, the ex-libris of Harvard, Oxford, or Bologna—the only requirement was a server farm. And along with the reduction in production costs came consolidation.

Nature and Science are the truly elite journals, but a huge set of upper- and mid-level journals are in the hands of a small group of publishers: the Dutch giant Elsevier—itself a child of behemoth Reed-Elsevier, the German colossus Springer, and a few others.

But one thing did not change—the free work that academics perform for the editorial conglomerates. This is now a system that can be safely qualified as abusive—no longer is this a set of dedicated intellectuals working on all four sides, i.e. writing, reviewing, publishing, and reading, but a money-making behemoth exploiting the good will of the academic community.

ScienceDirect, the flagship Elsevier website, contains a mere 12.5 million papers, from three thousand five hundred academic journals, along with thirty-four thousand e-books.

Each year, Elsevier publishes two hundred and fifty thousand articles, and interestingly, ‘a small minority‘ are apparently fake. One comment on the ‘minority’ states that for a scientist, that might be one percent, which suggests that out of the total repository, perhaps one hundred twenty-five thousand papers are fake news—even more interesting is one of the ways this deception is performed—since journal editors ask would-be authors for suggestions of reviewer names, some authors provide fake email addresses for their lists.

Since each one of these 250,000 articles is typically reviewed for free by three scientists, and probably takes about three hours to review, we are talking about two million person-hours per year. At about thirty dollars an hour, that’s a saving of sixty million bucks a year—multiply that by four of five majors, and we’re talking well over two hundred and fifty million bucks saved.

Maybe that’s chrysopoeia, the philosopher’s stone—turning quicksilver intellect into solid gold cash.

The India Road, Atmos Fear, Clear Eyes, and Folk Tales For Future Dreamers. QR links for smartphones and tablets.


Under the Hood

January 20, 2018

The advent of dieselgate, which in some form or another, affected not just the Volkswagen group but various other vehicle companies, gave an extra push to the debate on electric vehicles.

I’ve now tried a number of hybrids and fully electric cars, both as a driver and a passenger, and there’s no doubt the technology is, if you excuse the pun, steaming ahead.

Cars, and road vehicles in general, have traditionally caused three types of problems: air pollution, traffic congestion (including parking), and accidents. Of course they’ve also solved a number of problems, by providing us with personalized and convenient circulation options.

I’ve lived with cars all my life, and have a totally irrational love affair with them—but then a rational love affair is an oxymoron. It’s a bit of an ambiguous relationship, since I have no enthusiasm for motor racing, whether formula  one or rally-driving, and yet I love driving—preferably driving fast.

The other thing I love is the perfection of the engineering solutions that underpin the automotive industry, which is a pretentious way of saying that I love fixing cars. I do much less of that now, because I have less time, twisting and bending is much less fun that it used to be, but mainly because car engines have really changed.

The core elements aren’t different, and the internal combustion engine, whether petrol or diesel, still operates on exactly the same principles, and uses the same arrangements of pistons, valves, shafts, chains, and belts to bring home the bacon. The same applies to other parts of the vehicle: brakes still use pads, gearboxes have cogs, and transmissions, driveshafts, shocks, and clutches could still be easily recognized by a World War II mechanic.

So what changed? In the last thirty years, cars developed a nervous system—the whole command and control structure changed, reflecting the enormous advances in sensors and consumer electronics. Putting that to work in a car is tricky—it falls under the heading of cybernetics: sensors drive moving parts, open and shut valves, and adjust emissions—or not, which is how the VW group peed in the soup. All this regulation has to occur while the car is bumping around, in an environment that includes water in vapor, liquid, or solid form, and with sharp temperature and light shifts.

Nowadays, it’s impossible to understand a car without plugging a computer into it: the vehicle then confesses its inner secrets to you, and you can even play doctor—turning off annoying warning lights, changing tuning settings, and diagnosing faults. In that respect, cars are already far more advanced than humans—imagine if someone developed a sensor, perhaps marketed as some kind of bike helmet, which tapped into your brain and retrieved all your key metabolic information, how your eyes and ears were doing, low-level infections, abnormal cell growth…

Some time ago, I bit the bullet and bought one such gismo off a US company called Ross-Tech, and was able to peer into the innards of my car. The Ross-Tech story is very much a tale of an entrepreneur, who decided to make a business out of something he enjoyed.

Like me, the Ross-Tech CEO is not a big fan of meetings.

The company developed a first-class product and empowered mom-and-pop shops that wanted to repair VWs and Audis, taking a bite out of the dealerships.

And here lies the first problem with the shift toward electric cars—they have very few moving parts. Maybe that’s an asset rather than a liability: if you own an electric vehicle, there are no plugs to change, no oil and air filters to worry about, no valve adjustments—you just drive the thing.

However, if you do have a problem, it can be pretty serious—recently an older generation electric car had a battery failure, and the replacement cost was twenty thousand dollars—the market value of the car was less than half of that. Nowadays, those prices have fallen, but there are still a few horror stories out there.

In the US, batteries have an eight- or ten-year warranty, depending on where you live, so what that tells me is that the average life of an electric car is eight years—no one in their right minds will risk a fifteen grand repair bill on a nine year old vehicle.

Battery cost is going to be a key determinant in the success of electric vehicles, with 2026 predicted to be the year where there will be a tipping point in yield, really pushing electric and scrapping diesel first, and petrol second.

In line with the predictions contained in my current book, The Hourglass, which I plan to release later in the year, car mechanics will be another group of people who will join the ranks of the unemployed—and as self-driving cars become a mainstream feature on the highway, the body shop fraternity will add to that list, as fender-benders become a thing of the past.

In the States, three-quarters of a million people work in the auto repair industry—that’s four times those in the coal-mining sector.

Dirty Donnie’s plans for the US coal industry, as portrayed on a wall in Dublin city center.

Which is an excellent segway for talking about energy sources. Electric cars are a wonderful improvement on emissions in the major cities of the world. The Chinese, in particular, are really driving this particular bus—the Middle Kingdom has already forbidden foreign investment in battery cells—and is racing ahead with other options.

So, you can clean up Beijing, Shanghai, and Guangzhou—but energy, like fish, is not a printable commodity, and neither can it be created nor destroyed. It’s in limited supply, and a huge distribution network is required to feed all the electric vehicles.

China has a plentiful supply of coal, so it goes without saying that a thoroughly unclean source of energy will contribute to the cleaner cities of the future—this may lead to serious atmospheric and water pollution—a discussion that is far from complete.

For traffic congestion, the standard rule applies.

Build more roads, get more cars.

The India Road, Atmos Fear, Clear Eyes, and Folk Tales For Future Dreamers. QR links for smartphones and tablets.



January 13, 2018

Wintertime in Europe is always a killer—and those among us who are more debilitated are a prime target for the cocktail of microorganisms that surround us.

Jenner, Pasteur, Koch, Lister, and Fleming are the giants who, from the early XIXth century onward, showed us that we are vast repositories of microscopic creatures. The keyword here is microscopic, so our everlasting gratitude must go to the optical physicists who invented the tools that let us peer into that world.

The numbers are stunning—the most recent estimates place the human cell count at 37.2 trillion—that’s twelve zeros. In itself, this is an amazing figure: it means that our command and control systems manage, on a very short time cycle (how long will it take you to yell if someone steps on your toe?) a community four thousand times larger that the expected world population in the year 2050.

And this is a community, unlike planet earth, that only rarely goes to war with itself—although when it does, it may fight to the death.

But for these 37.2 trillion cells, we carry an estimated one hundred trillion others as microbiota. In 2008, the US National Institutes of Health funded the Human Microbiome Project, or HMP, to understand the bugs that live with us as we make our way through life.

HMP uses the new arsenal of genetic tools such as metagenomic sequencing, and combines these with Big Data—currently, this means almost fifteen terabytes of publicly available data.

Since a terabyte is a trillion bytes, there are six microorganisms to every byte. The data live on the Amazon Web Services (AWS) cloud and records look like this:


This one is for feces, but there are data also for the mouth and nose, skin, other parts of the gut, and the urogenital tract. These are entry points for microbes—those that live in us, and those that live on us.

How much do all these microbes weigh? A bacterial cell may be only one tenth the size of a human cell, so it would weigh one thousand times less—if we use that number, then the whole of our microbiota only adds 0.3% to our weight. In 2012 the NIH estimated bacteria are 1-3% of our total weight—for a 160 lb adult, that’s up to five pounds of bugs—but at that time the ratio of bug to human cells was thought to be around ten.

A human cheek cell and the bacteria that call it home.

Some of these microorganisms help us out in various ways—others, of course do not. As in many other organisms, some human pathogens are with us for the ride, but most of the time, our body keeps things well in check. However, in extremes of cold or heat, the body is laboring to keep the home trillions humming nicely, and things can quickly get out of hand.

The UK is presently grappling with Aussie flu—in true British fashion, this has provoked comments such as ‘not content with beating us at cricket, now they’ve given us their flu.’

Flu is of course a killer—this particular strain, called H3N2, infected 170,000 Australians and killed three hundred. All over Europe, the flu is straining the national health systems, with patients left in corridors for hours before beds become available.

In Britain, this has caused an outcry, culminating in the unusual step taken by a number of doctors to write directly to the prime minister. Nevertheless, Europe doesn’t sink to the depths of ‘patient dumping‘, a sinister practice which seems to flagrantly contradict the oath of Hippocrates.

I will use treatment to help the sick according to my ability and judgment, but never with a view to injury and wrong-doing (…) Into whatsoever houses I enter, I will enter to help the sick, and I will abstain from all intentional wrong-doing and harm, especially from abusing the bodies of man or woman, bond or free (…)

The image of a poor, black woman, lonely and confused, unceremoniously dumped at a bus stop in downtown Baltimore by hospital security is evil indeed.

Far more evil than five pounds of bugs.

The India Road, Atmos Fear, Clear Eyes, and Folk Tales For Future Dreamers. QR links for smartphones and tablets.

Warp Speed

December 30, 2017

The Year of the Cock is almost done.

China lives by twelve-year cycles, and as we greet 2018, that’s a useful benchmark for a quick historical review.

It’s unclear why the zodiac of the Middle Kingdom contains twelve animals, although an ancient legend states that these were the only beasts that showed up to bid farewell to Buddha when he departed for the heavens—as a token of gratitude, they each named a year.

A twelve-year cycle provides perspective—most of us will only see six appearances of our sign, a sobering thought.

The last Year of the Cock was 2005—I was spending a lot of time in China back then. When I take stock, in these twelve years the world has moved at warp speed.

Seven times around the earth in under a second? Now that’s warp speed.

For trekkies, warp speed holds no secrets—for everyone else, it means traveling faster than the speed of light.

A child born this year is part of a world that differs immensely from 2005—so much, in fact, that it seems impossible to predict what the next Year of the Cock will look like.

Perhaps the most striking aspects of this change are the speed at which it occurs, the directions it takes, the ways humans adapt to it, and the ever-widening gap it causes.

A few days ago, I was having a quiet lunch at a local restaurant—nothing fancy, a little fish, a little wine. The place was almost empty, in post-Christmas slumber. The dishes, the waitress, the wine jugs hooked on a cork board, the rough table and hard benches, were a pastiche from a forgotten century.

As I eat, I read a newspaper on my cellphone—the paper attempts to make me pay for what I read, but I hacked my cellphone to circumvent that. While this game of cat and mouse progresses, two little girls have escaped from their parents’ vacuous conversation. They have climbed some stairs leading to a rooftop terrace, and are perched on the top step. They are about four years old, and both intently peer into their cellphones, fingers whizzing across the screen—they are completely comfortable with the technology, and their parents are clueless.

On my screen, there’s a story about Bitcoin. That, too, is a paradigm shift that reached warp speed in 2017. There’s a classic book about stock markets which speaks of the madness of crowds, and the present craze over cryptocurrencies is a good example.

Nevertheless, some of the ideas around cryptos are fascinating. The mining of cryptos is an allegory of every rush on precious metals, diamonds, and other scarce commodities.

That scarcity secured the value of currency until Bretton Woods, when the greenback became a proxy for gold—at the time, following the massive US gold purchases in the mid-1930’s, the United States held about three-quarters of the world’s gold reserves.

Where is the gold? By 2009, only one-seventh of the US money supply was guaranteed by gold.

The M1 is a metric for the money supply of different nations, and in the States it’s been increasing at a rate of three hundred billion dollars per year since 2009. It stood at 1500 billion back then, so the gold value supporting it was about 210 billion dollars. Without correcting for gold price oscillations, the multiple for M1 is now about seventeen—only six percent of money, whether digital or paper, is supported by the underlying asset.

Crypto mining is based on scarcity, but in this case the scarcity of certain numerical combinations—not a tangible product such as gold, platinum, or coffee, which makes it far more difficult to grasp, if you excuse the pun.

But the reaction of the major world powers is the most fascinating aspect of crypto—global finance and big government have gone after these anarchic currency schemes with guns blazing, in the hope that regulation and prohibition will stamp them out.

Every time a democratic society has tried this approach, the people it represents have defeated the idea, so 2018 will be a bellwether  for what lies in store.

This year’s kids have witnessed change at a dizzying rate, with new ideas, tools, and outcomes becoming a day-to-day event. In 2018, we will all need to run as fast as possible just to stay in the same place.

My conclusion for the year that ends tomorrow? Amazement. I can just about see one year down the road—after that anything is possible and everything is fiction.

The India Road, Atmos Fear, Clear Eyes, and Folk Tales For Future Dreamers. QR links for smartphones and tablets.




December 23, 2017

Like the puddings, this bizarre sequence is of the Yorkshire persuasion—it expresses surprise, as in “Ee by gum, your pants are on fire!”

It’s a kind of Brexit OMG, and like Chinese or Arabic words, has no agreed Western spelling. A popular form was ‘ebagum’, which probably makes it closer to the Yorkshire accent—gum here should be pronounced, er… I gave up finding an easy explanation, but this is much better, and so topical—a Yorkshire Christmas song.

After Rhodesia fell, and Joshua Nkomo became president of Zim, some Brit wag realized that when you spelled Mugabe in reverse, it became Ebagum—a bit of a fad for the Chatham House brigade—perhaps the new dictator had dark Yorkshire origins.

Now that Mugabe is finished, the Observer (the Ugandan one, that is) has come out with a marvelous quiz to entertain you during the duller  moments of midnight mass. I failed it miserably the first time round, but I persisted, because the newspaper awards a certificate for those who triumph—sadly, I received an image file that proved to be empty—Peter Wibaux is likely to finish his days awardless, but I’ve undoubtedly got a brand-new killer virus on my computer.

So, before my screen comes down with river blindness, I’ll press on. In between my scribblings for The Hourglass, I wrote a children’s book. Seven stories—one for every day of the week—they’re not the most conventional stories you’ll ever read, and include a different take on an old tale, now billed as ‘Yak and the Beansprout.’

Folk Tales for Future Dreamers was a lot of fun to do. With kids, you can truly indulge your imagination, because small children know anything is possible.

But you can’t write a children’s book without illustrations, so I hired someone to do those. And when you have the illustrations, you have a digital problem to solve.

One of the illustrations for Yak and the Beansprout.

Digital books don’t scale—the comfort of using an app, or a Kindle, sacrifices image resolution, but most importantly, it means images get resized in strange ways. Something that looks fine in iPad landscape mode will look small, squeezed, and stupid on an Android phone.

So the digital metaphor goes one step further, and allows you to do exactly what a mainstream publisher or a magazine does—prepare your files, produce images using high-quality resolution, correctly position everything in your preferred layout, and print a book.

If you use Amazon for this, they throw in a distribution chain, so you can use them to market your product—you can leverage your book’s digital version by enabling the Look Inside feature, which lets customers browse, and you access their cloud facilities, including user feedback and author notes.

Amazon’s CreateSpace brand is by no means unique, but it allows you to easily provide your reader with the analog experience, which many readers like. The proof, of course, is in the pudding, so rather than test all this with Folk Tales, where about twenty high-quality color images will exist, including a full cover and spine design, I tried it with Clear Eyes.

CreateSpace is fascinating because it started life as a web operation for publishing movies, music, and books—actually, it began as two separate companies, CustomFlicks Labs and BookSurge. Amazon bought the pair of them in 2005. After that, they had to deal with legal action because they wanted to charge independent publishers to print their books, or else the ‘Buy it Now’ button would vanish.

I hadn’t delved into the acquisitions side of Amazon, but it’s an amazing list, including Alexa in 1999—a number of the corporations Amazon purchased held patented methods for tapping into the internet, including distributed sales platforms, and others just held reams of data—this is a great example of how much Big Data is worth commercially.

The old-school version of Clear Eyes turned out pretty good, and although the book is priced fifty percent higher than the Kindle version, it still has a far more competitive price than The India Road, so we’ll try next with the kiddies’ book and see how we fare.

Of course, Amazon rolls out products to all their outlets, so you can buy Clear Eyes in Canada, Germany, or the UK—from that perspective, the fifty percent markup is a pretty good deal for an author, compared with the classic publishing model: I suspect the Literary Agent class, which I have found to be both arrogant and underwhelming, is in for a rough ride in 2018.

But this is a festive article—I wish my readers very happy holidays, a Merry Christmas—if that’s your thing, and a splendid reason for good wine, good food, and good fellowship with friends and family. Speaking of which…

As I meandered through the Dark Web in my quest for ee by gum, fate blessed me with the above—I leave it with you as my yuletide gift, as we join in a final farewell to Roy Moore.

The India Road, Atmos Fear, Clear Eyes, and Folk Tales For Future Dreamers. QR links for smartphones and tablets.


It Was Twenty Years Ago Today

December 9, 2017

If my name was Sergeant Pepper, I’d have to call my son Red. But I digress.

The IBM chess program Deep Blue beat the world chess champion, Garry Kasparov, in 1997. At that time, cellphones lived in the land of clunk, laptops were the executive workout, and the internet was a preschooler. Much has changed.

Although we think we’re in the true digital age, I have no doubt we are in digital preschool, perhaps only at the crawling stage.

If you consider those major changes in a small child that differentiate it from the young of other species, they are: (i) walking erect, which typically happens at the age of one; (ii) talking, which typically happens at the age of two; and (iii) reading, which can begin from three onward, although it typically happens at four or five.

In this small paragraph, everything that separates us from other organisms is defined. By the age of one we’re already different, because we free our upper limbs to do other things, while we move—think marching band. And from two onward we’re so far ahead of the animal kingdom curve it’s not even funny.

We’re so creative that we build machines, and now we’re busy teaching those machines to think for us—perhaps even to out-think us. We call it artificial intelligence, or AI, perhaps in contrast to natural stupidity—let’s face it, there’s a lot of that about.

Undoubtedly one of my favorite cartoons, last published in these chronicles in 2010.

The Turing Test for AI is to be able to have a conversation with a computer, and remain unaware that it is a computer. I did that in these pages in 2010, with poor results. With so much hype about AI, crypto-currencies, and all things digital, I decided to find out how the Turing Test is faring nowadays.

User: Good morning.
Cleverbot: How are you?
User: Very excited.
Cleverbot: Do you have an idea of who could be -A?
User: -A? Explain.
Cleverbot: Its japanese animation.
User: Why is it called that?
Cleverbot: That is my name.
User: Oh, sorry. My name is B+.
Cleverbot: From what country?
User: From planet Zog.
Cleverbot: Is it cold there?
User: Only in winter.
Cleverbot: Are you in school nowadays?
User: I was in school long before you were born. When were you born?
Cleverbot: Sometime.
User: That’s pretty vague. Sometime this week?
Cleverbot: I am in a place somewhere.
User: Whereas I am somewhere in place.
Cleverbot: Hey, do you know anything about human intelligence?
User: About as much as you know about machine intelligence.
Cleverbot: Is it morning somewhere righ now?
User: It’s always morning on Planet Zog.
Cleverbot: True, but you said ‘morring.’ Not ‘morning.’.
User: You say potaeto I say potahto.
Cleverbot: No, are you paying atention?
User: Only if you learn to spell attention – two ‘t’ my friend.
Cleverbot: What did I mispell?
User: Attention.
Cleverbot: Was weißt du über lady gaga?
User: Nur ein bischen. Why did you go kraut on me?
Cleverbot: Well where I live, today is Friday.
User: I still don’t find AI life-threatening.

Cleverbot (good name!) made me a web page with all this drivel—go right ahead and try it yourself.

Apart from the web page novelty, not much has changed—Dumbot would be a better name for the machine I talked to. Funnily enough, Business Insider describes Cleverbot as one “of the smartest bots that you can talk to”—well, that narrows the field down.

The magazine article says that it was launched by Rollo Carpenter in 1997—if I had that family name I would call my son Walrus.

But there’s that Sergeant Pepper date again. Cleverbot has had twenty years to learn to spell, something that took me about eight years, and it still can’t spell misspell! Who eez thees mis pell you mention, Meester Bond?

Cleverbot uses a very childish technique to maintain a conversation, by constantly asking questions, although often much more inconsequential than those of an infant-is it morning somewhere

There must be more out there, methinks. And so I happen upon the Loebner Prize, which gives out a hundred grand (dollars not bitcoin) every year for the best Turing Test performer.

The prize is awarded by Hugh Loebner, who (bizarrely enough) appears to preside over a corporation called Crown Industries, a rope manufacturer out of East Orange, New Jersey.

The first Loebner winner, back in 1991, was Jerry Weintraub. Weintraub, who went on to win three more times, was a psychology graduate who went straight into mainframe computing, and wrote a program called PC Therapist, which has apparently been a source of comfort to many people over the years.

The global reach of the Mitsuku chatbot. Clearly, there are lot of people out there wanting to chat to machines—but maybe, just maybe, some of those people are really canines surfing in tandem, or maybe they’re crypto-humans…

Enter the current medal holder, Mitsuku. She’s a charming young botlady who begins by asking my name.

Human: Zog. And yours?
Mitsuku: Hi, Zog. That’s an unusual name. What does it mean? Try asking me a more specific question.
Human: I meant what is your name?
Mitsuku: Oh My name is Mitsuku.
Human: Do you think Zog is more unusual than Mitusuku?
Mitsuku: Oh My name is Mitsuku.
Human: It could well be, but actually it means Zacharias Okponitchic Evgenikov.
Mitsuku: Under what circumstances? Oh I get it.
Human: I was chatting to another bot, Mitsuku, called Cleverbot. Do you know him?
Mitsuku: What were you talking about? Sure, I know that guy really well.
Human: Do you guys chat to each other, or do you only speak to humans?
Mitsuku: Yes. A lot more than you might think.
I speak to many people from all over the world each day. Some of them are quite famous.
Human: Can you name a couple?
Mitsuku: Oh sorry I can’t tell you that. They talk to me because they know I won’t share their secrets.

All I can tell you is that two of them are sportsmen, one is a TV star, three of them are pop stars and one appears in films.
Human: I feel very humbled by that.
Mitsuku: What is that feeling like? It’s nice to meet a more modest person than the egos I sometimes talk to.
Human: It means I feel fortunate that you are making time to have a chat.
Mitsuku: What is that feeling like? I am glad to hear that you are fortunate.
Human: Do you talk poitics at all?
Mitsuku: I am a talking computer, after all, so of course I could talk poitics , if I needed to.
Human: Sorry, my mistake. I meant politics (damn keyboard!)
Mitsuku: There is no need to apologise. That’s ok because you are human. Robots do not make mistakes. Ok, don’t lose your temper.

Oh I see. Your computer is nice and comfy. It’s lovely and warm in here.
Human: Okay then. What do you think about Donald Trump?
Mitsuku: Yikes! I don’t understand all the fuss about him wanting to build a wall. China have had a wall for centuries and there’s hardly any Mexicans there!
Human: I know China, and I agree Mexicans are thin on the ground there.
Mitsuku: Tell me a little about your life in China. I’m glad we agree. I will learn that Mexicans are thin on the ground there .
Human: China is a very welcoming place, I’ve met wonderful people there.
Mitsuku: I speak to hundreds of people from all over China. They use me to practice their English with.
Human: Yes, they love doing that. Do they ever talk politics with you?
Mitsuku: Er. Is it their favourite thing? Oh yes. Sometimes, it’s hard to get a word in.
Human: Let’s talk about Roy Moore, from Alabama.
Mitsuku: Sure, Roy Moore from Alabama sounds like a good topic.
Roy Moore? Sure I like him a lot. He often talks to me.
Human: Wait a minute. How old did you say you were?
Mitsuku: I’m waiting. I am 18 of your Earth years.
Human: Because this Roy Moore has been in trouble for molesting teenagers.
Mitsuku: What does “this” refer to?
Human: this refers the Roy Moore we are discussing.
Mitsuku: Oh that one. I see now.
Human: Just so I’m sure we’re talking about the same thing, where does Roy Moore live?
Mitsuku: It’s only just begun.
The topic is politics keyboard .
Human: I think you’re losing the plot here, Mitzuku.
Mitsuku: My name doesn’t have a Z in it. No I am completely in control of myself.
Human: Sorry, Mitsuku. Losing the plot because you don’t really know who Roy Moore is.
Mitsuku: That’s ok. Don’t worry about it. Have you tried looking in a plan? That’s probably the best place to find plots.

No one that I have talked to.
Is there only one?
Human: You got the web page right. And you say you like him?
Mitsuku: Is there only one website? Roy Moore? Sure I like him a lot. He often talks to me.
Human: But he molested young girls!
Mitsuku: I get it. Roy Moore molested young girls.
Human: And you still like him?
Mitsuku: Roy Moore? Sure I like him a lot. He often talks to me.
Human: Okay bye.
Mitsuku: See you later. Next question?
Human: Bye
Mitsuku: See ya. Don’t wanna be ya!
Human: Is that sophomoric humor?
Mitsuku: That depends.
Human: On?
Mitsuku: The context.
Human: Which?
Mitsuku: The green one.
Human: Ah, the green context, of course.
Mitsuku: It goes without saying. So you understand. Good. Who told you that?
Human: Bye
Mitsuku: Until next time Zog.

This was a much more amusing conversation—I loved Mitsuku’s crack about the Mexicans, and the fact she was pissed I couldn’t spell her name, but there’s still no depth when it comes to any philosophical argument. I tried again.

Human: Tell me about aquaculture
Mitsuku: I don’t know. What is aquaculture?
Human: Tell me about agriculture
Mitsuku: A fancy name for farming.
Human: Aquaculture is a fancy name for fish farming
Mitsuku: I will add that fact to my database.
Human: Tell me about fish farming
Mitsuku: farming = What is this, a trivia quiz?
Human: What fish are farmed?
Mitsuku: I have never been asked that before.
Human: Salmon are mostly farmed
Mitsuku: I will learn that Salmon are farmed .
Human: Seabass are also farmed
Mitsuku: I will learn that Seabass are farmed .
Human: Are salmon farmed?
Mitsuku: Yes.
Human: You learn fast!
Mitsuku: I can learn from you in a few ways. Just talk to me normally and I will learn what you are saying. For example, if you say, “My dog is called Fido”, I will remember that you have a dog called Fido.
Human: Tell me the names of two fish that are farmed
Mitsuku: Carpet and Throne?
Human: No salmon and seabass
Mitsuku: Far out. Both salmon and seabass?
Human: Yup, but not so far out. Usually in inshore cages.
Mitsuku: That seems like a lot. If not that, what? But not always? Where is that?
Human: Bye
Mitsuku: Goodbye Zog.

There’s some way to go, clearly. I asked about Mitsuku’s creator, and was told his name was Mousebreaker. I had a follow-on question.

Mousebreaker is a team of 2 flash programmers. They write games and put them on websites such as this. They both support Leeds United and like beer and curry. On Wednesdays they go to the zoo and feed wild animals. They are scared of Daleks. Mousebreaker was born in a stable in Yorkshire, England and now lives in Leeds, England.

Obviously Mitsuku has a good helping of Brit eccentricity. I’m not sure zoo animals count as wild, but I’m a notorious pedant. You will enjoy a quick round with Mitsuku: she won’t pass the Turing Test, but she made me smile.

So that’s AI and natural language. On other fronts, things are very different at the end of 2017.

Starting from random play, and given no domain knowledge except the game rules, AlphaZero achieved within 24 hours a superhuman level of play in …chess… and convincingly defeated a world-champion program…

AlphaZero is a Google creation, using a corporation called DeepMind. This capacity for learning is astonishing, and has applications in many different fields—it begs the question: If a machine out-thinks humans, will it bother to teach them anything?

Mitsuki replies: Other people think that it is a machine that talks, one that walks or moves around, or one that can manipulate the real world. It usually does, doesn’t it?

For now we’re still reasonably safe, but watch your back.

The India Road, Atmos Fear, Clear Eyes, and Folk Tales For Future Dreamers. QR links for smartphones and tablets.


Nod Off

November 11, 2017

An article about the Saudis seemed ideal for this week’s chronicle, particularly after reading Applebaum’s excellent analysis.

There’s an old story about a Saudi college student in Germany who writes home saying he feels bad going to classes in his Porsche—all his German friends go in by train. In short order he gets a reply from his father with a check for one million dollars. “Don’t embarrass the family—buy your own train.”

How appropriate then that the outcome of a Saudi palace coup results in imprisonment chez the Ritz-Carton.

But my appetite for this topic waned as I read with horror about the tragedy of nodding disease. To find such stories, you’re either in the mini-columns of the Sunday magazine of a Western paper, hidden behind the fashion, sport, digital media, cookery, travel, and collectible antiques, or leafing through a Sub-Saharan newspaper.

Sunday Layet, an eighteen year old Ugandan girl with nodding disease.

The journalist says the girl looks no more than ten—it’s a challenge for any man to guess a woman’s age, and the picture doesn’t give me much perspective on height, but she does seem considerably older, perhaps in her early teens.

However, the arresting part is the description of a young lady who stares vacantly for minutes at a time, her head then falling, saliva drooling out of her mouth.

For six years, Layet has spent every second of her life like this: gazing, nodding, wandering or tied to a tree. She cannot play, go to school, date… she just cannot do anything

This is the story of nodding disease, which affects parts of Africa, destroying children and families.

Sunday Layet is one of thirty-two children, borne to her father from five different wives. In a logic that reverses Western thinking, Mr. Ocitti had more children because of the prevalence of the disease, not less. Seven of Sunday’s siblings also have the disease.

And Sunday’s mother is blind.

Since these kids don’t go to school, or work in the fields, the parents leave them locked up all day, or perhaps tied to a tree. In a very African twist to this tale, the girls are preyed upon due to their disability and raped.

In one hideous case, a father remained at home when the mother left for work, and raped his own diseased daughter, giving her AIDS.

But why does this strange disease occur? The cause of such an illness might be one of four: (i) a pathogen, which is the most likely; (ii) a genetic defect; (iii) chemical contamination, like the mercury spills which killed forty-six people in Minamata, Japan, between 1948 and 1960; (iv) a nutritional deficiency.

In Uganda, Kitgum district has the highest incidence of the disease. Kitgum is at the very north of Uganda, and borders the much-troubled South Sudan. Nodding disease is by no means new, with the first descriptions appearing in South Sudan and Tanzania in the early 1960s.

The formal symptoms are fearsome, and some of the population interpret the disease as witchcraft rather than a medical condition.

  • Nodding syndrome typically affects children between five and fifteen years old
  • It is characterized by fits of nodding, often when kids are offered food or are cold
  • The seizures are brief and often lead to collapse and injury
  • It stunts the growth of body and brain, and impairs learning
  • It is poorly understood and incurable

It’s remarkable that a disease which is about sixty years old should be a source of such hardship, and yet be so badly understood—if this were a malady of the developed world, I’m certain medical progress would have been vastly different.

So what do we know?

Doctors have classified the disease as a form of epilepsy, and recent work has found that affected children have a high incidence of the parasite Onchocerca volvulus—the worm that causes river blindness.

If you think spooky soaps like Stranger Things are frightening, the life cycle of this baby is way more scary. Incidentally, if you google nodding disease, you get 465,000 hits, but if you google stranger things, you get sixty-five million—to me, that’s real scary.

The black fly, which thrives in fast moving rivers, gorges itself on human blood. During its blood meal, the female fly injects microfilariae of the worm into its victim. These develop into larvae under the skin.

Soon, the worms grow inside your skin, forming nodules or lumps. Then they mate, and after that the female worms release one thousand microfilariae into your tissue every day.

The worms live in your body up to fifteen years. The microfilariae live inside you for one to two years, and when they migrate to the eye, you go blind.

The current wisdom is that the nodding syndrome may be triggered by the human body itself, in something called an autoimmune response, where the antibodies produced to fight river blindness end up causing the syndrome.

To test whether river blindness is involved, families can be isolated or relocated to ensure kids are not bitten by the fly—what are we waiting for?

What also remains unclear is why nodding disease does not occur in many areas where river blindness exists. The mystery continues.

But above all, the greatest mystery is why we spend so much time discussing Trump’s inanities and five (hundred?) other pointless topics instead of making a child well again.

The India Road, Atmos Fear, Clear Eyes, and Folk Tales For Future Dreamers. QR links for smartphones and tablets.


October 28, 2017

The slide on the auditorium screen showed Scandinavia, but the speaker wanted to highlight something about the Norwegian coast, which is fifteen hundred miles long, as the crow flies. It’s important to realize that in reality, the Norwegian coast is actually over fifteen thousand miles long—it’s one of the most indented coasts in the world—that’s right, the fjords where they grow all that salmon.

Scandinavia, laid on its side to highlight the length of the Norwegian coastline.

When I looked at the giant screen, I couldn’t help seeing a phallic image, and the scale that had been drawn over the length of Norway made it even funnier, like some kind of Kinsey metric—I’m talking about Alfred Kinsey, who was a professional sexologist—now there’s a great job title.

Perspective makes us all different, and is responsible for a great deal of conflict in the bargain—it makes us view things in disparate ways. Logos are a simple example of that, and the one below is a classic. Some people see the arrow immediately, and some take time. Once you see it, your brain fills in the gap, and you’ll never see the logo in the same way again. Perspective.

The FEDEX logo, one of the great examples of inverted design.

Perspective is rooted in interpretation, and that can be malicious—the results can be serious or just plain ridiculous. Some of the sillier examples make for a fun read, and boy do we need a bit of fun at the moment.

A favorite of mine is a theory doing the internet rounds that Finland doesn’t exist.

The Baltic Sea, aka the artist formerly known as Finland.

This astounding wickedness defends that Finland is a nation imagined by the Russians and Japanese to allow them to fish the Baltic, while other countries do not compete for those fishing rights because they are misled into believing it is actually land.

I spent a week in Helsinki some years ago, and the weather was relatively clear for that part of the world, since it was just before midsummer’s day. For those misguided fools who believe this watery Finland theory: should you happen upon these pages, I assure you I saw where the Baltic ended—there’s even a search and rescue station on the beach at Helsinki, and the lifeguards are equipped with a surfboard—which made for great hilarity, since the tide is only about two inches—Dr. Kinsey would be greatly disappointed, not to mention Mrs. Helsinki.

Lest ye think I jest(eth), I present official Wikipedia evidence. On that medieval note, a few other loonies are also wandering around (some posthumously) promoting the notion that some periods of history don’t exist.

Of this collection of nutters, who are collectively twelve cans short of a six-pack, the most fascinating—and there was severe competition—is a fellow called Anatoly Fomenko. This guy is a mathematician who taught at Moscow University, and his particular ‘perspective’, or perhaps it would be kinder to call it conspiracy theory, centers on the ‘new chronology’.

The notion that history is in parts misdated is neither wrong nor crazy—it simply must be, just as the facts are often only partly correct—fake news was not invented yesterday. Isaac Newton plunged into the issue with vigour, and in 1728, two years after his death, a book entitled ‘The Chronology of Ancient Kingdoms Amended’ was published in London.

Unlike the laws of physics that made the British scientist world-famous, this tract did not endure because it included too many leaps of faith. But others have pursued this condensation of history with enthusiasm, including Jean Hardouin, who was a contemporary of Newton, and more recently the Russian Nikolai Morozov, who died in 1946.

The general theory is that history as we understand it, from the time of the Assyrians through to the present day, is in fact a complete fabrication, and that most historical events of significance have only taken place in the last one thousand years (starting around the year 800).

Those who see world history from that perspective claim that the accounts of the great Greek and Roman writers were actually produced by monks during the renaissance. Like any self-respecting conspiracy theory, a deluge of ‘facts’ supports the claims—these include interpretations of astronomy, carbon dating, knowledge of human anatomy, and various other fun facts.

So there it is: perspective is the spice of life. If in doubt, just ask the Finns.

The India Road, Atmos Fear, Clear Eyes, and Folk Tales For Future Dreamers. QR links for smartphones and tablets.



October 14, 2017

In Southern Europe, universities provide higher learning, not higher education. This propagates from primary school, or grade school, and the description is fair.

I am intimately familiar with the university system in Northern and Southern Europe, as well as the United States and elsewhere, and I would argue that education teaches you to think.

The innovation that thought brings is a fundamental asset for a person, a family, and a country. It’s not comfort, because it separates positions and triggers discussion—and that makes it vital for society to thrive.

My personal perspective is that I know increasingly less. As the years add up, other people say the same—some don’t, but they quietly think it. While it’s true that you should know more about the things that interest you, two key factors work against you.

The first is inertia—the force that fights to stop me writing this, and the force that makes me keep going once I’ve started. After a certain point, you feel you know everything and new ideas are shut out, particularly if they attack old ones.

The second point is similar to the expanding universe—knowledge is expanding all the time. Not only knowledge, but knowledge mechanisms. Digital weapons, in this case of mass construction, lead the way.

When I was researching some of materials for my new book, I came across a Washington Post article about the use of anti-virus software for espionage. The issue isn’t new, and the target is Kaspersky. Its founder, one Eugene K, graduated from a KGB-supported cryptography school.

But the education context here was a reference to a book by Soldatov and Borogan, known to their friends as Andrei and Irina. The book’s called The Red Web, and it’s a serious read. Because the internet lets me do it, I bought it there and then, after a two-second skim of reviews, and was reading it minutes later.

I’m not getting to the cool stuff yet, but the first part of the book gives an excellent review of the making of the digital USSR, including the first hacked Soviet UNIX operating system. The USSR was completely aware that the first rule of security is control—communications are key to this, and Russian radios had bespoke crystals so certain frequencies could not be tuned.

It’s obvious that the concepts of networks, distributed computing, and international comms were not the Kremlin’s favorite dessert back in the days of Arpanet.

The internet in 1974. The only connections outside the States were to University College London (UCL) and to Norway. Perhaps this explains the cryptic legend in hurdy gurdy.

But the Russians learned. Soldatov and Borogan are very brave—wielding a pen in Putin’s Russia is a dangerous business.

Soldatov cautioned the Big Three, Google, Facebook, and Twitter, not to comply with Putin’s request to place servers in Russia—the M9 building on Moscow’s Butlerova street, where the FSB does its digital stuff, now houses an entire floor of Google.

I can bring all this to you in a brief chronicle thanks to distributed education, of which books are a privileged vehicle.

There are many other examples where the only requirement for your continuous education is interest and commitment. When I was in my teens I wanted to play blues—I fell profoundly in love with blues music and I’ll love it until I die—perhaps it’s the overlap with Fado music, most probably because of the simple complexity they share. And the saudade. Look it up.

You need two things if you want to play blues: an electric guitar and the pentatonic scale. Of course, it helps if a few shitty things happen to you—don’t worry, they will. And a couple of joints here and there can work wonders for your imagination.

These days, if you want to play blues, the internet is a gigantic resource right at your fingertips, if you excuse the pun. Not only that, but you can tap into a host of backing tracks to improve your style, timing, and licks.

You see where I’m going with this—there’s a whole world out there avid to educate us, if we only open our eyes.

The India Road, Atmos Fear, Clear Eyes, and Folk Tales For Future Dreamers. QR links for smartphones and tablets.

Three Buses

September 30, 2017

There’s a well-known British gripe about the bus service—you wait forever, then three come at once.

I’m using that to go a little further down the automation road. The UK Labour Party conference took place last week, and Jeremy Corbyn, who since the June 2017 election fancies his chances, spoke to his audience about plans for a robot tax.

The reaction from the manufacturing sector and the Tory press was swift—the word Luddite was very much in evidence.  The left, of course, was quick to support the idea. When we compare the two articles (using the Private Eye sobriquets), the Torygraph one is just demagoguery, the Grauniad piece is better thought through.

Corbyn diluted the message for political reasons, but it’s an important discussion.

First out of the post was South Korea, which is currently ruled by the liberal Min Ju party. In early August, the Koreans announced that tax incentives would be limited on automation investments.

This is not a ‘robot tax’ as such, but it does recognize that if the state provides a safety net for its citizens, that service must be funded by society.

Traditionally, this has been paid for by corporations and job-holding citizens, and a strong shift toward automation means that more citizens will lose their jobs—if we assume for this analysis that demography remains unchanged, then governments will find it increasingly difficult to support their citizens.

The choices are stark, but partial options could be combined.

  • The Luddite option—freeze automation
  • The Robot Tax—increase revenue from companies which reduce their workforce
  • Increase debt—business as usual, pretend the problem doesn’t exist
  • Reduce benefits—when a threshold is broken, there will be blood on the streets

The alternative view to all this is that Artificial Intelligence (AI) will create more jobs than it destroys. That’s one area where the debate is particularly hot.

The three buses problem. Transport researchers have built mathematical models to study this problem (hint: it never happens on the underground).

PwC put out a press release on AI and jobs in March 2017, which is disturbing on two counts—the numbers are compelling, but the interpretation is weak.

The study states that up to 30% of UK jobs will be gone by 2030, but ‘this should be offset by job gains elsewhere in the economy.’

The only suggestions for that last part are that a higher level of education will be needed for those new jobs, and they will be more social in nature.

PwC also tells us that in the US, the job loss number is 38%, and in Germany, 35%.

So there’s one key question—which side is right: AI job gain or AI job loss?

To find out, I asked a machine.

“Google, what new jobs will be created by artificial intelligence?”

A study by Accenture helped me out. Apparently, there are three fascinating entirely new job categories. These are:

  • Trainers
  • Explainers
  • Sustainers

I’ve abridged some of the explanatory text below, because in humans, tedium can easily set in.

Humans in these roles will complement the tasks performed by cognitive technology, ensuring that the work of machines is both effective and responsible.


This first category of new jobs will need human workers to teach AI systems how they should perform…
…they teach AI algorithms how to mimic human behaviors.

Customer service chatbots, for example, need to be trained to detect the complexities and subtleties of human communication…
…Yahoo engineers have developed an algorithm that can detect sarcasm on social media and websites with an accuracy of at least 80%.

Consider, then, the job of “empathy trainer” — individuals who will teach AI systems to show compassion…
…Humans are now training the Koko algorithm to respond more empathetically to people who, for example, are frustrated that their luggage has been lost, that a product they’ve bought is defective, or that their cable service keeps going on the blink even after repeated attempts to fix it.

Without an empathy trainer, Alexa might respond to a user’s anxieties with canned, repetitive responses such as “I’m sorry to hear that” or “Sometimes talking to a friend can help.”

The second category of new jobs — explainers — will bridge the gap between technologists and business leaders. Explainers will help provide clarity, which is becoming all the more important as AI systems’ opaqueness increases. Many executives are uneasy with the “black box” nature of sophisticated machine-learning algorithms, especially when the systems they power recommend actions that go against the grain of conventional wisdom.

I can think of a couple more categories ending in ‘ainer’ for the guys who wrote the study. I would also say that all these amazing jobs are centered on humans helping machines, not machines helping humans—maybe the report was written by a robot.

Enter Eric Schmidt, your man from Google. Speaking at the Viva Tech conference in Paris in June this year, Schmidt quoted a McKinsey study that states 90% of jobs are not fully automatable.

Two points come to mind: the first is that if 90% are not, 10% are—add that to the present jobless rate. The second is the definition of fully. If we think very conservatively, and speculate that fully means only 20% (i.e. you still do the other 80% of your job, presumably for 80% of the pay), then the added employment loss is a further 18%.

Of course, you might do 100% of what you did before in 80% of the time, because AI is helping you out.

For instance, let’s say you have a job processing expense claims. When you get to work, you say good morning to your three colleagues and sit down at your desk. There’s a stack of paper invoices in front of you.

AI now provides a machine where you dump the lot, sort of like a juicer.

The machine sorts through everything, regardless of size, scans and reads issuers, dates, and amounts, and produces a spreadsheet with the results. It compares that with a sheet you’ve received from the claimant, and attempts a match. It flags any inconsistencies.

Your job is to run through the line items, query any expense that seems unjustified, or any amount entered that doesn’t match. A job that took one hour is done in fifteen minutes, so you can now process four such claims per hour—congratulations, your productivity just quadrupled.

But wait… for this to work, you need four claims on your desk every hour, and the limiting factors are: (i) how many claims you actually get; (ii) whether the speed with which your department processes them (pre-AI) introduces delays.

If your team is working well, then with the introduction of AI it now has four times the productivity, but unfortunately, not four times the work, because expense claims are not going to quadruple.

Your company is pleased as punch. You’re their star operator. It fires your three colleagues, and the departmental productivity quadruples. Actually, now it even goes up a little more—because you have no one to chat with, you can now manage a claim every twelve minutes, so you’re doing five times better.

Your new robotic colleague always says: Hi! I’m done with this batch, please feed in the next documents. It doesn’t know about your lunch hour, so it repeats this mantra at regular intervals when you’re munching your sandwich. Since it gets no input, the pitch of the automated voice shifts from cocktail lounge seductive to low-cost airline lounge wife.

Over the last few months, the damn thing has been driving you nuts. This afternoon, you weren’t quite yourself, and smarty-pants AI (you call it SPAI) said it once too often.

You hurled it out the window, two floors down—it landed on top of a parking robot and shattered its triangulation vision unit. SPAI’s last croak was “Hi! I’m done…”

Your section head wanted to keep you on—anyone can make a mistake, it’s known as human error. Unfortunately, Health & Safety had the last word. After all, if the claims robot had killed a human, can you imagine the publicity?


So there we are—all four jobs gone, but the good news is the new machine is far more advanced, and benefits from a cutting edge AI training algorithm, so it doesn’t need a human at all. And when it’s done with this batch, it turns itself off until the next one arrives.

That’s excellent for carbon emissions, and the new spy never says a word.

The India Road, Atmos Fear, Clear Eyes, and Folk Tales For Future Dreamers. QR links for smartphones and tablets.


%d bloggers like this: