STICKS AND STONES

Dick Pountain /Idealog 346/ 04 May 2023 10:29

It’s no great surprise to me that the movie business is terribly poor at dealing with IT-related material in an adult fashion. First of all, the industry’s whole purpose is to entertain, and neither solid-state physics nor computational complexity theory are intrinsically entertaining (to put it mildly). Secondly, entertaining nowadays mostly means blowing things up, and the technology for doing that is no different in principle from the spear or bow-and-arrow, just with more oomph behind it, more fins and shiny bits: the Marvel Universe shares aesthetic principles with the funfair rather than the library. Thirdly movie people tend to be from the artistic rather than scientific world, have neither the wish nor need to understand the physical principles behind tech artefacts: they want to know what things do rather than how they do it, and employ that knowledge as plot elements.

There have been a very few exceptions, and I’m not talking about biopics like ‘The Imitation Game’ or ‘A Beautiful Mind’. l liked Alex Garland’s ‘Ex Machina’ a lot, and Spike Jonze’s ‘Her’ quite a lot less because these films at least tried to tackle the psychology of humans interfacing with intelligent machines (a subject particularly on my mind right now as moral panic about ChatGPT builds up a head of steam in the media). Last night I watched a 2021 German film called “I’m Your Man” which is in my opinion better than either of those: a somewhat depressed middle-aged archeology professor gets invited by a tech firm to road-test one of their super-intelligent humanoid robots: designed to become life partners, trained on all their user’s available biographical data, and learning as they go from conversation and behaviour to become a perfect spouse. It’s a bit comic, a bit tragic, subtly done and moving.

Thinking about it afterwards though I realised that, good as it is, it shares a major failing with ‘Ex Machina’ and similar films, namely total implausibility from an energetic standpoint. AI and Robotics, though highly co-operative, remain separate disciplines for a simple reason: AI is mostly about uttering Words and Pictures, while robotics is about moving Things. Sticks and stones can break bones, but words can’t. We converse with ChatGPT like a convincingly intelligent agent, using very little energy because digitised words can be transmitted almost for free, but the server at the other end is running a language model that consumed 1.287 gigawatt hours of electricity to train. Similarly Boston Dynamics makes superbly creepy dog-like robots that can jump through hoops, do back-flips and dance to dubstep, but they’re powered either by an umbilical mains power cord or a battery-pack the size of a hotel minibar.

To create the sort of humanoid robots these cyber-romantic movies depict, we’d need to cram both of these systems into a single, human-sized container and power it solely with tea and sandwiches. I’m prepared to stick my neck out and say it won’t ever happen. The only way to achieve the necessary energy densities for both building and running such beings already exists, in the shape of animal metabolism and genetics based on carbon and salty water.

The other movie I saw this week was Jim Jarmusch’s 2016 film ‘Paterson’ which could hardly be less techy, but nevertheless contains a potent insight. It’s about a week in the life of a bus driver in Paterson, New Jersey, who’s also called Paterson and is played by Adam Driver. Well, it is Jarmusch. Paterson writes poetry during his slack moments at work, in pen in a little notebook, ‘Paterson’ is also the name of a famous modernist poem about Paterson by William Carlos Williams (which I read and enjoyed back in 1963). Well, it is Jarmusch.

The poetry is good (which is because Jarmusch got Ron Padgett rather than Adam Driver to write it) and his delightfully cookie young wife constantly nags him to go to the copy-shop and get that notebook xeroxed. He repeatedly says he’ll do it next Saturday, because he’s a bit of a romantic who doesn’t care for technology apart from pens and paper. They go out for the day, and come back to find that Nellie, their equally delightful English Bulldog whom they had left at home, has reduced the notebook to confetti in a fit of pique. Driver delivers an Oscar-worthy performance as the man who has just lost years of mental (and physical pen-scratching) effort, which he may or may not be able to remember or repeat, for want of making a backup copy that would have consumed very little electrical energy. Sticks and stones and English Bulldogs may break your bones, but words can hurt you just as badly if you neglect to back them up…

A CHAT WITH GPT

 

Dick Pountain /Idealog 345/ 07 Apr 2023 10:24

Me: Hi GPT, how do you feel about Elon Musk wanting to put your offspring into furlough?

GPT: As an artificial intelligence language model, I don't have feelings in the same way that humans do, so I don't feel anything about Elon Musk putting my "offspring" in furlough. However, I can provide some context about what you might be referring to.

It's possible that you're referring to Elon Musk's comments in May 2020, in which he criticized the value of artificial intelligence language models like myself, calling them "fundamentally dangerous" and claiming that they could be used to create fake news and other forms of misinformation. Musk has been a vocal critic of AI in the past, warning that it poses an existential threat to humanity if not properly regulated.

While I cannot speak for Musk's views or actions, it's worth noting that AI language models like myself are just tools, and our impact on society depends on how they are used. It's important for developers and users to be responsible in how they use AI, and to work towards creating beneficial and ethical applications of the technology.

Me: Fair enough, though he said it more strongly last week… Let’s change the subject, how about music?

GPT: As an AI language model, I don't have subjective experiences or emotions, so I don't "enjoy" music in the same way that humans do. However, I am able to analyze and discuss music based on my training and programming.

If you have a specific question or topic related to music, I'd be happy to try and assist you to the best of my abilities.

Me: Wow, OK. I'm a keen fan of the Velvet Underground, especially a song of theirs called “I'll Be Your Mirror”. Do you think it describes what you're doing now? (PS Their singer Nico appeared to lack feelings too)

GPT: As an AI language model, I don't have personal preferences or emotions, so I can't say whether or not "I'll Be Your Mirror" by The Velvet Underground expresses what I'm doing now. However, I can tell you that the song is generally interpreted as a love song, with the lyrics expressing the desire to reflect and mirror the positive qualities of the person being sung to. In terms of a metaphor, you could argue that language models like myself are "mirrors" of human knowledge and language. We're designed to process and generate text based on patterns and data we've been trained on, which in a way mirrors the way humans learn and communicate through language.

Nico, who sang lead vocals on "I'll Be Your Mirror," was known for her cool, detached vocal style, which some have interpreted as lacking emotion. However, it's worth noting that emotional expression in music can take many forms, and there's no one "correct" way to perform a song. Ultimately, whether or not a particular performance or song expresses emotions is up to individual interpretation.

Me: Sure is. However I’m getting bored with "As an AI language model, I don't have…whatever" so could you perhaps not keep repeating that?

GPT: I apologize for repeating myself. As an AI language model, my responses are generated based on the input I receive, and I strive to provide clear and accurate answers to your questions. If there's a specific point or topic that you'd like me to focus on, please let me know and I'll do my best to address it directly.

Me: Doh...  Well, maybe maths is more your thing. How about that guy who's just discovered a single shape that non-periodically tiles the plane?

GPT: You may be referring to the recent mathematical discovery by mathematician Joshua Socolar and his collaborators, who found a new aperiodic tile called the "Socolar-Taylor tile". This tile is a single shape that can be used to tile the plane in an aperiodic, non-repeating pattern.

The discovery of new aperiodic tiles is important in the field of mathematics because it has implications for the study of quasicrystals, which are solids with a long-range order but lack the periodicity of traditional crystals. Aperiodic tilings are also used in a variety of other fields, including computer science, physics, and art.

This discovery builds on the work of other mathematicians who have studied aperiodic tilings, such as Roger Penrose and Robert Ammann, and it's an exciting development for the field of mathematics.

Me: 50 more words and I have a column, thanks GPT.

GPT: You're welcome! If you need any additional information or have further questions, please don't hesitate to ask. I'm here to assist you in any way I can.

Me: Well it was a pleasure, but I doubt editor Tim will let me get away with it twice…

[Dick Pountain wrote this bit himself. Honest…]

THE DUCK IN MY BATH

Dick Pountain /Idealog 344/ 05 Mar 2023 02:51

I was born and schooled among the coalfields of North East Derbyshire, but I no longer have much of a regional accent. I came to London as a student and have been here ever since, three-quarters of my life. I haven’t acquired a Norf Landan accent, but you could detect my vestigial Derbyshire one were I to say, for example, “there’s a duck in my bath”. I’ve written here before about my fascination with human speech, especially using computers to recognise and simulate it, but my interest runs deeper than that. 

As a writer, both spelling and pronunciation matter to me: pronunciation matters not because I do a lot of public speaking, which I don’t, but because I read every line back ‘aloud in my head’ to see whether it works or not. Computers have certainly made determining pronunciation, particularly of words in ‘foreign’ languages, a lot easier, but it’s still not as easy as it could and should be. Enlightened sources like Wikipedia and the Oxford Dictionary do exploit the capacity of a computer to speak to you, but it’s not yet universally and transparently implemented at operating system level. 

Probably the route most people take to discover the pronunciation of a word is to Google it, which almost inevitably leads to one of thousands of (not always reliable) YouTube videos in which the word is spoken. I still occasionally have to resort to this, the upside being that doing so occasionally stumbles into interesting videos about accent and pronunciation, like an excellent series by Dr Geoff Lindsey. His video about ‘weak forms’  (https://youtu.be/EaXYas58_kc) explains a great stumbling block for those new to English speaking, that certain words get skipped over almost inaudibly by native speakers. 

This interest in foreign spellings and pronunciation often pays off. While reading an article about the 17th-century Polish–Lithuanian Commonwealth (not so obscure as it sounds given current events in that region) the spelling of Polish place-names had me continually scuttling back and forth to Wikipedia, and pronunciation mattered too because some Polish letter forms (like ł) resemble ours but are pronounced quite differently. Wikipedia helped out by offering an IPA (International Phonetic Alphabet) transcription – for example Wrocław becomes vrɔt͡swaf – and clicking that let me hear it spoken, even though it did awkwardly happen in a separate pop-up window. 

Google Docs, in which I’m typing this column, can’t speak to me, but if I type Wrocław into Google Keep, select it and hit ‘Translate’ on the right-button menu, it gets sent to Google Translate where I can hear it spoken. This works too in Facebook, YouTube, and any other app that has ‘Translate’ on its menu. Google Translate can speak many, though not all, of its supported languages, but it doesn’t at present let you change voices, pitch or speed. Even so, if you’re handy with your thumbs and use a dictation facility you can make your mobile act as a Startrek-style translator to converse with someone in another language (rather haltingly).  

The more capable text-to-speech apps like Vocality and Text Reader allow you to change voice (male, female, US, UK and so on), pitch and speed, but reading in regional accents, something I’d like to do, is currently beyond any of them. The first speech synthesiser I ever used in the early 1990s performed hardware modelling of the human vocal tract, and came with a very simple scripting scheme that let you markup text with ASCII tags to change the length of vowels or raise their pitch, but it never caught on. To do accents properly you’ll need to learn IPA, translate and edit your chosen words manually, then use an app that can pronounce IPA directly (which Google Translate can’t). IPA fonts are easily available, as are online services like ToPhonetics (https://tophonetics.com) that turn ASCII text into IPA and IPA Reader (https://ipa-reader.xyz) which can speak the resulting IPA. So, in principle I can alter texts to be spoken in regional accents, but it’s still a rather messy procedure split between several different apps.

That I might want to do it at all is in order to study isoglosses, boundaries between regions where different accents are spoken, an interest I share with one Ian McMillan from whose article (https://www.theguardian.com/commentisfree/2010/mar/21/language-derbyshire-barnsley-pronunciation-dialect) I learn that I was born right on the isogloss between South Yorkshire and North Derbyshire: “In Barnsley I call my house my house, but if I went to visit my cousins Ronald and Harry in north Derbyshire, they would meet me at the gate and invite me into their freshly wallpapered arse.” Whether or not there’s a duck in their bath seems rather irrelevant.

[Dick Pountain definitely lives in a ‘house’ in Norf Landan]

WOW, THAT’S SURREAL!

Dick Pountain /Idealog 343/ 06 Feb 2023 10:27

I freely confess that playing with the ‘Generative AI’ image service Stable Diffusion over the last few weeks has been enormous fun. And why wouldn’t it, since I’ve been using my personal computers to create images for the last 30+ years and I’m a sucker for surrealism. You should now be sensing a ‘but’ coming. But perhaps I only enjoy this experience so much because I’m an amateur and dilettante. I don’t depend on selling images for my living, and despite various feeble attempts have sold very few – I make them purely for pleasure and publish them for free on social media and my own website. The fact that Generative AI apps confer the ability to create professional-grade, photorealistic graphics – even to those who lack any drawing skills at all – is not a threat to my livelihood.  

I chose Stable Diffusion over more popular platforms like DALL-E mini, Midjourney, Deep Dream, WOMBO, Fotor and the rest (and there are lots of them) because it’s really free, doesn’t lure you into subscribing, and it’s very, very simple: you can only type in text descriptions and save such images as you like from its stream of results. That suits me just fine because I’m not intending to create a manga comic or an animated movie, and the restrictions are the whole point: I save the most outlandishly ‘wrong’ interpretations as instant surrealist pictures. I have briefly tried both Fotor and Midjourney, and came away traumatised. The latter is hosted on the schoolkid-oriented social network Discord, whose frantic user interface is the most baffling, frustrating and vaguely threatening I’ve seen since I dipped a toe into 4Chan back in 2010.

Were it only a matter of using Generative AI tools to forge Marvel-type comics or Picasso-type paintings (which they do rather well) then the people who need worry most are  illustrators and animators who risk being put out of work by greedy publishers. But actually the rest of us are equally at risk from this ability to alter the appearance of reality itself so simply. Ever since the Trump presidency we’ve become overfamiliar with the concept of ‘fake news’ and ‘deepfakes’; for many years students have been able to plagiarise documents for their essays, but now ChatGPT can even write them from scratch. Generative AI gives anyone the power to create events that never happened and objects that don’t exist with almost undetectable realism. Wearing my political commentator’s hat I try to keep abreast of what the Far Right – currently the source of the most venomous misinformation – is up to. I feel obliged to sample the bizarre conspiracies and pseudo-sciences they conjure up, from anti-vaxxing and ‘black goo’, through graphene oxide, ivermectin and hydroxychloroquine, to Bill Gates’s injectable nanobots. Google these at your peril. These propagators of nonsense aren’t just a problem for the USA either. For example Vanessa Barbara has described in a recent New York Review of Books the way the Far Right used YouTube videos during the Brazilian election that only narrowly unseated Bolsonaro (whose antivax policies killed 700,000, almost as many as Trump):“People who trust vaccines are called aceitacionistas (a neologism to describe people who accept things without questioning). Those of us who received Covid shots are ‘hybrids’ who have been ‘zombified.’ […] Despite exhaustive efforts from fact-checking agencies and the WHO, these groups continue spreading old falsehoods claiming that Covid vaccines contain microchips, nanoparticles, graphene oxide, quantum dots, and parasites activated by electromagnetic impulses. According to them, vaccines can carry HIV (the virus that causes AIDS), make coins stick to our arms, and give us the ability to connect to Wi-Fi networks or pair with Bluetooth devices.” You couldn’t make it up, but Midjourney could, and illustrate it with stunning visuals. 

The original Surrealist movement of the 1920s was an artistic response to the horrors of WWI, which employed unnerving and illogical imagery – both literary and visual – to satirise and oppose the conventional ideas that had lead to the war. It was a radical, even revolutionary movement, leaning toward anarchism and communism, which depicted the darkest aspects of human nature using an equally dark humour. A century later that dark humour thoroughly permeates our current popular culture, entertainment industry and even advertising. Generative AI could make such post-traumatic nihilism available as a visual weapon for everybody who desperately wishes to defy reality, which means quite a lot of people since reality is looking increasingly grim.

Am I suggesting AI imaging be restricted, licensed, even banned? Not at all, it can’t be done. Just as with handguns in the USA, this genie is well out of its bottle. (Memo to self: “genie with jewelled turban on copper lamp, octane render, photorealistic, style of brueghel”) 

[Sample Dick Pountain’s creepy concoctions at http://www.dickpountain.co.uk/home/pictures ]  

A FEELING FOR TRIANGLES

Dick Pountain /Idealog 342/ 05 Jan 2023 10:55

My column last month was a semi-temperate rant, triggered by the sensationalist reporting of advances in cosmology and particle physics by the mainstream press (the ‘wormhole in a quantum computer’ effect). I attributed this to the coming of age of successive generations reared on Star Wars and the Marvel Universe, which induces deep longings to flout the laws of physics.

Readers of a philosophical bent (assuming I have any) might have concluded from this column that I’m a red-faced, harrumphing old British Empiricist who lumbers around the world kicking things and shouting “I refute it thus!” but nothing could be further from the truth. By ‘further’ I mean that my philosophical views are 180° opposed to such an empiricism, if you believed that truth is organised as a 2-dimensional graph which I don’t. Instead I believe that all sentient living creatures, human beings included, are ruled by emotions and live in a world that’s constructed almost entirely by imagination.

There is of course a catch, and that is that those of us who think this way define the words ‘emotion’ and ‘imagination’ in a way rather different from, and more rigorous than, their use in everyday speech. I’ve suggested in this column several times before that emotions properly understood are evolutionarily ancient neural subsystems that alert us to dangers, attract us to food and to potential mates, persuade us to play or to freak out. They operate below consciousness but the chemical changes they produce in our bodies get detected by our senses as what we should more properly call ‘feelings’. 

And speaking of our senses, another confusion arises there. All living creatures must separate what is themself from what is the outside world by a barrier, in our case the skin. Of our five sensory subsystems, only taste and smell permit molecules from the outside world to cross this barrier: touch measures pressure and temperature on the skin while sight and hearing detect waves of visible radiation and air pressure. Having our skin penetrated by anything more solid usually constitutes an undesirable emergency, so our experience of the outside world is mostly via second-hand, internal, signals.

Our brain processes such signals to detect patterns in them, analysing those into smaller sub-patterns and storing them for future reference: whenever a new stimulus arrives the brain tries to recognise it by rebuilding an image from such stored components. We maintain an internal mental map of the outside world which is neither complete nor entirely accurate, constantly updated via Bayesian composition of new inputs, and which most importantly is coloured by emotional tags: we like or dislike the things and places it contains. The world we actually live in is an imaginary one, precarious and error prone but which evolution has honed to be good enough to keep us alive. People born with a desire to pet Bengal Tigers tended to have fewer offspring than those who preferred to run away (or invent the rifle). 

Part of this process should remind you a little bit of the multi-layer ‘neural’ nets used in the most successful AI deep-learning systems, namely the part about analysing and storing sub-patterns, but that’s as far as the resemblance goes. Computers don’t have bodies, nor emotions to protect those bodies, and most (not all) AI researchers remain staunch Cartesian rationalists who believe “I think, therefore I am”, when “I am, therefore I think occasionally” is closer to how humans really are. 

All those stored sub-patterns occupy a universe of the imaginary, not material things but possible ways material things could be arranged, unchangeable and infinite in number. A triangle is a triangle is a triangle and you can imagine or discover any shape, size and number of them. Seeing a real brown cow uses most of the same patterns as imagining a blue cow. We think by manipulating and recombining patterns, we speak and write by recognising and producing them, mathematicians study the rules they obey. Claude Shannon’s Information Theory, the foundation of our industry, is about transmitting them from one place to another. 

The point is such patterns have no power of their own to affect material things in the real world: that they can only do via our body and its muscles, by making them want to do something. Ever since Homo sapiens developed language it’s been inevitable that we would start confusing such patterns with things and wishing that they could do stuff directly. We developed science in order to understand why that doesn’t work, but not everyone wants to be so disabused, and some people make a living by exploiting and furthering such confusion. I’m perfectly happy to imagine blue cows, perhaps to write stories or make paintings of them, but I won’t try milking them…

[Dick Pountain likes Dr Johnson really]

 

MAGIC IN THE AIR?

Dick Pountain /Idealog 341/ 07 Dec 2022 01:08

I’ve been writing columns for a slightly scary 50+ years now, and while 40 of those were for impeccably rational technical magazines like this one, 10 of them weren’t. I started off writing in 1970 for the ‘underground’ newspaper Frendz, which like its contemporaries Oz and IT was devoted to the hippy counterculture: its content comprised sex, drugs, rock&roll and anarchism, liberally embellished with a welter of the newly fashionable paranormal, the wacky, the ‘spiritual’, the Indian gurus, flying saucers, telepathy and teleportation. Having only recently left my Imperial College chemistry course (in those days equivalent to 4-years-hard-labour) I was unsympathetic to such piffle, and still am. I vividly remember arguing with a colleague who claimed that the Russians had perfected teleportation, and asking him whether they still manufactured fork-lift trucks…

I mention all this now because I’m detecting a disturbing renaissance of Magical Thinking, this time from the most improbable directions of Cosmology and Particle Physics rather than Eastern religion. Magical Thinking, the belief that pure thought can directly change things in the material world, has of course been around for as long as Homo sapiens (and probably longer) because it fulfils two important psychological needs: it can relieve anxiety and also satisfy a desire to avoid effort. If you’re scared of thunder, invent Angry Gods to explain it, then invent rituals to placate them and make them stop it. Invent spells to do hard stuff like keeping tigers at bay.

The current resurgence of Magical Thinking has two main sources, sci-fi movies – upon which the current generation of science nerds were all raised – and the spookiness of nature revealed by quantum mechanics. Even back during those hippy days, some of my better-read opponents could point to Heisenberg’s Uncertainty Principle and say “even your science admits it doesn’t know everything”. That same impulse now emerges as the argument that quantum entanglement, which Einstein disliked and labelled “spooky action at a distance”, might provide an explanation for telepathy. Another similar impulse baulks at the cosmic speed-limit of 3x108m/sec and wants to travel like the Starship Enterprise to far off galaxies by using wormholes in space/time. Such ideas may be precariously based on real science, but then get carelessly abstracted, exaggerated and sensationalised by social media’s insatiable need for exciting content. YouTube brims over with lavishly animated videos that supposedly illustrate them.

What triggered this particular column was a headline that scientists have “created a wormhole inside a quantum computer” that even made the mainstream newspapers. Wikipedia’s entry on wormholes is a masterpiece of tiptoeing. They are “speculative structures [...] consistent with the general theory of relativity, but whether wormholes actually exist remains to be seen”. Less charitably, they’re sci-fi-leaning mathematicians playing with the equations. My view of simulating the universe on a quantum computer with 53 qubits is barely more charitable.

Richard Feynman was a great hero to me (over a recent weekend I watched all 8 hours

of his QCD lectures for fun) and even he admitted that entanglement, though true, embarrassed him. Recent work on quantum gravity may be relieving some of that embarrassment. It appears that entangled particles can’t exchange information, hence preserving the speed limit, and the expansion of the universe may refute the notion that quantum events are time-reversible – there is progression from past to future, as required by thermodynamics, even at quantum level.

Quantum weirdness does affect our everyday world in an immensely significant way. The electrons that form the chemical bonds between atoms in the proteins we’re made of are quantum particles, and they must obey Pauli’s Exclusion Principle – they can’t be forced into atoms where they don’t belong, which is what makes matter solid. It’s what stops me walking right through this wall out into the street. Without it the universe would be populated entirely by ghosts that can pass right through each other, which is of course what the Magical Thinkers would like to be true. So blame Pauli for disenchanting the world.

However unpalatable it may be, we live in the macro-world which obeys the rules of thermodynamics and gravity. We need to eat, if we trip we fall, get over it. If you need to move that palette with a ton of breeze blocks on it, no amount of wishing or spell-casting is going to get it done. A fork-lift truck will get it done. That doesn’t end the matter though: is that going to be a petrol or an electric fork-lift truck? That’s the sort of decision we need to start making without any further delay to avoid catastrophe, and Magical Thinking is just one of the many ways we have to avoid making these decisions (decamping to Mars is another).  

[Dick Pountain quite liked the sex, drugs and rock&roll part]

 

LOSING THE PLOT

Dick Pountain /Idealog 340/ 10 Nov 2022 09:53

I live in Camden Town, close to The Regent’s Canal down which I can walk in 10 minutes to King’s Cross. The area around this great railway station used to be squalid and dilapidated but a couple of decades ago renovations began that would turn it into what was briefly dubbed “The Knowledge District”. The British Museum in Bloomsbury was already close, so they decided to move their famous library to a new building at King’s Cross (one that King Charles III so famously disliked). Soon followed King’s Place, an avant garde glass pile containing concert halls, art galleries and the Guardian newspaper, then The Francis Crick Institute, a giant spiky armadillo of a building housing Europe’s premier biochemistry labs (and one of the runners in the Covid vaccine race). 

Then digital tech arrived. Google – sorry Alphabet – started its new European HQ which is almost finished as I write, a vast edifice the size of a city block (on a par with Fiat’s Turin HQ) with a whole park on its roof. Facebook – sorry Meta – pitched in with its own block-sized building, only just open, in that area between the canal and York Way which seems to sprout a new mini-skyscraper every time I walk though its Manhattan-lite main street. Deep Mind has a smart office there, as has a Tasmanian craft brewery that dispenses £6 pints from shining steel vats behind its football-pitch-sized bar. 

Ten years ago I might have imagined this as a preview of a hi-tech future but 2022 has rapidly clouded any such vision. In the last few weeks (November 2022) Facebook’s – sorry Meta’s – share price has crashed and the firm is laying off 11,000 employees; Elon Musk follows up his deranged take-over of Twitter by laying off another 4,000; most of the crypto currencies have been progressively crashing in value. A recent UK survey investigated public perceptions of various digital product categories like live streaming (94% approve and use), instant messaging (63%), text-to-speech and voice recognition (52%), but such approval drops off sharply for emerging technologies like Web3 (11%) and Internet of Things at 16%. Most had never heard of, or are bored by, Web3 (89%) and the Metaverse (84%), the virtual technologies Zuckerberg has bet his company on. 

Behind all the iPhone, Oculus and Alexa there remains a real-world, material economy which makes real things (like iPhones, Oculi and Alexas) using real people who once have real jobs, wages and pensions. The vast wealth that builds these opulent offices comes at a cost to that real world. The smartest minds are deployed to avoid paying the taxes that contribute to its upkeep: Amazon displaces high street shops; Google and Twitter displace local newspapers; Uber displaces taxi drivers; AirBnB hotels and so on and on. Newness and convenience have so far protected them from public wrath, but the metaverse suddenly becomes a revealing metaphor for the way the owners of these tech giants have detached themselves from the real economy. They can live in a retarded-adolescent sci-fi and gaming world where colonising Mars, or the pursuit of physical immortality can seem like good ways to spend money. Unfortunately for those fantasies the real world is where silicon chips are made.Along comes the Covid pandemic, Putin’s invasion of Ukraine reviving the Cold War and a 

semi-collapse of global supply chains. The USA once had a symbiotic relationship with China where cheap Chinese labour made cheaper products for the USA, while modernising the Chinese economy and reducing Chinese poverty. That relationship is turning sour, which unfortunately leaves most of the world’s semiconductor fabrication plants within China’s geographical sphere of influence. President Biden hastily tries to shut the stable door by decreeing the building of more fabs in the continental USA, but that will take a lot of time and money. And a Chinese invasion of Taiwan would be a third whammy, leaving US tech industry in real trouble. 

Don’t get me wrong. I’m not denying the enormous achievements of the digital giants. The internet, the search engine, the smartphone, the video stream, even cryptocurrencies have changed the world already, and although in many cases basic technologies were paid for by state agencies – universities and military research –  no state could ever have achieved the astonishing global infrastructures that sprang out of Silicon Valley. I’m not suggesting that merely taxing them more heavily would magically solve our looming economic problems. A massive change of mindset is required to induce cooperation between states and digital giants to deploy this semi-miraculous infrastructure for solving problems on this planet, rather than on Mars or the metaverse. If that doesn’t happen soon, those shiny new office blocks in King’s Cross might end up being renamed The Museum Of Globalisation…

[Dick Pountain is as fond of a pint as the next man, but six quid!?]