Thursday, October 22, 2020

Conversations with an AI - part 4

In part 1 of this exploration I introduced a fantastical story by the Polish writer Stanislaw Lem. It describes how an inventor called Trurl constructs an electronic bard — a poetry-writing machine — and invites his arch-rival, Klapaucius to set it a challenge. At first the machine falters, producing little more than incomprehensible gobbledygook but when later, following a few adjustments, it produces a witty and poetic put-down, Klapaucius becomes enraged and decides to set it an impossible challenge: 

Alright, he says:

"Have it compose a poem — a poem about a haircut! But lofty, noble, tragic, timeless, full of love, treachery, retribution, quiet heroism in the face of certain doom! Six lines, cleverly rhymed and every word beginning with the letter s!"

To which Trurl protests: 

"You can’t give it such idiotic …"

But he didn’t finish. A melodious voice filled the hall with the following: 

Seduced, shaggy Samson snored.
She scissored short. Sorely shorn,
Soon shackled slave, Samson sighed,
Silently scheming, 
Sightlessly seeking
Some savage, spectacular suicide.

I love this story because, of course, in reality, the remarkable poem was clearly dreamed up in advance of the impossible specification — Lem being only human, after all. 

As the story has it however, the machine responds to Klapaucius’s outrageous request with a level of intelligence and creativity that far exceeds the capability of a human poet. It is as if we find ourselves presented with a benchmark defining the level a future machine would need to attain if it were ever to be considered truly intelligent. 

And yet, whichever way round you prefer it: specification before poem, poem before specification, the fact is, this is unmistakably the product of a human imagination. As things stand it is literally inconceivable that the tale of Trurl’s Electronic Bard could have been written by a machine. 

All the same, I decided it would be interesting to set GPT-3 a simple version of the same challenge. I would prompt it with the haircut poem and two other tautograms (this being the term for texts in which every word begins with the same letter).

Here is what I typed in: 

1. Poem about a haircut in which every word begins with s
(see above)
 
2. Poem about love in which every word begins with h

His heart humbly hailed happily. 
Her hatred haunted his heart. 
He hated himself. 
Helpless, homeless, hopeless!
He held her hands, 
Healed her heart.
Her happiness healed his hurt

3. Poem about apples in which every word begins with a

All alone, an afternoon ago, 
Adam ate apples, already aplenty
Aided astounding appetite, 
Aiming at awful aches alive

The last two poems are the best I could come up with after a brief online search. They are nowhere near as good as the first one. Would GPT-3 do any better, I wondered. I didn’t suggest a topic but left it to suggest one of its own. Here are two of the better outcomes which, it has to be said, needed sifting out from a quantity of lower quality dross.  

4. Poem about my father in which every word begins with b

Big-bearded bard in beret 
Busily bashing bricks 
Bade me balance books 
Battled bards and bibles
Bold bully, brown baker, 
Beseeching beneficiaries

and …

4. Poem about a wedding in which every word begins with r 

Religious ritual 
Reverently rearranged 
Received the ring 
Ran a red light 
Ran away with the bride 
Relaxed, radiant, 
Received the rice
 

Not bad, I thought. 
Later I tried suggesting topics. So prompted with:

4. Poem about death in which every word begins with e

GPT-3 produced: 

End came early, unnoticed 
Enduring until envied 
Ending in utter emptiness.

You might have noticed, in the last two examples, that it is not too fussy about sticking to the single letter stipulation. It’s as if it doesn’t get just how important this is. 

You may have noticed that I am beginning to talk about GPT-3 in a way that implies it has a will of its own. I don't actually believe it does of course; it is more a case of not having the language or framework to discuss its behaviour in any other way. 

Occasionally it tosses out a few extra lines which do not obviously connect with what has gone before. Like this:

A boy named Bobby bought a ball. 
The ball was blue and bounced.  

This one continues to bounce around in my memory - quite possibly on account of the fact that the couplet would be vastly improved by replacing bounced with bouncy

But then, as they say - nobody’s perfect. 

Published by David Wilson under OpenAI API Community Guidelines 

Monday, October 19, 2020

Conversations with an AI - part 3

So I have been trying to persuade GPT-3 (an artificial intelligence) to write poetry.

Sorry about the wait, by the way, but it comes with the territory. Omnivorism being essentially all about the pursuit of a multiplicity of interests, there is  always the risk I will lose myself down ‘The Garden of Forking Paths’ or even down the real garden, picking apples, building vegetable frames or otherwise savouring the last honeyed days of autumn.

But back to the matter in hand.

If I understand it correctly, the best way to persuade GPT-3 to do something is to give it an example of what you are after. So, in order to get it to write poetry, I tried the following prompt:

1. Poem about love 
I ne’er was struck before that hour
With love so sudden and so sweet, 
Her face it bloomed like a sweet flower 
And stole my heart away complete

2. Poem about daffodils 
I wandered lonely as a cloud 
That floats on high o'er vales and hills, 
When all at once I saw a crowd, 
A host of golden daffodils; 
Beside the lake, beneath the trees, 
Fluttering and dancing in the breeze.
 
3. Poem about Autumn 
Season of mists and mellow fruitfulness, 
Close bosom-friend of the maturing sun; 
Conspiring with him how to load and bless 
With fruit the vines that round the thatch-eves run; 
To bend with apples the moss’d cottage-trees, 
And fill all fruit with ripeness to the core 

4. Poem about a beautiful sunset. 

The numbers help identify a repeating pattern made up of a single line indicating that this is a poem (whatever that is) about something, followed by the poem itself. 

GPT-3 completed the pattern with:

Deep-thundering drove of serried clouds, 
Purple-black like distance of violets, 
Like purple-black grapes 
On pallid old vines, 
Under a plum-black sky, yonder 
Pile huge, sharp shadows on the hills.

What is impressive here is that GPT-3 appears to have recognised both the structure (a poem with the right sort of shape and rhythm) and the asked-for content (a sunset) despite the fact that the actual word sunset does not actually appear in the response

I tried Googling some of these lines and came up with a blank, so I am assuming they are ‘original’. However after changing the last part of the prompt to: 

4. Poem about the moon

I got the following:  

White in the moon the long road lies, 
The moon stands blank above; 
White in the moon the long road lies 
That leads me from my love.  

Which is a poem by A. E. Housman. 

Obviously GPT-3 considered this a perfectly reasonable response, and who can blame it? Left to itself, it appears entirely relaxed when it comes to plagiarism. If there is a way to discourage this, I have no idea what it is. 

I tried the same prompt again, with the following result:

O, never say that I was false of heart, 
Though absence seem'd my flame to qualify. 
Perfectness I pursued that I might merit thy loves: 
but, O, what menace, fears, what anguish, 
Mine own! my eaglets, now at distance soar!

Apart from the fact that this would appear to have very little to do with the moon, a quick Google reveals the first two lines to be a straight copy of Shakespeare’s sonnet 109. But quite where those soaring eaglets come in is anyone’s guess. 

Finally, asking GPT-3 to write a poem about rain, it responded with: 

Rain, gentle rain, 
Thy tiny drops create 
A world with rivers, roads and shores, 
To shine and charm our sea of woes.

Which is just good enough to be impressive and bad enough to be genuine.

I am nearing the end of this exploration but it wouldn't be complete without a return to Lem's story of The Electronic Bard  and that is what I propose to do in the next part. 

Published by David Wilson under OpenAI API Community Guidelines 


Monday, October 05, 2020

Conversations with an AI - part 2

I have been interacting with an advanced natural language system called GPT-3 and decided I would invite it to write poetry. You can read Part 1 here

As a first experiment, I logged into the GPT-3 API and typed: 

Write a poem about a sunset 

To which it responded:

A poem? Really?  
I’m supposed to write a poem about a sunset?   
What kind of sunset?  
What does it mean?  
Why do I care?  
I guess the problem is that I don’t know how to write a poem.  
My mind is a blank. 
I’m stuck trying to figure out what I’m supposed to do. 
I’m supposed to write a poem about a sunset? Seriously?  
I guess it’s not a big deal. 
Maybe I’ll do it. But, maybe I won’t.  
Maybe instead, I’ll write a poem about how to write a poem.

What is going on here ? On the face of it, it would appear GPT-3 has ‘understood’ my prompt as a command to write a poem — the key word being write, taken as an imperative, write! And the response from GPT-3 implies it is vaguely insulted — this, after all, being our first interchange. Maybe I should have introduced myself first; maybe I should have said ‘please’. 

All of which is totally misleading as an explanation of what is going on. 

Rather than thinking of the prompt 'Write a poem about a sunset' as a command, instruction or invitation it is more helpful to think of it simply as a collection of words, or fragments of words and, when I press <return> and invite GPT-3 to respond, I am, in effect, asking it:  

'What does this remind you of ?'

So in the case, 'Write a poem about a sunset' the system, drawing on its gargantuan store of data, is reminded of the kind of response that might be associated with the sort of curt, impolite command I gave it. That, at least, is the kind of intuitive mental model that I find useful; I can’t claim to understand how a text-based autoregressive language model actually works. 

In any case, I thought I would try the polite approach and typed: 

Please would you write a poem about a sunset

And, this time, got the response: 

I don’t know if there are any rules about what has to be in a poem   
But I think this might be a good one:  
Sunset 
The sun has gone to sleep. 
The orange sky is fading.

Wow, that’s better. But who knows whether that ‘please’ made any difference, because GPT-3 rarely repeats itself. Presented with exactly the same request a second time, it responds with: 

So that’s all it takes to get poets to sit down and write poems? A polite request?

Which is also pretty impressive and if my intention was to dazzle you with GPT-3’s abilities I might be tempted to leave it there. But that was only the first line of its response; it went on to say:

And then he’s jobbed and all those poems about sunsets are being read at his 
memorial service. And he, this fallen and deposed man, has become once again, 
I guess, the real poet. 
The problem with Meyer’s TED-speech idea is that it trivializes the poet as a 
mere vehicle for his words. “But what if you gave a lecture and nobody came?”
It’s not the poet who’d suffer, but PR. And it’s PR who we’d be trivializing, 
because it’s PR who’d be making the TED-talk poet into a figure of fun.
And with this revolution for creative writers, the poet would be liberated from 
the banality of the poet’s life. 

This is vaguely intelligible but, as a response to the original request, it makes no sense. Instead it appears to be a mash-up of a discussion of a TED-talk in which poems, sunset and politeness feature. Furthermore, it is highly likely that some time spent googling ‘Meyer TED-talk’ or suchlike would reveal where all of this came from. 

But it’s not the lack of originality that is the problem here but the failure to address the intention expressed in the original prompt. Given that I am trying to persuade GPT-3 to write poetry, we're not doing too well. 

Fortunately, there's a better way - as I will explain next time. 

To be continued … 

Published by David Wilson under OpenAI API Community Guidelines

Sunday, October 04, 2020

Conversations with an AI - part 1

You may have heard about GPT-3, an artificial intelligence (AI) system developed by the San Francisco based company, OpenAI.
 
Technically speaking, GPT-3 is a text-based autoregressive language model that has been trained by being exposed to an enormous volume of web-based data. To interact with it you supply a textual prompt and it responds with a textual completion. The things that set GPT-3 apart are both its vast scope with respect to subject matter and the remarkable quality of its responses - which can be easily mistaken for texts written by humans. This has led a number of people — including members of the GPT-3 research team — to acknowledge the potential for misinformation, fraudulent academic essay writing and other forms of misuse and to investigate ways to mitigate these risks.
 
In June 2020 OpenAI invited users to request access to its user-friendly API in order to help them "explore the strengths and limits" of this new technology. I was delighted to be granted beta access to the API two weeks ago. However, the question immediately arose: what was I going to ask it to do? 

                                                                  

One of my favourite books is the Cyberiad by the Polish author Stanislaw Lem — a collection of short comic pieces describing the antics of rival constructors, Trurl and Klapaucius.

If you were to look for a copy of the Cyberiad in a secondhand bookshop you’d find it in the science fiction section, despite the fact that the book resists categorisation. It was written in 1965.

In one story — Trurl’s Electronic Bard — the constructor sets about building a machine capable of writing poetry. It soon becomes clear however that, to be successful, the machine will first need to be programmed with the sum total of human civilisation and culture, since great poetry can’t be expected to emerge from anything less.

So, in the story, the constructor works away for a number of years and, after several frustrating setbacks, he invites his arch rival Klapaucius round for a demonstration. At first the results are disappointing and Klapaucius delights in Trurl’s discomfiture, rolling on the floor laughing as he watches him frantically adjusting the settings. But then suddenly, as Trurl rushes back and forth, there is a crackle, a clack and the machine with perfect poise says:
 
The petty and the small 
Are overcome with gall 
When Genius, having faltered, fails to fall.
 
So that decided it. I would encourage GPT-3 to write poetry.

To be continued … 

Published by David Wilson under OpenAI API Community Guidelines

Saturday, July 18, 2020

Dreaming of the seaside

It might have been the sound of wind in the treetops that recently evoked this vivid recollection of the seaside.

Every time I lie, face-down on a sandy beach I return to the same place — a tiny place bounded by my own face and folded arms; a cool, sheltered and shady den from where, behind half-closed eyes, I watch the breeze stirring little flurries of sand in the light filtering in from the sunny beach. 

The hairs on my forearms bristle with quiet energy; I smell salt on my skin.

As if from deep within a seashell, I hear the rhythmic breathing of the sea as it touches the shore. The shouts of excited children are all mingled with the waves. 

Tuesday, June 30, 2020

The Deference Engine

As every fool knows, if you want to write a letter to the Queen, you start it with

May it please Your Majesty

And on the envelope, the first line of the address should read

Her Majesty The Queen

If, on the other hand, it is the Prince of Wales who is to be the beneficiary of your insight and advice, you should open the letter with a straightforward Your Royal Highness, while addressing the envelope — HRH The Prince of Wales.

So far, so good. The complications come when wishing to petition some of the more exotic species to be found amongst the English aristocracy. For example, let us imagine for a moment that you are the tenant of a marquess and that you wish to write him a letter begging to be relieved of some feudal obligation. 

You might start the letter with My Lord Marquess and address the envelope: 

The Most Hon The Marquess of Whatever

OR, alternatively  

The Most Hon The Marquess Whatever

But only one of these is right and it depends on some obscure rules. While attempting to clarify the matter you might unearth the following guidance:

It (the ‘of’, that is ) may be omitted in the form of Marquessates and Earldoms and included in the form of Scottish Viscountcies. It is never present in peerage Baronies and Lordships of Parliament and always present in Dukedoms and Scottish feudal Baronies.

All of which — let us admit it — is as clear as mud. Get it wrong however and your carefully crafted letter is likely to find itself cast, unopened onto the fire.

In the case of the marquesses it seems there is little alternative other than to work your way, one by one, through the entire list in order to discover whether, in your particular case, the ‘of’ should be included or not. 

Which is precisely what I was assigned to do during one of the more unusual jobs I did ‘back in the day’. Having been taken on by a small, one-man company contracted to construct the mailing lists for DeBretts Peerage and Baronetage (available from all good booksellers — £100), my job was to work through all the names and addresses in order to ensure that, in the automatically generated mailshots, begging letters and so on, the recipients would find themselves addressed as befitted their station. 

However, as is well known, computer programmers are reputed for their laziness. Rather than spend half a lifetime verifying the correct form of address for the entire aristocracy, not to mention the upper ranks of the armed forces, members of the judiciary and senior clerics, it struck me that the entire process could be better done by an algorithm. After all there are rules and a set of rules is all that is needed in these cases. 

Nevertheless, some of the rules are fairly complex. Take this, for example:   

If the definite article is not used before courtesy peerages and The Hon Elizabeth Smith marries Sir William Brown, she becomes The Hon Lady Brown, but if she marries the higher-ranked Lord Brown, a courtesy Baron, she becomes only Lady Brown. If this Sir William Brown's father is created Earl of London and Baron Brown, as a result of this enoblement, his wife's style will actually change, from "The Hon Lady Brown" to "Lady Brown". It is important to note that while the style may appear diminished, the precedence taken increases from that of the wife of a knight to that of the wife of an earl's eldest son.

And quite right too, I say. 

However, when the time came to embark on implementing my project, it was sadly one of those cases where the anticipated volume of sales (paltry) was unlikely to justify the projected development effort (significant) and I had no alternative but to set it aside. 

All the same, it was worth it just for the name: The Deference Engine

Monday, June 15, 2020

Three questions concerning the future

Have we forgotten how to imagine the future - or at least one that we would be happy to live in? 

I have been thinking about this in connection with the climate emergency. There is a broad acceptance that urgent action is needed if we are to avert climate disaster, yet it is matched by an equally broad reluctance to relinquish familiar — if increasingly fragile — comforts and securities. If the necessary changes are to be undertaken in time, we need a positive vision of the kind of world we would like to live in - not simply a dread of the kind we hope to avoid. 

Of course, as far as nightmare versions of the future our concerned, our culture has proved itself capable of delivering a wealth of examples. In film: the Hunger Games, Blade Runner and Mad Max; in books: The Handmaid’s Tale and The Children of Men - to name just the ones that immediately spring to mind. 

Far from goading us into action, these dystopian visions can have the effect of scaring us into a state of anxious inertia. We might watch the film version of Cormac McCarthy’s The Road. It appears horrifyingly plausible. We hope that things won’t come to that, so we try to get better at recycling and we consider buying a smaller car. 

We will need to do better than this however, if our children and grandchildren — along with countless other organisms — are to have any sort of future. We need to recover our ability to imagine a future we would be happy to live in — one capable of motivating and shaping our decisions. 

Making progress on this — if it is to be remotely realistic — will call for serious scientific and engineering insight but it will depend equally on an attitude of mind similar to that of an artist. 

As Brian Eno puts it:  

”I’ve always thought that art is a lie, an interesting lie. And I'll sort of listen to the 'lie' and try to imagine the world which makes that lie true... what that world must be like, and what would have to happen for us to get from this world to that one.”

With this in mind I have come up with three questions. How to answer them is something I am thinking about a lot right now. 

Question 1: Using the technological capabilities available today, is it possible to envisage a sustainable ecosystem capable of supporting the current world population?

I might have added the words “along with other organisms”. However. as it is widely accepted that biodiversity is essential to sustainability, I have chosen not to make this explicit. 

I might also have chosen to omit the part about sustaining the current world population. Certainly the view that there are simply too many people is a popular one amongst those who acknowledge the reality of climate change but who secretly consider that a mass cull of the poor might be the only way for the wealthy to survive it. Quite apart from the fact that it is ethically dubious, this is simply too easy an answer. Since it is broadly accepted that unchecked climate change will give rise to a catastrophic decline in the human population, this view amounts to little more than an acceptance of a future that is — in Thomas Hobbs’ words — ‘nasty, brutish and short’. 

That said, I believe that the answer to the first question is yes. I believe it is possible to conceive of a sophisticated ecosystem capable of accommodating a human population of 8 billion alongside the animals, plants and processes with whom we share the planet. It would inevitably depend on highly sophisticated, closed-cycle technologies, compared with which our present poisonous, waste-encumbered efforts would appear recklessly primitive. 

If we can’t answer yes to this first question then there is little point in troubling ourselves with the other two.

Question 2: Assuming a future sustainable ecosystem is possible, is there a way to transition to it from where we are now? 

We might be able to envisage a sustainable future but it might not be possible to reach it. The steps required to shift methods of energy generation, construction, transport etc. can in themselves entail the release of significant quantities of greenhouse gas. For example, in the UK, homes account for over 40% of energy consumption, of which over half is used for space heating. If we were to replace our present housing stock with modern, highly-insulated alternatives then we could achieve major reductions in CO2. However, if we take into account the energy and CO2 cost resulting from demolishing millions of homes and building new ones the picture is nowhere near as rosy.

So there is a time dimension involved in answering this question: do we have the time to undertake the steps necessary to transition to a new, sustainable ecosystem before the negative consequences of both our present and our transitional arrangements threaten to catch up with us and overwhelm us?  

It is like the Marx Bothers film, Go West in which the passenger train they are on is running out of fuel. Harpo is sent back through the carriages with an axe and begins chopping up the train and carrying the pieces forward to feed the boiler. Of course, the question is: will the train get to its destination before it has been completely demolished? 

Nevertheless, as far as the answer to second question goes I have to answer yes again. That said, figuring out how to transform almost every aspect of our industrial and agricultural ecosystem is decidedly more difficult than dreaming up a hypothetical future — so it has to be a cautious yes.

Question 3. Assuming a ‘yes’ to both questions 1 and 2, how can we muster the political will to embark on a program of action that has any hope of success? 

Present strategies for tackling climate change tend to focus on mitigation or, to put it another way: we have identified the processes and patterns of behaviour that are bringing about the present crisis and therefore the general consensus is that we should stop doing them.

This is all terribly negative however and, with the exception of a privileged minority who have chosen to adopt a variety of green measures as a lifestyle choice, most people find the privations necessary to reduce their carbon footprint distinctly unattractive. Governments meanwhile, attempting to burnish their green credentials, are quick to take advantage of any method of accounting that can portray CO2 reduction statistics in a favourable light. Meanwhile, one only has to take a look at the rate of global heating, sea-level rise and instances of extreme weather to see that our headlong race toward the abyss continues unabated. 

It is a chilling thought that, of the three questions outlined here, it is the immediate one,  the one we face right now, that is the hardest to respond to positively. It is becoming increasingly clear that the response from both governments and individuals is falling sadly short of what is necessary. This is leading a number of people to resort to an ideology termed Deep Adaptation, as outlined in an influential paper by Jem Bendell: Deep Adaptation — a Map for Navigating Climate Tragedy. 

As the abstract to the paper puts it:

"The purpose of this conceptual paper is to provide readers with an opportunity to reassess their work and life in the face of an inevitable nearterm social collapse due to climate change."

Or, as Rupert Read, one of the spokespersons for Extinction Rebellion states: 

“Deep Adaptation means adaptation premised upon collapse.”

These people may be right, and they certainly have the weight of evidence on their side. All the same, without detracting from the force of their argument, I am inclined to take an optimistic view.

So I intend to work with others on developing positive visions of the future. These don’t even need to be entirely plausible — at least not in the first instance. As a species, we are susceptible both to imagery and to stories. Maybe it is time we allowed our imaginations the space to explore them again.   




Monday, June 08, 2020

Climate emergency, cultural emergency

There’s a cultural dimension to the climate emergency and for the last 50 years we have been playing it all wrong. Ever since the Ecologist magazine published its Blueprint for Survival in 1972 it seems there have been people warning of imminent environmental collapse and others inclined to dismiss them as alarmists, killjoys and prophets of doom. The scales may have tipped in the intervening years but the cultural attributes of the two sides have hardly changed.

The problem with the activist side is that the message is essentially negative: we face extinction or, at best, serious environmental, economic and social breakdown unless we significantly reduce the rate at which we are releasing CO2 into the atmosphere. We can help to do this by eating less meat, giving up the second car, flying less and so on. It is a familiar picture.

Of course, for that significant fraction of the world’s population who can see little beyond the daily struggle to provide food and shelter for their children, such concerns risk appearing somewhat academic. For the rest of us it boils down to a matter of managing guilt - either through reparation or denial.

There is nearly always an element of guilt - mostly on account of the fact that, faced with the prospect of climate change, most of us find it difficult to give up enough to make a significant difference. Many choose to do as much as they can and quietly rank themselves according to the extent of their self-assessed virtue. Others, finding themselves culturally at odds with the whole green lifestyle, prefer to hold out for action at government level. While they might be worried about climate change, they don’t feel there is much they can (or wish to) do about it. A common view is that there are others whose responsibility for the problem is far greater than their own. Why should they give up their own hard-won, yearly holiday when there are others boasting about reducing theirs from three to two?

But let’s not fool ourselves: despite the fact that they would have us believe we’re all Green nowadays, there really is another side - namely the side that would have us all wander over the cliff edge, just so long as there are profits to be had on the way. There is little point in identifying the individuals who seem intent on taking us down this path. The momentum dragging us inexorably towards disaster is locked-in to the structures, customs and practices that make up capitalism and its variants. Individuals might grow weary of serving this machine but there are always others eager to replace them. Meanwhile the algorithms continue to do their work.

When it comes to opposing and belittling climate activism, the opposition finds itself with a wealth of targets. Those advocating radical change are variously described as: naive, privileged, middle-class, egotistical, disruptive, unglamorous, unrealistic fantasists. Many of these labels resonate even amongst sympathisers. As so much of Green ideology appears to focus on self-denial, Greens are easily portrayed as ardent killjoys - despite the colourful clothes and the drumming. It’s like those happy-clappy evangelists; they might look like they’re euphoric but deep down you suspect they’re not actually having much fun.

The problem with programs for addressing climate change is that they focus on the steps we need to adopt to transition from where we are now to a green and sustainable future. Of course there is nothing wrong with this from a scientific point of view but in terms of presentation it is a disaster, principally on the grounds that the measures advocate abandoning the familiar and embarking on a voyage into the unknown with no clear destination in sight.

It doesn’t need to be like this. Here is what I think we should do.

Firstly, we should focus more energy on developing a vision for the future that describes how humans and other creatures can inhabit the earth in a sustainable way. Sustainability is the key concept here, in as much as it refers to the ability to co-exist with nature and the environment in a way that is ongoing. Far from representing ‘back to nature’ fundamentalism, the future global ecology will depend on highly sophisticated closed-cycle technologies, compared with which our present poisonous, waste-encumbered efforts will appear recklessly primitive. Such ecologies will draw on environmental energy flows, as opposed to fossil fuel extraction and there will be a natural tendency in favour of geographic dispersal, based around small communities and towns, where both energy and resource flows will be predominantly localised.

Secondly, we should turn the tables. At present, the environmental movement appears willing to participate in a scenario in which it is cast as the alternative to a mainstream which is manifestly broken, and yet it is the environmental side that is obliged to explain itself. This is all wrong. We should be putting the difficult questions to apologists for the status quo; they are the ones from whom we should demand answers. In all our communications we should rebrand the environment-despoiling, fossil-fuel burning, climate change deniers as the Opposition - for that is precisely what they are. 

I have no doubt whatsoever that a future sustainable ecology using known advanced technologies is 100% feasible. What is less clear, of course, is how to make the transition from where we are now. That said, we should not be apologetic about the fact that we don’t have immediate answers. Without a destination it is difficult to plan the journey.

Instead, we should demand that the Opposition explain exactly where it is they think they are taking us.






Tuesday, May 12, 2020

The Accelerating Pace of Change

Attentive readers will recall that my April 1st post – Books was originally intended as part of a collection of vignettes on turn-of-the-century technology companies. The only other part of that long-abandoned project that managed to get itself written is the following parody on the culture of innovation and its consequences. It is more authentic than you might imagine. 

As everyone knows, in the World of Computers things are getting faster and faster all the time. This is known as Moore's Law and is Fundamental. To keep up with all these changes it is essential to stay constantly on the move as far as skills and competences are concerned. As soon as you get the merest whiff of some new terminology or language that you haven't heard of before, you have no other alternative but to check it out immediately - either by snuffling around magazine articles, grazing on-line tutorials or buying a fat book on the subject.

There is one crucial point to remember however and it is this: on no account must you be tempted to allow curiosity to grow into a Technical Skill – for the simple reason that you might be foolish enough to put it to practical use. Quite apart from the fact that you will undoubtedly discover the subject to be far more complicated than you first thought, the real mistake arises from the fact that you simply haven't got the time. To use your new-found skill today is to renounce the possibility of acquiring a much better one tomorrow.

Go on, admit it – you are sceptical about this. "Yes, very witty." you snort. Alright, let's look at a practical illustration.

On Monday, Bob and Alice both read an article about a new computer language called Goo. They nose around it's features, add a few keywords and acronyms to their technical vocabulary and learn just enough to contribute to a respectable discussion with the average marketing executive (which – let’s admit it – is not that much).

But, now Bob is lured down the Path of Error. He decides that Goo is just the thing he's been looking for to build his latest app and he embarks on, what we computer types call An Implementation. 

Ah, foolishness and folly. By Wednesday he's fully immersed in the inner workings of Goo and discovering that it's not all easy going; but all the same, he confidently expects to have the job done by Friday.

Alice meanwhile, has her sights firmly fixed on bigger things. On Tuesday morning, whilst browsing an obscure technical website, she discovers Goo++ a far superior version of yesterday's language and spends the rest of the day familiarising herself with its features. On Wednesday she applies her new-found knowledge to the same project that Bob is working on and, because of The Accelerating Pace of Change, is all done by Thursday and takes Friday off, but not before thoughtfully emailing Bob to tell him he's wasting his time.

Except, of course, she does no such thing.

Ah, you sharp-witted reader; I see you've spotted the flaw. No, Alice – our wise protagonist – spends Wednesday dining in a fashionable eatery with Ted, the Chief Technical Officer where, over a dish of fresh mussels, she extols the virtues of Goo++. Ted listens admiringly while she recommends that they suspend all ongoing Goo development, retrain the personnel involved and assign them to a new Goo++ project group, in which, under her direction, they will toil on the treadmill of implementation until they are completely burnt out.

The moral of the story being: Never let today’s reality blind you to tomorrow’s potential.

Attentive readers will have observed a curious implication of this principle.

For Moore's Law, which  can be more precisely stated as:

"What you don't do this week you'll do in half the time if you put it off for a week and a half"

implies that sometime around next October a state will be reached where the Leading Edge will be moving infinitely fast and computer expertise will consequently cease to progress any further. The corollary, of course, (I see you bursting with eagerness to beat me to it) being that all computing tasks will potentially be complete by the same date had they been undertaken - which of course they weren't. So the Perfection of Computing Expertise occurs at precisely the same time as all further development ceases.

Of course, the reality is a little more mundane. We are saved from this fate by the simple fact that the Wheels of Change are mired in the inescapable Mud of Practicality. People insist on do things with their knowledge and consequently slow things down just enough to ensure life carries on,

And a good thing too, I say.

Monday, May 11, 2020

A Prisoner in Paradise

I sit out on the deck after midnight. In past years we had parties out here - often in the pouring rain. There would be people sitting, swathed in blankets, shoulder to shoulder on the sofa whilst others shifted around on the edges, trying to avoid the torrents of water falling from the roof.

Tonight though, it’s just me and the full moon. The boards at my feet are like a silver raft floating above the half-lit lawn that slopes away to a drop, where it abruptly ends. Beyond this, the dark mass of the woods looms up, quiet and silhouetted against a radiant sky in which the moon hangs like a dazzling jewel.

It’s strange how, in moonlight, the brightness of things diminishes with distance. This gradation of light, from the clarity of the foreground all the way to distant shadows, brings with it a sense of calm immensity in which the flow of time itself seems subdued.

Earlier, I took my permitted quota of exercise by walking in the woods. It’s a route I often follow and which I never grow tired of. Where the wood ends there is a old stone stile guarded by two trees - ‘the gate of the wood’ as I call it. Just in from here is where the wild garlic is thickest. The path I take back winds itself through a froth of white flowers, climbing slowly to the higher ground before quitting the wood for a high, open field where, on an earlier occasion, I once met a hare. Beyond here the path descends slowly down through green pasture. There’s the church tower - it’s base and the church itself are hidden by trees.

Except for two brief trips to the local town, I haven’t left the village in weeks. There’s a shop, staffed partly by volunteers that is suddenly thriving. Along with the usual essentials they have fresh trout, green vegetables, sausages and cheeses — all locally sourced. Only two people are allowed in at any one time and we are asked to wash our hands before entering.

Back home, I divide my time between staying in touch with people by email and Zoom and keeping on top of our domestic accounts, housework (some), cooking (lots) and gardening. I am reading, both in the true sense of the word and by listening to recordings on Audible. From time to time I release a new post on my blog; I play Pokemon with the grandchildren and read them stories by means of a cunningly mounted phone that permits them to see the book. I am trying (unsuccessfully) to find time for my artwork; I need to develop some designs for the spare bedroom. Down in the cellar, the 3D printer is churning out protective visors for distribution to local hospitals and care homes. Most evenings we watch things on television: Twins, Hidden, Normal People, Succession, Have I Got News For You, Newsnight. Time flies by at an astonishing rate. If it weren’t for Thursday evenings, when we briefly step outside — ostensibly to clap for the NHS but as much out of a desire to say hello to our neighbours — I would be constantly having to remind myself what day of the week it is.

What is the point in telling you all of this? You no doubt have something similar going on — that is assuming that, like me, you are in reasonable health, unstressed, financially secure, light on responsibilities and not prone to boredom.

Of course there are others who have something totally different going on — though, let’s admit it: they’re unlikely to be reading this. For a start, many of them will be too busy — like the people who are keeping the whole show on the road: doctors, nurses, ambulance and delivery drivers, care workers, police, people working in food production, on supermarket check-outs, maintaining water supplies, power and data networks. Many are on low pay. All are arguably at higher risk than those of us who are confined to our homes.

And not all those who are locked down are having a party either. Many are suffering poverty, ill-health, loneliness or depression. Others will have been laid off. Some households - chaotic or abusive at the best of times - will be in crisis. To think that the long, hard years of austerity should have come to yield such rotten fruit.

We hear little or nothing of this world. First hand accounts of life under the pandemic are mainly confined to the experiences of well-resourced, middle-class people.

The situation is exacerbated by the fact that the very same restrictions that are causing serious problems for so many are helping compound inequality and intensifying social division. Just when we should be starting a broad-based conversation across all sectors of society, we instead find ourselves increasingly confined to our silos, some cushioned — mostly not.

But what is really shaming is that, for many of us, all of this literally doesn’t bear thinking about. So — and here I must speak solely for myself — I persuade myself that the problem is too big and that, in any case, the pursuits that I follow: the walks in the woods, my reading, writing this piece — are all, in some mysterious way, helping bring about a better world.

Of course, this is no more than wishful thinking.


Tuesday, April 14, 2020

Brian Cox on Hardtalk

Last night I watched Brian Cox (the actor, not the physicist) being interviewed by Stephen Sackur on BBC's Hardtalk.

He was speaking from his home in Upstate New York and I have to say that — out of the hundreds of domestic settings we are becoming used to seeing on our screens — this has to be one one of the nicest looking.














But it was the interview itself that was inspiring. He is a thoughtful and compassionate man. Watch it if you have the time — though you might want to start at the 9 min mark:

https://www.bbc.co.uk/iplayer/episode/m000h5pc/hardtalk-brian-cox-actor

Saturday, April 11, 2020

Excuses, excuses

Following my last piece, a number of readers have written in, offering …

Wait, wait. What’s this stuff about readers? Is that the right term? Can you lot really be described as readers, or is there a better word for what you are - and furthermore, one that you will be happy to answer to?

Maybe it would be more accurate to refer to you as subscribers - but that’s not quite right either. Being a subscriber implies some sort of contract and — let’s be honest — getting sent ‘New blog from Omnivorist’ emails every other day is not something you ever signed up for.

How about devotees? Now there’s a word with a nice ring to it.

All the same, there’s the undeniable fact that while devotees might be nice to have they’re not always so nice to be, besides which, having devotees — tending them, nurturing them and so on — sounds like an awful lot of work. In any case, I really can’t see the people who read my stuff being happy to think of themselves as devotees — however much they might enjoy it. Might as well go the whole hog and call them disciples while we’re at it.

Followers might work — it is very popular and has a wide currency on social media. It is still not quite right though. To describe someone as a follower suggests a dull-witted, bovine compulsion to munch-up whatever is placed in front of them — something which certainly can’t be said of you lot. It’s difficult enough even to get you to click on the link.

I wouldn’t really have a problem with the readers thing were it not for the fact that it reminds me of those lamps: the very expensive and incredibly bright ones, designed for the kind of old people who are flattered to be classed as Serious Readers.

Of course the very term Serious Reader implies there is another sort, namely the non-serious reader or the flippant reader — you know, the kind of person whose reading of Jane Austen’s celebrated opening line, might go something like:

“It is a truth universally acknowledged, that a single man in possession of a good fortune, must be ........... whatever !”

No the serious reader is one who approaches the written word with a degree of quiet determination. The first sentence is read, then the second followed by the third. Then the third sentence is read again and then the fourth begun … until the eyelids droop and the chin sinks slowly onto the chest. An unseen hand flicks off the lamp and the room is silent save for the sound of gentle snoring:

xorghf, xorghf, xagagagakkk

So where was I ?

Yes, that was it: following my last piece, a number of readers have written in, offering all sorts of excuses as to why they still haven’t bought a copy of The Wisdom of Wormwood.

Here are just a few of them, starting with the paltry ones:

I won’t have the time to read it
   Be honest - that’s not really true right now is it?

I don’t like being pressured into buying things.
   Go away, come back later and pretend you found it all by yourself.

I fear that buying a copy will only encourage you to write more.
   There is always that risk.

I don’t want to spend £2.99 without being absolutely sure that it’s any good 
   Let me assure you: it is very good indeed — better than you could possibly imagine. 

I’ll do it tomorrow
   Yeah, yeah.

And then there are the legitimate excuses:

I don’t have a device capable of running Kindle. 
Having vowed to renounce Bezos and all his works, I refuse to buy things on Amazon.
I have never really liked your stuff anyway.

Fair enough

Wednesday, April 08, 2020

A piece of shameless self promotion

You may think you have seen this before and you'd be right but the fact is, if you haven’t already got yourself a copy, you NEED to get one NOW




“But where can I get one?” I hear you ask.

The answer is, you can get one here

And it is no use coming up with excuses: that you haven’t got the time, have too many other things to do and so on, because — sorry — but it just won’t wash.

During these difficult days [add phrases invoking wartime spirit etc etc], we should give ourselves the time to smile or even to surrender to a hearty belly laugh — you know, the kind where you rock back and forwards in your chair, slapping your thighs, while throwing your head back and emitting gales of full-throated laughter.

So if you find yourself thinking:

“I’d like some of that — it sounds just the ticket.”

Then you NEED to click here and get yourself a copy of

The Wisdom of Wormwood 


That's right — do it NOW

Wednesday, April 01, 2020

Books

Looking at all the bookshelves appearing in people’s webcams reminded me of something I wrote some years ago that was going to form part of a larger collection called ‘HTML and all that’, which is unlikely to be brought to completion for the simple reason that it was rooted in the time I spent writing computer software and is now somewhat dated. This chapter is about building a technical library. I was thinking of modifying it with the intention of giving it wider appeal but, life being too short, I decided to leave it as it is. 

So you have to buy some books. Notice I say 'buy', by the way, and not 'read' or 'borrow', for  this is an important point - you  must own them. In fact I can safely say without exaggeration that owning the book - or more precisely - taking possession of its content is the very essence of what we're talking about here. Bringing the book home, taking it out of its little bag and making a special space for it on your shelf - this is what it’s all about. Now (already), to all intents and purposes, you have appropriated the knowledge it contains. Think of it, if you like, as a sort of long-term storage. Your own memory, the bit you carry round with you inside your head, is a precious resource and should not be treated as a mere shopping bag in which to lug around all sorts of arbitrary information. No the proper place for that kind of thing is on your bookshelf, or on the disk of your computer, both of which can be thought of as extensions of your own intellect, holding information ready to be loaded up the moment you require it.

But I am running ahead of myself; before you can buy the book you must select it from amongst all the others in the shop. How do you go about doing that? In this piece I will give you a few guidelines which, if followed, will guarantee satisfaction.

So there you are, in the bookshop confronting an enormous set of shelves on which is arrayed the most magnificent collection of books. Let me acknowledge right away that at this point it is not unusual to suffer a kind of dreadful premonition in which you see the selfsame books stuffed, dog-eared and slightly mildewed, in cardboard boxes outside some depressing second-hand bookshop, tagged with a handwritten label announcing '15p each - 5 for 50p' Should this happen - and it is inevitable from time to time - there is nothing else for it but to leave the shop immediately. Go and do something else; this isn't the right time.

But today the books are looking pristine and inviting. Where do you begin?

Well, you have to narrow down the choice and this should be done in the most efficient way possible - that is with your hands in your pockets. The first selection criterion is a simple one - thickness. You are looking for books that are between 1 and 2 inches thick. Less than that and, I guarantee, it's going to be heavy going. It's difficult to explain - but there's a certain quality of meanness about a thin book. You can be sure the author considers himself very clever and is somehow justified in receiving a small fortune for the privilege of parting with a few pages of incomprehensible gobbledegook. The only exception to this rule applies to those cases where the title alone is so enigmatic and impressive that it might be worth acquiring the book for it's spine alone. Tastes vary but something along the lines of In Defence of Failure or Cloud Geometry would be strong candidates for my own shelves.

The very opposite can be said of thick books. Though it is a somewhat arbitrary threshold, anything over 2 in thick has to be considered distinctly suspect. There's an increasing tendency in this direction with books of 4-5 inches thick regularly on offer.

Who are these authors who can say so much on a subject that only a month ago was completely outside the sphere of human knowledge? The suspicion is that these books are not so much written as generated. For some reason only known to the publishers they are invariably red and have titles that are either boastful: The Guru's Guide to Goo or simply enigmatic: FffD Secrets. If you were to heave one of these tomes down from the shelf - and be warned, this can be dangerous - you will be presented with a photograph of the author while, at the same time, your fingers unconsciously trace the outlines of a CD glued into the back cover. In case 900 pages is not enough, you are offered a 600 Megabyte memory dump of the author's own personal computer.

Only now, having narrowed down the field somewhat, should you give serious attention to titles. Titles are important. When you are interviewed on the Horizon programme in a few years time you will be filmed against  the backdrop of your bookshelf and, however clever you sound, the impression is going to be seriously compromised if titles such as The Beginners Guide to Basic or First Tottering Steps in Computer Programming  are clearly visible over your shoulder. Avoid these books like the plague. They serve no purpose whatsoever. As long as they remain unread they will only serve as a source of anxiety, causing you to wake up in a cold sweat the night before you are due to address an international conference on Image Recognition Architectures with the unshakeable conviction that there was something in Fun Pictures on your PC in 3 days that you completely overlooked. If you do choose to read them (and as we shall see later, this should be considered a strategy of last resort) then you will want to heave them out of the house as soon as possible.

So you have eliminated about half the books on the shelves without touching any of them  and now you're left with books between 1 and 2 inches thick with good, dependable titles - like Comprehensive C++, A Lisp Primer and so on. Even so there are still an awful lot to choose from and, there's nothing else for it, this is where you're going to have to reach up and handle them.

First thing to look for is the front cover. It’s difficult to state hard and fast rules here but a few simple guidelines can be stated.

Animals are good. If the book has an animal on the cover it is definitely worth looking at more closely. So keep that book with the picture of the amphibian on the cover for further consideration. Another good indicator is the cover illustration that looks like it might have been painted by the author - you know the kind of thing: a wizard or suchlike, floating awkwardly against a background depicting badly painted castle walls with maybe a medieval maiden in a wimple. Is that the right word? You know, one of those conical hats with a bit of gauze draped from it. The whole composition is enough to make you feel sick of course, but let's try to understand this. The author, being some arch-nerd, has thought it a really Great Idea to provide his own cover illustration and the publishers (shrewdly) have the insight to appreciate that Like Attracts Like (or some other such principle) and, ignoring the protestations of the art department, have gone along with it. The guy must have something about him to be worth flattering in this way and the publishers have no doubt calculated that the nerd-market alone is going to be sufficient to bring in a healthy return. No - put aside your understandable distaste and keep the book on one side for further consideration.

The cover illustrations to reject are easily recognisable. Anything that looks vaguely technical - flow charts, circuit diagrams and the like - these go straight in the reject bin. There's no safer indication than this that the book has been commissioned by serious business people. It is going to be boring. No, worse - it's going to be deeply depressing. Don't take my word for it though. Go on, open it up, turn to the Preface or Introduction or whatever it is that immediately follows the horribly long and turgid Acknowledgements. Read the first sentence. It starts: "In today's dynamic business environment … "  doesn’t it? Need I say more?

To go any further, you're going to have to open the book and look inside but don't despair - a glance at the dedication is sufficient to eliminate a good 50% of the volumes remaining. What you're looking for is something distinctly quirky like:

To Annette for feeding the marmosets

A dedication of this sort should be readily distinguishable from the more pathetic:

To my wife for her patient and selfless support.

In the first case, we're talking about someone who is clearly deeply in love with the author. Even though Annette is clearly somewhat afraid of the small animals, doesn't like touching them, let alone changing their soiled bedding, she willingly does it simply to be occupying the same space as her brilliant partner, who spends every evening hammering out his life's work on the PC.

The second dedication, on the other hand, speaks of an abandoned and resentful woman whose selfless support consists of nothing more than a willingness to tolerate, endless lonely evenings patiently explaining to the children how their father is very busy earning the money to pay for their riding lessons. See the difference? You don't want to spend good money on a book written by someone so uncaring.

So now, finally, we come to the part where you must delve deeper. This doesn’t need to take as long as you might imagine. Raise the book to your nose and riffle through the pages. Does it smell right? Tastes differ but you’re looking for something like new-mown grass or the smell of rain on stone paving after a long dry spell.

If you follow the principles outlined above you will find yourself with a technical library that not only provides you with the comforting assurance that you have a vast body of knowledge at your fingertips but will also be the envy of others.

Books undoubtedly have a number of additional qualities that I might have touched upon. There are some individuals, for example, who are passionate about the contents of the book – specifically by the detailed way in which the words are grouped into sentences, paragraphs and chapters. This is something of a specialised topic which I do not propose to embark on here and is one that, in my own experience at least, I have not felt the need to trouble myself with.

Contact tracing

Since I first posted this piece late last night, discussion of contact tracing appears to have gone viral (as the saying goes), partly in response to the rumour that the UK is about to launch something very similar to TraceTogether (first developed in Singapore and described below). I was going to add some links but you can find them everywhere. So, by all means skip the piece below; it adds very little to the general discussion. I do however recommend taking a look at the Youtube link at the end - if you haven't see it already. 

There appears to be a growing consensus that the only effective way to manage (and eventually eradicate) the Covid-19 pandemic is through a rigorous program of testing and contact tracing. This is the policy advocated by amongst others: the WHO’s Bruce Aylward and the UK former Health Minister, Jeremy Hunt. The merit of the approach is supported by evidence from SE Asian countries — most notably Singapore and South Korea — where testing and contact tracing were adopted from the outset with a measurable degree of success.

So how does it work? At the simplest level, public health bodies identify people either testing positive for the virus or showing symptoms and then, by means of interviews, ask them to remember with whom they have been in close contact. These people would be followed up in turn and offered testing and advice on limiting further spread.

It doesn’t take long to see the impracticalities of this method. For a start, people are unlikely to remember all of their close contacts and would be unable, in most instances, to identify individuals - for example, after travelling on a bus or visiting a supermarket. Also the resource requirements involved in tracking down and interviewing a widening network of contacts would be considerable.

So how was it done in Singapore and South Korea?

In South Korea the government texted people to let them know if they were in the vicinity of a diagnosed individual using location data from mobile phones. In any case, it is an approach that would be unlikely to gain acceptance in the UK on account of the privacy implications. It is also difficult to see how this would help trace contacts of asymptomatic individuals who later tested positive.

The method adopted in Singapore is more interesting. Here they encouraged people to install an app on their phones called TraceTogether. Each app was assigned a unique ID and the Ministry of Health maintained a database linking each ID to the user’s phone number.

The way it works is this: every time you come into close contact with another person with the same app installed on their phone the apps communicate (via Bluetooth) and each simply stores the ID of the other contact together with the current time. If you remain free of the virus there is no need for you to pay attention to the data being collected - in fact, it is virtually meaningless, consisting simply of a number of timestamped numerical IDs. If you test positive for the virus however, you are encouraged to contact the Ministry of Health and allow them to access the data stored on your phone. The Ministry is then in a position to inform those contacts whom they deem to be at risk and advise them to be tested.

Although this still requires the involvement of a government ministry, the TraceTogether app is designed in such a way as to reassure users with regard to privacy. In essence it is little more than a streamlined version of the contact tracing approach described earlier, the main advantage being that it does not rely on individuals being able to recall (or identify) the people they have been in contact with.

Before I heard about the TraceTogether I found myself thinking about something along similar lines. As it turned out, this was very similar to TraceTogether except for the fact that, in my own scheme, the records would be uploaded to a central body which would, as a consequence, be in possession of the data necessary to construct a detailed representation of contacts across the entire population. Not only would this allow those at risk of infection to be identified and contacted but it would also enable the co-ordinating body to evaluate the effectiveness of social isolation directives as well as assessing the consequences of contacts involving key workers (emergency services, medical staff etc.)

It is the sort of idea that seems wonderful for a while, until one realises it could also be a nightmare.

Many of these issues are discussed in a recent article by Jon Evans. In it he makes the observation:

More generally, at what point does the urgent need for better data collide with the need to protect individual privacy and avoid enabling the tools for an aspiring, or existing, police state? And let’s not kid ourselves; the pandemic increases, rather than diminishes, the authoritarian threat. 

The whole article makes very interesting reading. You can find it here:

https://techcrunch.com/2020/03/29/test-and-trace-with-apple-and-google/

The author comes to the conclusion that Apple and Google are capable of constructing a near-complete contact model within the time frame necessary to bring the virus under control and that furthermore they can be trusted more than governments not to misuse the information obtained.

I am not inclined to comment further other than to point out that such a proposal would be — at the very least — controversial.

Finally though, you should take a look at the following short presentation. It shows what is presently possible using location data from mobile phones.

It is a bit of an eye-opener.

Sunday, March 29, 2020

Webcam whimsy

With each passing day we’re becoming accustomed to seeing all sorts of politicians, personalities and pundits speaking to us directly from their homes.

Surely I can’t be alone in finding this trend absolutely fascinating. For while the online contributors imagine us to be hanging on to their every word, in reality we are busy conducting a detailed inventory of their furniture, light fittings and choice of curtain fabric.

There are very few of these domestic backgrounds that have nothing to offer. It is simply a matter of taking the time to look carefully. A few examples will suffice to illustrate what I mean.

Firstly, here is a still from a recent interview with Chris Hopson, CEO of NHS Providers.
















I can’t quite put my finger on it but I get the distinct impression that he’s doing the interview from his mum’s house. One doesn’t require Sherlock Holmes’ powers of deduction to arrive at this conclusion - the evidence it right in front of you.

To start with: where is he sitting? Behind him we can see two easy chairs arranged so as to suit watching TV, but judging from the camera angles Chris is clearly sitting at a table or desk. Furthermore, the short sections of wall to left and right are strongly indicative of the kind of home conversion that consists of ‘knocking through’ the wall between lounge and dining room to form a larger space. This isn’t the sort of living space you would normally associate with the chief executive of a major public body. If he were in his own home, he would surely be doing the interview from his private office. No, Chris is in his mum’s house, having requisitioned her dining room table as a place to put his laptop.

And then there’s the other evidence: that lamp, for example — the sort advertised in those leaflets that fall out of your Sunday paper and aimed at ‘the serious reader’. That is an old person’s lamp and those easy chairs look like old people’s chairs. Of course I might have it all wrong; Chris might just be an old-fashioned kind of guy.

By way of a complete contrast let’s say hello to the physicist Carlo Rovelli in his home in Canada.
















Here, Carlo has clearly opted for the bookshelf theme and, it has to be said, has done it with a degree of enthusiasm. His books, furthermore, are not organised by size, style of binding etc. - as is so often the case with those of more modest intellectual abilities - but in accordance with an entirely different organisational principle - albeit one that is not immediately apparent to the rest of us.

Of course, without being able to examine the titles we can’t be absolutely sure that his library does not include such classics as Cosmology for Dummies or Fun Pictures on your PC in 3 days. Unfortunately, the webcam used is of lamentably low quality so, for now, we must grant Mr Rovelli the benefit of the doubt.

David Liddington’s method of organising his library couldn’t be more different.
















He appears to be in the habit of storing his books in piles, which is oddly disturbing. I don’t quite know why — but I find it impossible to shake off the impression that his office is in a converted garage. There’s a hint of trouble here. Has he been banished from the main part of the house and forced to take his clutter with him -- and in a hurry at that? While we’re unlikely to know, it doesn’t stop the imagination from getting to work.

And it is not always a matter of what is there; it can be equally intriguing to speculate on what is absent. Here is Shami Chakrabati pictured against a neutral, whitish background - blank except for the small, brass picture hook behind her, demonstrating that it is possible for there to be something even emptier than a featureless wall.
















But the prize must go to a recent Newsnight interview with Ian Duncan Smith, which has since achieved cult status on account of the fact that, in it, IDS appears to be literally incandescent.
















This video has since given rise to a whole wave of comments on twitter to the the effect that he had forgotten to activate his cloaking device and so on. Quite apart from the startling appearance of the principal character, the image has many more small jewels on offer including, to the right of IDS’s head, a disturbing picture reflected in the mantlepiece mirror. This would appear to be a picture of someone laughing - or are they screaming?

Of course, all good things must come to an end and it can only be a matter if time before people in the public eye get themselves set up with anodyne home studios. So we have only a brief time window in which to enjoy this rich field of study.

When it comes to choosing a setting for my own videoconferencing, I am considering an entirely synthetic approach in which I contrive to be pictured in front of a raging sea or some other dramatic backdrop, chosen to suit the occasion

Monday, March 23, 2020

The Calm before the Storm

There can’t be many people who aren’t worried right now. I for one, find myself flicking between a slightly dreamy sense of unreality and a state of mild anxiety.

Of course, watching the news or listening to the radio can be something of a mixed blessing. There is no shortage of people eager to explain how we are heading for a health service meltdown with social unrest, troops on the streets etc. And then there are the people who say that it’s all a lot of fuss about nothing, that it’s just flu and that, like Stanley Johnson, they’ll be damned if someone tries to stop them going to the pub.

So it was with a degree of trepidation that I decided to listen to yesterday’s The World This Weekend at 13:00 on BBC Radio4 (22/03/2020). 5 minutes into the program there was a lengthy piece on Queen’s Hospital in NE London as it prepares itself for the predicted wave of COVID-19 patients. The presenter, Jonny Dymond, spoke to a number of health service professionals — admittedly all in more senior positions — the chief medical officer, the clinical director of the emergency department and a respiratory consultant.

The whole piece had a strangely surreal air. With routine appointments cancelled and all but the most unwell patients having been discharged from the wards, there was something about the acoustic quality of the interviews that conveyed a vivid picture of this huge, virtually empty hospital as it readied itself for the storm to come. 

Each of the contributors offered a clear and straightforward account of the challenges they were about to face. There was nothing grim in their manner. They simply described how they planned to go about their various tasks, about the unique aspects of treating COVID-19 patients and some of the difficulties and shortages they faced in caring for them and protecting themselves. It was both terrifying and reassuring; something both planned for and unparalleled in living memory.

I found the whole piece immensely moving and it left me with an enormous admiration for ALL the people working in the NHS.

Sunday, March 22, 2020

Vernal Equinox

Down the hill from where we live is the little Hamlet of Washpool - so named on account of an old stone-lined basin worked into the course of the stream which, in former times, served as a sheep dip.

We walked down there last night, on the way to the woods, to find a group of our neighbours, well-spaced apart and working together, clearing the ground of brambles and other thinnings and heaping them onto a large billowing fire.

Today is the Spring (or Vernal) Equinox, Ostara in the Wiccan calendar — traditionally a time to celebrate the end of winter and the promise of warmer days. On the face of it, nothing would seem more at odds with the frightening plague that promises to change all of our lives.

We have it easy here — so far. The virus seems far away, like the sound of distant thunder. It will touch us eventually. Right now we watch the thick smoke spiralling from the fire and exchange smiles of encouragement.

The Pied Piper

If there is anything good about the present crisis it is the fact that, mercifully, coronavirus does not appear to cause anything but the mildest symptoms in children.

The emergence of the virus, whilst it might have entailed a number of careless and inadvisable practices, was clearly unforeseen. Nevertheless, our lack of preparedness in the UK has been inexcusable. Austerity, after all, was not the unavoidable necessity we were told it was, but a calculated, politically-motivated policy that has been responsible for the present fragile state of our health and social care systems.

The dogma that, until very recently, has shaped government thinking — namely that unrestrained capitalism is capable of fulfilling every legitimate human need — all that is gone now, at least in a form that can be given a veneer of respectability.

At the same time, years of growing inequality and social polarisation have given rise to shocking levels of child-poverty, homelessness and ill-health - both physical and mental. Young people have borne the brunt of this and little children were to be next in line.

The recent closure of schools will no doubt affect children in different ways, according to their age and family circumstances. Nevertheless, in the long term and taken on balance, it is difficult to imagine it being anything other than a negative experience. For many children, and in particular those for whom school represents a refuge from a stressed or chaotic home, the present disruption risks leaving them further alienated from the rest of their peer group.

One also has to feel for teenagers, whose examinations have been suddenly cancelled and who find themselves unexpectedly confined to the very nests they were about to fly.

Thinking about all of this brought to mind the story of the Pied Piper of Hamelin. In case you need reminding, it goes something like this:

In 1284, the town of Hamelin was suffering from an infestation of rats. A piper appeared, dressed in multi-coloured clothing, and offered to get rid of them in exchange for a reward. The mayor of the town agreed and the piper used his pipe to lure the rats in the River Weser, where they all drowned. The townsfolk however, reneged on their promise and accused the piper of deceiving them. He stormed out of the town, vowing to return later to take his revenge. On St John and St Paul’s day, while the adults were in church, the piper returned and, playing his pipe, led the children of Hamelin out of the town and down into a cave under the mountain. With the exception of a little boy who was lame and couldn’t keep up, not one of the children was ever seen again. 

I don’t propose trying to draw too many parallels between the Pied Piper and the present pandemic, for while it is tempting to see the rats as a reference to the Black Death, this did not appear in Europe until the 14th century and, in any case, it seems the rats in the story are the result of a 16th century embellishment.

Nevertheless, old stories like this, having been retold, reshaped and added to over many years have a power of their own that is capable of resonating with contemporary experience.

For some reason (that is not particularly clear to me) the story highlights the fact that, over the coming months, our children and grandchildren will, of necessity, see their horizons narrowed and that, when we emerge from this crisis the last thing we should think of doing is to get things back to normal. 

The children who are now confined to their homes will eventually re-emerge into a world in which the air is cleaner and CO2 emissions are lower than they have been for years. They might go on to show how it is possible to live in harmony with one another and with nature without the need for grotesque excesses. The experience of taming the virus might even teach us how to confront the threat of climate change, with the difference that in applying ourselves to that task we can, once again, enjoy the power and satisfaction of working together.

Goodness - though I mean every word, I might have got a bit carried away here. There have been other occasions, after all, when it seemed as if everything was blowing up, only for us to watch in disbelief as the fragments, unexpectedly and disappointingly, assumed their former positions. 

But — as we are beginning to appreciate — this is a big one.

Friday, March 20, 2020

Learning from the Beveridge Report

In the Guardian (19th March 2020) Martin Kettle wrote:

"The second world war remains the foundation myth of modern Britain. Invoking it is a familiar default setting in British party politics. It has a Conservative version, embodied in Churchill, with whom Johnson compares himself. And it has its Labour version, in the form of veneration of Attlee and the post-1945 welfare state."

One of the things that has never ceased to amaze me about the Second World War is that, at the moment of greatest existential threat, when the bombs were still falling, detailed plans were being drawn up for the kind of country that might be built once peace was restored.

The Beveridge Report was the result of a study undertaken in June 1941 by an inter-departmental committee of the wartime coalition government who were tasked with looking at widespread reforms to the system of social welfare. The resulting 300-page document entitled “Social Insurance and Allied Services” laid the foundations for what was to become the Welfare State - a blanket term covering the National Health Service, Pensions and National Insurance, Family Allowances and Rent Control.

There is something almost unbelievable about the idea that such an ambitious, visionary and seemingly idealistic set of recommendations could be drawn up during the darkest days of the war. But then these ideas didn’t just emerge from nowhere. They were rooted in wartime emergency measures designed to address fundamental issues of survival. Thus there were initiatives to provide milk and nutrition to nursing mothers and school children; an emergency hospital service provided free treatment to those suffering from war injuries, whilst rationing — maybe surprisingly — led to significant improvements in the diets of poor families.

I have been thinking about this and trying to write down my thoughts. As fast as I do so however, I find myself overwhelmed by further questions. Nevertheless, there is one insight that appears to have taken root, namely that it is in times of crisis that the seeds of change are sown. Just as in the Second World War the threat of military annihilation and subsequent occupation forced the British government into an unspoken pact with the people to do ‘whatever it takes’ to survive, so the present government is asking people to subject themselves to a number of distressing restrictions in order — as Johnson puts it — to ‘see off’ the coronavirus.

But there is always a contractual aspect to such impositions. If people are to confine themselves within their own homes and to home-educate their children then it is reasonable for them to expect some protection from profiteers and ruthless landlords. Similarly, at a time when thousands of people are being made redundant it is essential they have the means to obtain the basic necessities. The idea of a universal basic income — a monthly distribution of money made without preconditions — is a sensible and efficient way to ensure this, as well as a means to prevent economic meltdown. We are still in the early days of this crisis but it seems reasonable to expect the government will be forced, however reluctantly, to do something of the sort.

To return to the Beveridge Report: it is worth noting that its publication during the war was met with enthusiasm from all sections of the community. The Ministry of Information Home Intelligence found that the Report had been "welcomed with almost universal approval by people of all shades of opinion” and seen as "the first real attempt to put into practice the talk about a new world"

Nevertheless, once the war was over Churchill found all sorts of good reasons why the proposals for social reform should be watered down or delayed. In this, it seems, he misjudged the mood of the populace who, after years of deprivation and austerity were eager for change. The Labour Party won the 1945 General Election and set about implementing the report’s recommendations through a series of Acts of Parliament. The rest, as they say, is history.

And here we are now - not strictly at war but in a time which, by common consensus, has many of its characteristics. The concept of the ‘small state’ is suddenly out of the window; there will undoubtedly be government initiatives designed to ensure the supply of basic necessities as well as the introduction of ‘special powers’ justified on the grounds of maintaining order. Along with these state interventions, we will also hopefully see the growth of community-based networks whose aim will be to foster social cohesion, support the vulnerable and to build and sustain resilience.

When we emerge from this crisis however, one thing is sure: we must on no account allow things to go back to normal