Tuesday, March 02, 2021

Following the Science

 At the start of the pandemic the UK government made a lot of the claim that it was following the science in determining its course of action.  

The general feeling was that this was a Good Thing. After all, science had been quick off the mark in identifying the virus and cracking its genetic code so wasn’t it generally a good idea to hand the tiller over to the scientists and trust them to steer us through the pandemic? 

It is only on reflection that it becomes clear just how bad an idea this following the science is. In fact it isn’t even an idea - more a complete abdication of responsibility dressed up in a catch phrase.

Science, for all its potency, does not have a destination. How can we follow the science when the science has no idea where it is going? We might as well say we are following the law. 

Which is not to say that there is no role for science and engineering in planning for a post-pandemic world. While government is forced to respond to short-term imperatives, the resulting disruption to economic activity presents an opportunity to initiate all sorts of ambitious longer term goals: the green economy, universal basic income, localisation, lifewide education, integrated health and social care. 

Restructuring on this scale would call for significant levels of scientific and engineering input but the underlying vision is something that must be owned and initiated by a wide range of social institutions,  

As it is, the government’s only discernible long-term goal is the restoration of the familiar, pre-pandemic, service-based economy with the role of science confined to little more than regulating the pace at which we are allowed to return to our old, unsustainable ways. 

Thursday, February 04, 2021

Crowds and Power

Crowds and Power by Elias Canetti is a book I have owned for longer than I can remember. I have never read it but, for some reason, it has always fascinated me. Maybe I will read it one day but, in any case, that is not what this piece is about. 

Neither is it about the Gamestop affair - the story of how a shoal of marauding, individual investors set out to beat and humiliate a bunch of major hedge funds. 

No, this post is about The Good Law Project and its attempt to call the government to account over its award of highly lucrative Covid-19-related contracts to private companies.  

There are all sort of concerns about the way in which these contracts were let. Procurement processes were either cursory or entirely absent; many of the companies concerned had links to Tory donors or friends of government ministers; many had little or no relevant expertise in the products or services they were contracted to provide. 

The Good Law Project, along with a cross-party group of opposition MPs, is asking the High Court to make a declaration that the government failed to comply with its legal obligations in declining to publish details of these contracts. That’s all. Right now, we are simply asking for openness and transparency. 

It is easy to think of the law as some sort of machine that kicks into action in response to unlawful acts. Nothing could be further from the truth however. The law only works when someone is prepared to bring a case before the courts - and this is an option that is becoming increasingly difficult due to the prohibitive costs involved. 

In the present case, the government has assembled a huge legal team, to defend what it has already admitted to be persistent and unlawful conduct. It is as if it is trying to scare off any form of scrutiny. And of course, when seeking how to fund this intimidatory behaviour they have only to look to the beneficiaries of their largesse. 

So maybe this is where those ‘crowds’ come in. The Good law Project is a not-for-profit organisation that is using the law in the service of truth and the common good. It is paid for entirely by individual contributions and through crowd-funding. 

I would ask everyone to consider making a contribution.

As history repeatedly reminds us: if we work together we can make a difference. 

Tuesday, January 26, 2021

All kinds of electric garlands

I have recently taken to leafing through the documentation accompanying the recent UK/EU trade deal. An odd choice of bedtime reading you might think, and to be honest, I felt the same way at first but that was before I came across the Harmonised Commodity Description and Coding System (or Harmonised System for short).  

On the face of it this is an inventory of every conceivable tradable commodity along with its corresponding numeric code. All that businesses are required to do when preparing goods for shipment is to look up the correct HS product code and enter it on the customs paperwork. 

Simple, you might think, but you’d be wrong, for a glance at the Harmonised System reveals it to be a very strange creation indeed. What follows is a sample set of categories:

Bells, gongs or the like
Wigs, false beards, eyebrows and eyelashes
Narwhal and wild boar tusks
Toys representing non-humans dressed as Father Christmas
Articles of Gut (other than Silkworm Gut), of Goldbeater's Skin, of Bladders or of Tendons
Braces, belts, bandoliers and wrist straps, but excluding watch straps
Father Christmases with or without a sledge 
Puzzles of all kinds.
Glass eyes other than prosthetic articles
Swordsticks, loaded walking sticks or the like
Swim rings with animal feature appendages
Frogmen’s and other goggles
Gimped horsehair yarn.
Imitation yule logs
Brooms brushes, mops and feather dusters.
Electric garlands of all kinds.

What kind of world is this? A world devoid of crash helmets, corkscrews and trombones but in which, nonetheless, there is a healthy international trade in false beards, frogmen’s goggles and imitation yule logs.

And what is it about toys representing non-humans that makes it necessary to define a special subcategory to distinguish those dressed as Father Christmas (with or without sledge)?

Slowly and with mounting horror I begin to understand the hell into which British manufacturers have been plunged. Picture, if you will, the following: 

In a West Midlands engineering company a call is put through to Dave Roberts, the sales manager: 

Roberts: Hello, sales. How can I help? 

Caller: Ah, good morning. This is Herman Meyer from the Electric Vehicle Research Institute in Stuttgart. I am told you manufacture a high-torque stepper motor?   

Roberts: Yes we do - it’s one of our best products. 

Caller: This is wonderful. If I place an order for 50, how soon can you deliver them?  

Roberts: Ah well, I’m afraid that might be difficult. We have them but we can’t find the right code to put on the customs form. 

Caller: Oh dear. Do you know how long it will take to resolve the problem?

Roberts: Sorry … but no, I can’t be sure. 

Caller: What a pity, but I don’t think this is going to work. Goodbye

Roberts: Wait, wait! Is there anything else I can interest you in? We have great line in  swordsticks and all kinds of electric garlands … 

Caller: <click>

Roberts: Damn, damn! 

Roberts: (calling over his shoulder to the warehouse manager) 
Jim! Those steppers - stick them on eBay. Let’s get what we can for them.

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:  
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.