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.   

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: