Between Poetry and Precision

Human beings have always had a slightly strange relationship with communication. We spend an extraordinary amount of our lives trying to make ourselves understood, yet some of the forms of communication we value most seem almost deliberately designed to resist complete understanding. We want clarity when we are giving directions, writing a contract or proving a theorem, but we are perfectly happy to spend centuries arguing over what a poem means. In one context, ambiguity is a defect. In another, it is the whole point.

Mathematics probably represents one extreme. A mathematical statement is valuable partly because, once the symbols and assumptions have been agreed, there is very little room for personal interpretation. Two people separated by language, culture and centuries should still be able to arrive at essentially the same meaning. Logic works in much the same way: we define terms, state premises and try to remove enough ambiguity that the conclusion follows whether we happen to like it or not.

Poetry sits somewhere near the other extreme. A poem can mean something slightly different to everyone who reads it, and sometimes something different to the same person at different stages of life. A line can remain with us for years precisely because we are not entirely sure why it matters. A painting does not normally come with a specification describing the emotional response it is intended to produce, and music would be rather impoverished if every composition had to be accompanied by instructions explaining exactly what the listener was supposed to feel.

What interests me is that both forms of communication came from the same human mind. We invented mathematics and poetry, formal logic and metaphor. Apparently, we need both the ability to remove ambiguity and the ability to create it.

The things we mean, and the things we leave unsaid

Perhaps that is because human beings do not communicate only information. We communicate moods, intuitions, possibilities, memories, fears and things that we ourselves may not completely understand. Sometimes we want another person to know exactly what we mean. At other times, we want to create a space around what we mean and allow the other person to enter it.

We do this constantly in ordinary conversation. We speak differently to a lawyer than we do to a child, differently to a colleague than to an old friend, and differently again to somebody we love. Some situations reward precision, while others depend heavily on shared context, implication and things left unsaid. A close friend can sometimes understand an entire paragraph from a raised eyebrow. It is a terribly inefficient communication protocol, but somehow it works.

Humour may be one of the best examples. Any comedian will tell you that if a joke has to be explained, it is more or less dead on arrival. The joke often works because the listener makes the final connection. Timing matters, shared knowledge matters, and sometimes the funniest part is precisely what was never said. Once somebody starts explaining the reversal, the hidden assumption or the double meaning, the joke may become easier to understand, but it usually becomes much less funny.

There is something particularly amusing, then, about the fact that I now occasionally find myself asking AI why a particular joke was funny. I can laugh at something, remain slightly uncertain about why I laughed, and then ask a machine to dissect the mechanism for me. It can often do a respectable job: identify the incongruity, explain the reference and point out where the expectation was subverted. But by the end, the joke feels a little like a frog in a biology lesson — better understood, perhaps, but not obviously improved by the procedure.

That distinction between understanding and explanation matters. We often behave as though understanding something means being able to make it completely explicit, but human experience does not always work that way. We can understand a piece of music without being able to describe why it moves us. We can feel that a metaphor is exactly right without being able to replace it with a literal sentence. We can hear sadness in somebody’s voice even when the words themselves contain nothing sad at all.

Some forms of meaning become weaker when we make them too precise. That is worth remembering because we are entering a period in which millions of us are being trained, almost accidentally, to do exactly the opposite.

A new kind of listener

We have, of course, been communicating with computers for decades, but until recently relatively few people had to communicate with them directly. Those of us who wrote software became accustomed to an unusually unforgiving listener. A misplaced character, an incorrect type or a badly formed expression could cause an instruction to mean something completely different, or nothing at all. The computer did not care what we intended. Intention had to be translated into something precise enough for the machine to execute.

Most people were insulated from that experience. They interacted with buttons, menus and forms, while software developers performed the translation between human intention and machine instruction. The interface was deliberately constrained. Instead of asking a computer to understand what you wanted, you selected from the options that somebody had already anticipated for you.

Artificial intelligence changes this relationship in a way that I think is more significant than simply giving us a new generation of software tools. For perhaps the first time, an enormous portion of the population is having complicated conversations with computers in ordinary language. People who have never written a line of code are asking machines to write, research, analyse, design, summarise, plan, explain and reason. The interface is no longer a menu of predetermined choices. It is language itself.

And this exposes something rather uncomfortable about language: describing what we actually want is surprisingly difficult.

We say, “Make this better,” and the machine immediately reveals the problem hidden inside that apparently simple sentence. Better in what sense? Shorter? More accurate? More persuasive? More formal? More imaginative? We ask it to make something “clean” or “professional” and discover that those words were carrying a considerable amount of unstated meaning inside our own heads.

This is not really a problem unique to AI. Anyone who has managed people, worked in a team or tried to explain a requirement to a software developer has experienced the same thing. We give an instruction that feels perfectly clear, receive something quite different from what we imagined, and only then discover how much of the specification never left our head.

The difference is that AI makes this experience constant. It gives us a listener that can accept endless clarification, is literal enough to expose our assumptions and yet intelligent enough to tempt us into believing it understood more than we actually said. The result is a new pressure on human beings to become much more deliberate about how they express intent.

Precision as a new mass skill

People who become effective users of AI soon develop a particular set of habits. They provide context, state constraints, give examples, distinguish between what is required and what is merely preferred, and describe what a successful result should look like. When the output is wrong, they learn to ask not only why the AI failed, but whether the instruction itself left room for the misunderstanding.

We tend to call this “prompt engineering”, but I increasingly think that description misses the more important point. These are communication skills.

Software developers have been practising this kind of precision for decades because computers demanded it. What has changed is the scale. A skill that was once particularly important to programmers is now becoming useful to teachers, lawyers, marketers, accountants, students, managers, designers, doctors and almost anyone else whose work involves AI. Ordinary language has become an interface to machines, and that means people are discovering that being able to formulate an intention clearly has practical value in a way it perhaps did not before.

I suspect this will eventually affect the way we communicate with one another as well. If you spend enough time providing context to an AI, separating assumptions from requirements and noticing where vague language produces unintended results, some of that discipline is likely to follow you back into human conversations. A manager may become more conscious of describing the outcome they actually want rather than assuming everybody shares the picture in their head. A developer may become more careful about making architectural assumptions explicit. A writer may notice more quickly that an argument depends on something that was never actually stated.

There is a broader point here. Human communication is often remarkably dependent on assumptions. We forget context, presume knowledge the other person does not possess and confuse what we intended to say with what we actually said. AI gives us a strangely effective mirror for this weakness because it repeatedly confronts us with the distance between those two things.

If that makes us clearer thinkers and better communicators, it will be one of the more interesting side effects of the AI revolution.

But there is a danger in learning any useful skill: eventually we start applying it everywhere.

The cost of explaining everything

The modern world already has a strong tendency to reward whatever can be made explicit. Objectives become metrics, experiences become ratings, conversations become action items and thoughts become bullet points. There are good reasons for much of this. Precision helps organisations function, engineers build things and societies coordinate increasingly complicated systems.

AI gives us another incentive. The more clearly we can describe what we want, the more useful the machine often becomes. Ambiguity has a cost, so we learn to remove it.

What worries me slightly is the possibility that we may eventually confuse this with a general theory of good communication.

Some things should be precise. If I am asking an AI to modify a financial calculation, write a piece of software or summarise a legal document, I do not want poetic ambiguity. I want assumptions stated, terms defined and important uncertainty made visible. But it does not follow that every valuable form of communication improves as ambiguity decreases.

A poem is not a failed specification. A metaphor is not an inefficient equation. A joke is not incomplete merely because part of its meaning exists in the listener rather than in the words themselves.

In fact, much of what makes human communication beautiful may come from this incompleteness. The listener or reader participates in creating the meaning. We bring our own memory, culture, mood and experience to what is being said. That is why the same poem can mean something different at forty than it did at twenty, and why a song can suddenly acquire significance because of something that happened years after we first heard it.

Perfectly precise communication tries to eliminate that variability. For many purposes, that is exactly what we want. Art often depends on it.

There is also something deeply human about implication. Sometimes we deliberately do not state everything, not because we are being careless or dishonest, but because saying less can communicate more. A pause can matter. A sentence can be affectionate, threatening, sarcastic or sad without any of those properties appearing in its literal meaning. Human language carries a shadow around the words themselves, and we spend our lives learning how to read it.

I would hate for us to become so impressed by our newfound ability to communicate efficiently with machines that we begin treating that shadow as noise.

Between poetry and precision

Perhaps, then, the real communication skill of the AI age is not simply becoming more precise. It is learning when precision is useful and when it destroys something we wanted to preserve.

There will be situations in which we need the language of mathematics: definitions, assumptions, constraints, logic and clarity. AI is making that mode of thinking relevant to far more people than before, and I think that is largely a good development. Being forced to explain what we actually mean can expose unclear thinking, hidden assumptions and contradictions that would otherwise remain comfortably unnoticed. The ability to communicate clearly may become one of the most important practical skills for getting value from AI.

But there will also be situations where clarity is not the only objective. We will still need stories in which the meaning is not stated, jokes that nobody explains, paintings that refuse to tell us what to think and poems that mean something slightly different every time we return to them.

Human beings have spent thousands of years developing both traditions. We invented mathematics because the world sometimes demands precision, and poetry because the human mind sometimes demands something else. One helps us remove ambiguity from reality so that we can reason about it; the other sometimes reintroduces ambiguity so that we can experience it differently.

AI is now forcing an unprecedented number of people to practise the first of these skills. I suspect it will make many of us clearer thinkers and better communicators, and I hope it does.

But I also hope that, in learning how to make ourselves better understood by machines, we do not begin to believe that being perfectly understood is always the purpose of language. Somewhere between what is said and what is understood lies interpretation, imagination, humour, metaphor and mystery. It is an inefficient space, and no doubt a frustrating one if you are trying to write a specification, but it may also be where much of the beauty of being human lives.