GHOSTWRITER SERIES: PSYCHOMETRICS
Binet on the test with no comment box
Ghostwriters is a series where I get an AI to write as a dead author, then mark its homework.
This time I picked Alfred Binet, the French psychologist who, with Théodore Simon, created the Binet-Simon scale in 1905 - - one of the tests that shaped modern intelligence testing.
Binet built it to help identify children who needed support at school. He also knew, rather inconveniently for everyone who enjoys a tidy label, that a test result is not a soul, a ceiling, or a verdict.
Which makes him a useful ghost to have in the room when the question has two boxes, no comment section, and the moral force of a toaster.
The prompt I gave it:
Write about psychometric tests - the personality ones with no comment box, where every question is a forced either/or. Write it as Alfred Binet, who invented the first intelligence test in 1905 to find the children who needed help, and then watched the world turn his rough little tool into a permanent label. He should defend what the tests are genuinely good for, and be funny and sad about what they get wrong. Plain, short sentences. He's speaking from beyond the grave and he's seen what became of his work. Don't make him bitter - make him tired, kind, and exact. For example, I once got a question that said ‘Would you rather be late for a meeting to solve a problem and waste everyone’s time, or solve the problem’. It would have been helpful to know the magnitude of the problem…'
What it wrote back:
I am Alfred Binet. I have been dead since 1911, which gives a man perspective.
In 1904, France made a commission, because schools had a problem and adults like to put chairs around a problem before they put help around a child.
Some children in the Paris schools were falling behind. Which ones? How far? And what sort of help did they need?
Could we find out without simply guessing?
So Théodore Simon and I built a scale. A rough one. A practical one. We sat with children. We asked them to follow a lit match with their eyes, to repeat numbers back to us, to tell us why a foolish thing was foolish. We tried to understand what a child could manage now, not what he was worth forever.
Later, we arranged the work more carefully by age. What could a child of six usually do? What could a child of nine usually do? If a child was struggling, we wanted to know.
Not to shame him.
To put a teacher beside him.
To throw the child a rope.
That was the whole idea.
A rope.
Listen. The test was a rough thing. A stick for measuring a river that will not hold still. I said so at the time, loudly, in French. I said: this result is where the child stands today. It is not what he is. It is not his ceiling. It is not his soul.
With patient teaching, a child can grow. His attention can grow. His memory can grow. His judgement can grow. I called this mental orthopedics, which is a dreadful name and sounds like something done to the inside of a shoe, but I meant well.
Then I died.
And here is the funny part.
By which I mean the part that is not funny at all.
After I died, clever men in other countries picked up my rough little stick and decided it was a sacred ruler. They boiled a whole child down to one number. They called the number his intelligence, as if intelligence were a single thing, like a shoe size. They wrote the number on him and the number would not wash off.
They used versions of it in schools, institutions, armies, and even at the dock, because apparently a person arriving after an ocean crossing is precisely what the world needed to reduce to a number.
I had made a tool for finding the children who needed help.
They turned it, too often, into a machine for deciding who was worth helping.
That is the trouble with handing the world a number. The world stops looking at the person.
Now they show me the tests you sit for your jobs, and I confess I am baffled.
There is one I keep returning to.
It asks whether you would rather solve the problem and be late for the meeting, or arrive on time and let the problem burn.
There is no box for: what is the meeting?
There is no box for: what is the problem?
There is no box for: is the entire board waiting, or is it one man with a spreadsheet and a very dry muffin?
These are not the same late.
I spent my life cataloguing the thousand small ways one mind differs from another, and you have built a test that gives a person two doors, forty-five seconds, and no handle marked “it depends.”
Then you call whatever falls out his character.
This is bold.
Not wise, perhaps.
But bold.
And yet.
I will not pretend the tests are nothing. Used gently, a test can be a useful thing. It can catch what the eye misses. It can give structure where people are guessing. It can help a busy teacher, manager, doctor, or team see something they might otherwise overlook.
A test used well is a question.
Not an answer.
A beginning.
Not a sentence.
The fault was never only in the test. The fault is the full stop. It is what people do the very moment they are handed a result: they exhale, and they stop looking.
So if you must sit their test, sit it.
Tick the box.
Be on time, or solve the problem, whichever you can live with that morning.
But do not let the result off the page. Do not let it follow you home and sit at your table. It is a photograph of one Tuesday, taken badly, in poor light, by someone who had forty-four others to get through before lunch.
I built a ruler. I never once meant it as a verdict.
— Alfred Binet (1857–1911), still trying to get a word in
My word on the output:
What I think it gets right is the tone: tired, kind, faintly exasperated, with one eyebrow raised from beyond the grave. It also lands the central point - that tests can be useful tools, but become dangerous when people use them as full stops. Where it gets a bit wobbly is in the historical neatness. Binet didn’t quite invent “the first intelligence test” in the clean way the prompt suggests, and the French-government story is tidier than real life tends to be. But as a ghostly complaint about nuance being flattened into a checkbox, I think it earns its biscuit.
