“In environments where the rules are stable and feedback is immediate, early specialisation wins. Where the rules change, the winner is whoever tried several things before choosing.”David Epstein · Range: Why Generalists Triumph in a Specialized World · 2019 · David Epstein, «Range», Riverhead Books, 2019 — redare a distincției dintre medii binevoitoare și medii ostile, necolaționată pe ediție
First write what you think in three lines, then open the model.
Epstein argues that early specialisation only pays in worlds with stable rules. The world a child of today will work in is not like that, so preparation looks different from "learn to code at eight". The four habits with their exercise. One, your own thinking before the tool: the house rule is that you first write what you think in three lines, and only then open the model. Without that step the tool replaces your thinking instead of extending it, and the difference shows over years. Two, checking: any figure, quotation or claim that comes back is confronted with an independent source. A model produces plausible text, not true text, and the habit of checking is the only defence — the same one that protects against disinformation. Three, taste: being able to say why one version is better than another. Taste is trained by volume and comparison — read a lot, listen a lot, look a lot, plus the question "which of the two and why". Four, depth in a field they chose: you cannot judge an answer in a field where you are nothing. Here Epstein does not contradict specialisation, he only moves its moment: breadth first, then depth chosen knowingly. What you do concretely: one project of their own carried to the end every year, at any age; the obligation to explain out loud what they did; and at least one field where they are better than you.
The order of operations sounds like a detail, but it is everything. The difference between someone who thinks with a model and someone who thinks through it doesn't show in a day. It shows in what remains after years: the ability to start from zero, alone, on a blank page. Picture a student who always writes his outline after reading what the tool generated. Gradually, his first idea becomes a reaction, not a creation. He no longer knows what he would have said on his own. Epstein would say the trap is here: the tool is excellent at producing something plausible instantly, and instant plausibility is the hardest thing to refuse. The three-line rule is not empty ritual. It is how you keep access to your own mind. Which raises a natural question: once your first thought is down, what do you do with it?
Passage one stopped at your own thought, written in three lines. Step two is what you do with the answer you get back: you check it. A model produces plausible text, not true text, and the difference is invisible at first read. So the rule is simple: any figure, name or claim you receive gets compared against an independent source, outside the tool. Think of a recipe that says 180 degrees with fan. You don't take it from the first site you find; you compare two sources. Exactly that gesture, applied to a generated paragraph. Checking isn't distrust of the tool, but distrust of the plausible, which is the sneakiest enemy because it looks like truth. And if you check constantly, a rarer habit emerges: you can judge which version is better. How do you train that taste?
Why it matters Because the first generation growing up with a model that writes for them risks never finding out what they can write themselves, and the only thing that prevents it is the order of operations: your thought first, then the tool.