You have seen the posting. You may have approved one.

It reads like a clerical error, and online it gets passed around as a joke. It is neither. That line is the visible edge of a decision thousands of organizations made over the past two years, almost none of them on purpose.

I have argued here that AI is climbing two ladders at once — from routine tasks toward judgment, and from junior roles toward senior ones — and that the casualty is the entry-level job that has trained two generations of experts. Every senior anything, I wrote, was once a junior something.

Then I spent the summer with the data. Some of it backed me. Some of it took me apart. The second half is more useful.

Researchers at Stanford's Digital Economy Lab, using payroll records of millions of American workers, found that employment for 22-to-25-year-olds in the jobs most exposed to AI — software development, customer service — fell 16 percent relative to everyone else. Older workers doing the same jobs were fine. The young absorbed it.

The declines showed up almost entirely where AI replaces a person's work rather than assisting it. Where AI mostly helps, employment grew. Hold onto that. Employers confirm it themselves. In a survey of about a thousand hiring managers this summer, 31 percent said they had raised experience requirements for entry-level roles.

Nearly a third watched AI absorb the work juniors used to do, then required that juniors arrive already experienced. That is not a labor market adjustment. That is a catch-22 with a job posting attached.

Start with a number I have used myself.

I have been citing........

© Psychology Today