I think a big part of the problem is that people fundamentally misunderstand what the funnel is. The way to get people into a field isn’t rousing arguments, it’s cool results, accessible entry research, and opportunity.
As a kid, I didn’t go into pure mathematics because someone convinced me that it was a good use of my time, it was because I saw cool videos about mathematical theorems and decided that it looked fun. I didn’t move into applied maths because someone convinced me, but because there was interesting, non-trivial modelling that I could pick up and work on; and I didn’t move into the trading industry because someone convinced me that options liquidity is the primary measure of a civilizations virtue, it was because nobody else would hire me in Australia, but a trading firm offered me a shit tonne of money.
Doing interesting work is itself an important part of the recruitment funnel, keeping some easy problems on hand for grads is another important part, and (imo) diversifying the industry out of like 2 cities (London and SanFran) would be a great way to remove a thin wedge from the top of the funnel.
Some people are going to go into whatever field they think is maximum utility, but I reckon they’re the exception. Most scientists are fundamentally amoral people who will go into whatever they find interesting, and whatever they can get work in. I’ve seen people change fields from climate research into weapons manufacturing because the opportunity wasn’t there, and ML Safety is squandering most of the world.
I think a big part of the problem is that people fundamentally misunderstand what the funnel is. The way to get people into a field isn’t rousing arguments, it’s cool results, accessible entry research, and opportunity.
As a kid, I didn’t go into pure mathematics because someone convinced me that it was a good use of my time, it was because I saw cool videos about mathematical theorems and decided that it looked fun. I didn’t move into applied maths because someone convinced me, but because there was interesting, non-trivial modelling that I could pick up and work on; and I didn’t move into the trading industry because someone convinced me that options liquidity is the primary measure of a civilizations virtue, it was because nobody else would hire me in Australia, but a trading firm offered me a shit tonne of money.
Doing interesting work is itself an important part of the recruitment funnel, keeping some easy problems on hand for grads is another important part, and (imo) diversifying the industry out of like 2 cities (London and SanFran) would be a great way to remove a thin wedge from the top of the funnel.
Some people are going to go into whatever field they think is maximum utility, but I reckon they’re the exception. Most scientists are fundamentally amoral people who will go into whatever they find interesting, and whatever they can get work in. I’ve seen people change fields from climate research into weapons manufacturing because the opportunity wasn’t there, and ML Safety is squandering most of the world.