I'm not sure that is what I'm thinking of; I seem to recall something more pessimistic than that, challenging the assertion that the less efficient factories really went out of business. "More likely to survive" != "Much more likely to survive", it may just be a statistically significant 'difference' (was it)?

What I got from Hanson's post was that people overestimated the speed of selection acting on profitability. Even though one person might be able to produce widgets half as cheaply as the next person, it might take a much longer time than people think for the first person to displace the second person, especially if the first person's lower costs per unit are due to their particular size (such that expanding would increase their costs).

Basically, you need to be actually losing money to go out of business, and even if you're making more money than the next guy, that may not translate to you making him lose money.