Perhaps she will get into this in part 2, but a key part of the problem here is that of bad incentives, wherein a software company is punished (by the stock market or if they're not public yet, by investors who want it to go public. Most software products cannot grow beyond a certain size (whether measured as users or features or revenue), which is not a problem unless you think you have to be making a billion-user infinite growth machine. But if the people paying the salaries would rather make 1,000 bets on the Next Big Thing, and if 999 of them fail but one succeeds that is far better than 100 who fail and 900 which become medium-sized, profitable companies, then overproduction is what you get.<p>If everyone rationally responding to their incentives, produces an irrational behavior in aggregate, you have a systemic problem. We have a systemic problem.