One more important thing to understand about Jobs "miracle" is that he was allowed to do what he was obsessed with. No idiotic "manager" or board member intervene with ideas of "cutting costs" on packaging or materials or any other fast-food technologies to reduce the product to the mix of cheapest and crapest ingredients imaginable. No idiots insisted that it is much more "effective" to just add a "theme" to and old code, to make it look like touch-capable (hi Symbian, WinCE) etc. No one said that re-implementing from scratch, because everything else is crap is costly and time-consuming, and so on.
There are lots of people with good taste, sense of style and quality (read Pirsig's book) and enough self-discipline to follow do what one is preaching, but it is an extreme rare situation when such people have enough influence to make things their own way.
I guess a half of YC business is about trying to spot an employ such obsessed individuals, no matter what exactly they want to accomplish. Early funding of even one of such guys worth waiting and funding hundreds of mediocre, especially if one has connections to channel or sell them off.)
Igor Sysoev was obsessed with efficiency (in that time c10k problem was actual), so src/core and src/os/unix should be taught in colleges (btw, the module system is already an over-engineered mess).
There are many other examples, but the big idea is simple - spot the right people, all that numerous micro-optimizations, while valuable, are superficial.
They are, but the causes are even uglier and grounded deeply in so-called human nature which cannot be changed. So, less-naive approach is to understand and accept things as they are.
There are lots of people with good taste, sense of style and quality (read Pirsig's book) and enough self-discipline to follow do what one is preaching, but it is an extreme rare situation when such people have enough influence to make things their own way.
I guess a half of YC business is about trying to spot an employ such obsessed individuals, no matter what exactly they want to accomplish. Early funding of even one of such guys worth waiting and funding hundreds of mediocre, especially if one has connections to channel or sell them off.)
Igor Sysoev was obsessed with efficiency (in that time c10k problem was actual), so src/core and src/os/unix should be taught in colleges (btw, the module system is already an over-engineered mess).
There are many other examples, but the big idea is simple - spot the right people, all that numerous micro-optimizations, while valuable, are superficial.