An incomplete list of caveats to Sharpe off the top of my head:

• We can never measure the true Sharpe of a strategy (how it would theoretically perform on average over all time), only the observed Sharpe ratio, which can be radically different, especially for strategies with significant tail risk. There are a wide variety of strategies that might have a very high observed sharpe over a few years, but much lower true Sharpe
• Sharpe typically doesn't measure costs like infrastructure or salaries, just losses to the direct fund. So e.g. you could view working at a company and earning a salary as a financial strategy with a nearly infinite sharpe, but that's not necessarily appealing. There are actually a fair number of hedge funds whose function is more similar to providing services in exchange for relatively guaranteed pay
• High-sharpe strategies are often constrained by capacity. For example, my friend once offered to pay me $51 on Venmo if I gave her $50 in cash, which is a very high return on investment given that the transaction took just a few minutes, but I doubt she would have been willing to do the same thing at a million times the scale. Similarly, there are occasionally investment strategies with very high sharpes that can only handle a relatively small amount of money

This is very, very cool. Having come from the functional programming world, I frequently miss these features when doing machine learning in Python, and haven't been able to easily replicate them. I think there's a lot of easy optimization that could happen in day-to-day exploratory machine learning code that bog standard pandas/scikit-learn doesn't do.

If N95 masks work, O95-100 and P95-100 masks should also work, and potentially be more effective - the stuff they filter is a superset of what N95 filters. They're normally more expensive, but in the current state I've actually found P100s cheaper than N95s.

One key dimension is decomposition – I would say any gears model provides decomposition, but models can have it without gears.

For example, the error in any machine learning model can be broken down into bias + variance, which provides a useful model for debugging. But these don't feel like gears in any meaningful sense, whereas, say, bootstrapping + weak learners feel like gears in understanding Random Forests.

I think it is true that gears-level models are systematically undervalued, and that part of the reason is because of the longer payoff curve.

A simple example is debugging code: a gears-level approach is to try and understand what the code is doing and why it doesn't do what you want, a black-box approach is to try changing things somewhat randomly. Most programmers I know will agree that the gears-level approach is almost always better, but that they at least sometimes end up doing the black-box approach when tired/frustrated/stuck.

And in companies that focus too much on short-term results (most of them, IMO) will push programmers to spend far too much time on black-box debugging than is optimal.

Perhaps part of the reason why the choice appears to typically be obvious is that gears methods are underestimated.

Black-box approaches often fail to generalize within the domain, but generalize well across domains. Neural Nets may teach you less about medicine than a PGM, but they'll also get you good results in image recognition, transcription, etc.

This can lead to interesting principal-agent problems: an employee benefits more from learning something generalizable across businesses and industries, while employers will generally prefer the best domain-specific solution.

Nit: giving IQ tests is not super cheap, because it puts companies at a nebulous risk of being sued for disparate impact (see e.g. https://en.wikipedia.org/wiki/Griggs_v._Duke_Power_Co.).

I agree with all the major conclusions though.

For the orthogonal decomposition, don't you need two scalars? E.g. $x=ay+bz$ . For example, in $R^2$ , let $x=(2,2),y=(0,1),z=(1,0).$ Then $x=2y+2z$, and there's no way to write $x$ as $y+az.$