Apparently providing this messy rough categorization appeared to help in some cases. From the article:
> To force CheXzero to avoid shortcuts and therefore try to mitigate this bias, the team repeated the experiment but deliberately gave the race, sex, or age of patients to the model together with the images. The model’s rate of “missed” diagnoses decreased by half—but only for some conditions.
In the end though I think you're right and we're just at the phases of hand-coding attributes. The bitter lesson always prevails
https://www.cs.utexas.edu/~eunsol/courses/data/bitter_lesson...
> Also important was the use [in Go] of learning by self play to learn a value function
I thought the self-play was the value function that made progress in Go. That is, it wasn't the case that we played through a lot of games and used that data to create a function that would assign a value to a Go board. Instead, the function to assign a value to a Go board would do some self-play on the board and assign value based on the outcome.