FWIW I strong-disagreed that comment for the latter part:
Gradient descent isn’t really different from what evolution does. It’s just a bit faster, and takes a slightly more direct line. Importantly, it’s not more capable of avoiding local maxima (per se, at least).
I feel neutral/slight-agree about the relation to the linked titular comment.
FWIW I strong-disagreed that comment for the latter part:
I feel neutral/slight-agree about the relation to the linked titular comment.