New paper : Eliminating all bad local optima

So there’s this new 1-page paper out.

The authors “leave it to the reader to judge whether removing local minima in this fashion is trivial, deep, or both.”

Do you all have any idea ? I don’t quite know if it’s brilliant or not. I guess one way to find out would be the Jeremy way, “try it”, but have anyone already tried or have thoughts on that?