A test blog post.
By the way, have you ever been suspicious of PCA in high dimensions?
Check out the results of PCA of high dimensional random walks with comparison to neural network training
by J. Antognini and J. Sohl-Dickstein (2018).
The authors show that the \(k\)-th principal component of a random walk corresponds to (asymptotically, in dimension) the \(k\)-th Fourier mode.