speck1447

It is fashionable, on LessWrong and also everywhere else, to advocate for a transition away from p-values. p-values have many known issues. p-hacking is possible and difficult to prevent, testing one hypothesis at a time cannot even in principle be correct, et cetera. I should mention here, because I will...

TL;DR * One major obstacle to interpretability is that complicated neural nets don't tell you where or how they're representing important concepts, and methods to find these representations are imperfect. * This problem is less present in simple neural networks, so one natural idea is to initialize a complicated neural...