Hacker News Reader

> That's somewhat equivalent of partially seeing the secret internal state

Not just partially, xorshift128 is designed such that the output depends only on the last 4 results. So this is "just" learning the output function of xorshift as a neural network.

View on HN

Perhaps you might consider how big that output function ideally is, then compare to the capacity of the neural network they used and the number of samples provided.

My reading of it is that it's essentially one-to-one (up to minor constant factors), they took the binary circuit for xorshift128 and replace the xor gates by functionally equivalent NN blocks, and then trained the weights.

Reply on news.ycombinator.com