News for hackers. Stuff that matters.

skyriverbend

One thing that’s always struck me as strange about modern NNs is they tend to be two-dimensional and one-directional, right?

Whereas our brains are three-dimensional and have neural feedback loops. It seems clear to me that those feedback loops are an essential part of “thought”.

Any idea why more architectures don’t have neural loops built into them? Is it because they would cost too much to train? Lack of control?

No worries! `npm create tamagui` gives you a Solito app with Tamagui as the UI:

https://github.com/tamagui/tamagui/tree/master/starters/next...