22 points chenglou 1 day ago 7 comments

dvrp 1 day ago | parent

I think for everyone interested in this project checking your OG twitter thread is also somewhat mandatory:

https://x.com/_chenglou/status/2110557373651931267

It took me a bit to wrap my head around what you did.

seamossfet 1 hour ago | parent

Clever, I wonder what would happen if you did this in reverse? Like, if we froze the weights then added some layers trained on a bunch of weird edge cases then tried to convert those weights back into branches.

QA through entropy lol

auraham 57 minutes ago | parent

It seems interesting but I am confused. What is the purpose of that landing page? It is not clear since it showcases several (not related) ideas:

- turning js code into something else, arguably high-level code for training neural networks

- a mini OS inside the browser

- a gallery

- document search

echoangle 51 minutes ago | parent

I think this is basically a compiler that turns arbitrary JS code into weights of a neural net that then behaves exactly like the JS program. And the stuff at the bottom are demo projects that are now running as a neural net.

freecodeio 49 minutes ago | parent

the "DEMOS" label is rather small, I understand the confusion

gregsadetsky 50 minutes ago | parent

As far as I understand, this doesn't turn "regular" JavaScript into a NN, it's rather "write your logic in a DSL that creates a neural-net-shaped circuit"

the source code for the OS demo is not "regular" code, it's full of `emiRelu`... https://github.com/chenglou/handwired/blob/main/src/handwire...

The main site & readme seem to overclaim, while the docs say things like "With Handwired you write a numeric program" and "No tool converts existing JavaScript source into a program" - https://github.com/chenglou/handwired/tree/main/docs

happy to be proven wrong, to have misunderstood this, etc.