This is all so unscientific and unmeasurable. Hopefully we can construct more order parameters on weights and start measuring those instead of "using claws to draw pelicans on bicycles"

"Dance has Labanotation. Music has staff notation. Architecture has plan/section/elevation conventions. GNL brings the same rigor to garments — a generative descriptive language where a valid expression is sufficient to construct a garment without ambiguity."

AI lmao

Holy shit there is so much cope in this thread. Give the boy his props

The brain trims it's context through forgetting details that do not matter

LLMs will have to eventually cross this hurdle before they become our replacements

Beautiful

Yes, reminds me of Proce55ing in its prime, used for complex webviz like this. I love this so much.

Dioxus is the real deal. It makes it super easy to create web-apps

I went from knowing nothing about web stuff to building this tool https://chakravarthysoftware.com/work_distributor in a week

AI designed websites are so easy to spot that I need to actively design my UI so that it doesn't look AI

Literally just find and replace

find and replace is step 1 that generates all the compile errors I want it to loop through

I'm wanting to do it on an entire programming language made in rust: https://github.com/uiua-lang/uiua

Because there are no float32 array languages in existence today

Why do you want a float32 array language? Anyway the free glm4.6 model that is opencode defaults to should be fine. Why pay for something to do this.

I want to use an array language for Real-time 3D. Float32 is faster for real-time calculations and can map memory directly to the GPU since 3D graphics runtimes are limited to float32.

AI is mostly garbage at creating useful abstractions. I'd feel threatened if I was a competitive programmer or IMO kid

Tell me you haven’t used codex-xhigh without telling me you haven’t used it. It’s bad at overall architecture and big picture. But not at useful abstractions.

Cursor browser all over again