jacobpedd

> For best results, our project structure needs to be set up with LLM workflows in mind. Specifically, we should carefully manage and keep the cognitive load required to understand and contribute code to a project at a minimum.

What's the main barrier to doing this all the time? Sounds like a good practice in general.

> A lightweight neural network is then used to reconstruct a hole-free image including detail beyond splat resolution.

Seems like if you added a similar super resolution step to 3DGS you would get similar detail improvements?

This is awesome guys!

Api companies should use this as a playground

You’re totally right. Missed the the second Sunday part.

Wasn’t aware of the SUN#2 syntax. I find it interesting it used 8,14 as its best approximation. You can see it trying it’s best.

There is a trailing ') from a bug that I just fixed. I don't think that's correct. Tricky prompt!

Ya, sadly there's a rolling "requests per minute" on my OpenAPI account.

A very good chance actually! Stay tuned

I added your example to the training data and it seems like it helped it learn exceptions. Here's the result for your prompt:

0 0 8-14 1-4,6-12 *

Thanks, fixed!