Hacker News Reader

How often do papers like this make it to industry applications/published research. Seems stuck in between the two.

It's from industry. It's a funded research startup.

This is going to shred when it reaches industry.

But yeah very math heavy for a software engineering paper.

You seem to know your stuff.

Will this technique work with existing model weights?

Yes, it is just a way of computing the self-attention in a distributed way