News for hackers. Stuff that matters.

A comment on Attention at Constant Cost per Token via Symmetry-Aware Taylor Approximation.

Re:Attention at Constant Cost per Token via Symmetry-Aware T... by yanosh_kunsh on Wednesday February 04, 2026 @10:21AM (#46886911)
So does that mean that LLM inference could go down significantly in price and/or context length would dramatically increase?
[ Parent | on HN ]

There are no comments on this comment yet.