Ideas & society2026 · shared on Hacker News
Show HN: KV-Cache Grafting – Boosting frozen 12B LLMs to 93.3% AIME accuracy
Explore Show HN: KV-Cache Grafting – Boosting frozen 12B LLMs to 93.3% AIME accuracy, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.
GO BEYOND THE ABSTRACT
The conversation around the idea.
Original Hacker News threads. Different perspectives, questions, and things worth thinking about.
Showing up to 100 related threads. A paper may appear in a comment rather than the original submission.
Links found in the discussion
Up to 50 recent source links, in HN item order.
YDaWe01 ·
AI Data Center Power Constraints Are the Real 2026 Bottleneck
2 points2 comments
YCorbenic ·
Show HN: KV-Cache Grafting – Boosting frozen 12B LLMs to 93.3% AIME accuracy
1 points0 comments
YWetime ·
Making models smarter and cheaper at the same time
1 points1 comments