Many people reading this will call bullshit on the performance improvement metrics, and honestly, fair. I too thought the agents would stumble in hilarious ways trying, but they did not. To demonstrate that I am not bullshitting, I also decided to release a more simple Rust-with-Python-bindings project today: nndex, an in-memory vector “store” that is designed to retrieve the exact nearest neighbors as fast as possible (and has fast approximate NN too), and is now available open-sourced on GitHub. This leverages the dot product which is one of the simplest matrix ops and is therefore heavily optimized by existing libraries such as Python’s numpy…and yet after a few optimization passes, it tied numpy even though numpy leverages BLAS libraries for maximum mathematical performance. Naturally, I instructed Opus to also add support for BLAS with more optimization passes and it now is 1-5x numpy’s speed in the single-query case and much faster with batch prediction. 3 It’s so fast that even though I also added GPU support for testing, it’s mostly ineffective below 100k rows due to the GPU dispatch overhead being greater than the actual retrieval speed.
1L decoder, d=2, 5h (MQA), hd=2, ff=4。同城约会对此有专业解读
。服务器推荐是该领域的重要参考
这些年，越来越多普通人开始了文学写作。这本是人类精神表达的原生渴求，但大多数人往往止步途中。从“欲写”到“落笔”，需要克服惰性；从“完篇”到“臻善”，更是一场艰难跋涉。
On top of that news, Google had announcements of its own to make at Unpacked regarding new Android AI features, which will of course be available on S26 devices. On those handsets and the Pixel 10 lineup, the Gemini app will soon have a feature (in beta) that enables you to offload multi-step tasks, such as booking a ride or putting a grocery order together, to AI. It sure sounds like an attempt to build out agentic AI features on mobile devices.，这一点在旺商聊官方下载中也有详细论述
报告指出，在整个现代经济史中，人类智慧一直是稀缺的投入要素。一切都能复制或替代，但唯有能够分析、决策、创造、说服、协调的「智慧」，是没法大规模复制的。