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.
Babies are beautiful. I always want to smile at them in the street, perhaps because they are a rarer and more precious sight in this ageing country or because they remind me of my grandchildren. There are about 3.5 million children aged four and under, while dogs on the streets are a more plentiful 13.5 million. Is the dog boom compensating for fewer children? As time goes by, there are going to be ever more grandparents and ever fewer children to beam at foolishly.
，更多细节参见爱思助手下载最新版本
昨天，xAI 12 位联合创始人之一的 Toby Pohlen 发文宣布离职。
Translate instantly to 26 languages