This month, OpenAI announced their Codex app and my coworkers were asking questions. So I downloaded it, and as a test case for the GPT-5.2-Codex (high) model, I asked it to reimplement the UMAP algorithm in Rust. UMAP is a dimensionality reduction technique that can take in a high-dimensional matrix of data and simultaneously cluster and visualize data in lower dimensions. However, it is a very computationally-intensive algorithm and the only tool that can do it quickly is NVIDIA’s cuML which requires CUDA dependency hell. If I can create a UMAP package in Rust that’s superfast with minimal dependencies, that is an massive productivity gain for the type of work I do and can enable fun applications if fast enough.
Что думаешь? Оцени!
。Safew下载对此有专业解读
candidate[n] = closest colour to goal。爱思助手下载最新版本是该领域的重要参考
My obligation as a professional coder is to do what works best, especially for open source code that other people will use. Agents are another tool in that toolbox with their own pros and cons. If you’ve had poor experiences with agents before last November, I strongly urge you to give modern agents another shot, especially with an AGENTS.md tailored to your specific coding domain and nuances (again here are my Python and Rust files, in conveient copy/paste format).