Can 1.8 Billion Stars Recreate the Milky Way We Photograph?
Starting from the simplest "one star, one pixel" rendering, eight failures and 600 million stars later, the Milky Way slowly emerged from a real star catalog.
Reading
Starting from the simplest "one star, one pixel" rendering, eight failures and 600 million stars later, the Milky Way slowly emerged from a real star catalog.
从最直白的"一星一像素"出发,八次翻车、六亿颗星,一步一步把银河从真实星表里逼出来。在这个过程中才发现,以前从来没认真想过头顶的星空为什么长这个样子。
Step two isn't better prompting. It's externalize first, reuse second. This post explains how Skills carry work knowledge, the three parts of a good Skill,...
用好AI的第二步不是更会写 prompt,而是先外化、再复用。本文讲清 Skill 如何承载工作知识、好 Skill 的三要素,以及如何组织 Skill 文件夹让 Agent 自动找到。
After weeks of severe insomnia, I used AI to build an iOS app that exported HealthKit data and ran multivariate regression to find the root cause—late-night...
作为一个重度AI用户,我在经历长期严重失眠后没有走常规的"排除变量"路线,而是用AI写了一个iOS app导出HealthKit数据,做多变量回归分析找到了真正的原因——晚上使用AI高强度思考。这篇文章分享了AI如何在全链条上提供执行力支持,也反思了人的judgment和认知上的成本结构,在AI时代如何重塑我们的决策路径。
LLM的默认输出是consensus:正确但平庸。Deep Research其实是Wide Research。我们找到了一种系统性方法,用个人认知上下文把LLM从consensus里强行扯出来。一年实验,有控制变量证据。