Karpathy：高度定制化软件的时代
作者: @karpathy
原文链接: https://x.com/karpathy/status/2024583544157458452
评分: 5 | 平台: x.com | 语言: en
English | 中文
Very interested in what the coming era of highly bespoke software might look like.
对即将到来的高度定制化软件时代充满好奇。
Example from this morning - I've become a bit loosy goosy with my cardio recently so I decided to do a more srs, regimented experiment to try to lower my Resting Heart Rate from 50 -> 45, over experiment duration of 8 weeks. The primary way to do this is to aspire to a certain sum total minute goals in Zone 2 cardio and 1 HIIT/week.
今天早上的一个例子：我最近对心肺训练有点懈怠，所以决定做一项更认真、更有规律性的实验，用 8 周时间将静息心率从 50 降到 45。主要方法是在 2 区有氧训练中达到一定的累计分钟目标，外加每周 1 次 HIIT。
1 hour later I vibe coded this super custom dashboard for this very specific experiment that shows me how I'm tracking.
1 小时后，我用 vibe coding 做了一个超级定制化的仪表盘，专门追踪这个实验的进展。
Claude had to reverse engineer the Woodway treadmill cloud API to pull raw data, process, filter, debug it and create a web UI frontend to track the experiment.
Claude 必须逆向工程 Woodway 跑步机云 API 来获取原始数据、处理、过滤、调试，并创建一个 Web UI 前端来追踪实验。
It wasn't a fully smooth experience and I had to notice and ask to fix bugs e.g. it screwed up metric vs. imperial system units and it screwed up on the calendar matching up days to dates etc.
过程并不完全顺利，我不得不留意并要求修复一些 bug，比如搞混了公制和英制单位，日期和天数对不上等等。
--
TLDR the "app store" of a set of discrete apps that you choose from is an increasingly outdated concept all by itself.
总结：从一个独立应用集合中选择的"应用商店"概念本身正日益过时。
The future are services of AI-native sensors & actuators orchestrated via LLM glue into highly custom, ephemeral apps. It's just not here yet.
未来是由 AI 原生的传感器和执行器通过 LLM 胶水编排成高度定制化、临时性应用的服务。只是这个未来还没有完全到来。
*💬 12063 likes | 1015 retweets*