Karpathy 用 Claude Opus 5.5 两小时做出 HackerTube
2 hours with Opus 5.5 on Medium effort. Not even High.
Karpathy 用 Claude Code 配合 Opus 5.5(Medium effort)约两小时做出 HackerTube:让 Claude 从 Hacker News 20 年间的 4300 万条评论中筛出 6454 条被反复推荐的视频,并搭建上线了浏览网站。他称全程只与 Claude 对话,手动部分仅是在 Google Cloud 创建 API key、启动 VPS 和购买域名,之后把 IP 交给 Claude 完成更新、加固、部署和优化。他还把评论分析数据打包成一个 zip 文件,供他人让 Claude 生成自己的版本。
查看原帖周末小项目:HackerTube。我被 YouTube 的推荐烦到了,于是让 Claude 把 HN 二十年来的 4300 万条评论筛选成 6,454 个被反复推荐的视频。观看体验*明显*更好,用 Opus 5.5 大约花了 2 小时: https://t.co/JIhXN7OSh1 - 无需任何登录就能获得优质推荐(状态保存在本地浏览器会话中) - 缩略图是视频中段的代表性画面,而不是用户上传的那种经过超级 A/B 测试极致优化的图 - 评论分析的底层数据打包成一个 zip 文件,把它交给你的 Claude,让它给你生成你自己的版本 - HackerTube Longs ✊ 再稍微说说过程: 我默认使用 Claude Code(Mac 桌面应用),Opus 5.5,Medium effort。我只跟 Claude 说话,让它做所有事,我唯一协助的“手动工作”是在浏览器里(让人想起 MenuGen):1)我得从 Google Cloud UI 创建某种 API key,用来向 YouTube 查询视频元数据,2)我启动了一台 VPS 服务器用于托管,3)我买了域名。机器起来后,我把 IP 给了 Claude,让它更新、加固、部署和优化代码,它把整套都做完了。 许多原本甚至要花几周/几个月的出色项目,现在几发提示词就能当早餐搞定。我们还有哪些没想到的?
查看原文
Weekend hack: HackerTube. I was annoyed with YouTube's recommendations so I had Claude filter down 43M comments over 20 years of HN to 6,454 videos that keep being recommended. *Significantly* better viewing experience, ~2 hours with Opus 5.5: https://t.co/JIhXN7OSh1 - Excellent recs without any logins (state is kept in local browser session) - Thumbnail is a representative frame from middle of the video instead of the super duper A/B test hyper-optimized user uploads - Underlying data from the comment analysis as one zip file, point your Claude at it and ask for your own version - HackerTube Longs ✊ A bit more on the process: I use Claude Code (desktop app for Mac), Opus 5.5 on Medium effort as my default. I only talk to Claude and have it do everything, the only "manual work" I helped with in tandem was in the browser (reminiscent of MenuGen): 1) I had to create some kind of API key from Google Cloud UI to query YouTube for video metadata, 2) I booted up a VPS box for serving and 3) I bought the domain name. Once the box was up I gave Claude the IP and told it update, secure, harden, deploy and optimize the code, and it did the whole thing. Many awesome projects that would have normally taken weeks/months even can now be few-shotted for breakfast. What else are we not thinking of.
正文 · AI 翻译
在 Medium effort 下用 Opus 5.5 花了 2 小时。甚至都不是 High。
Karpathy 不喜欢 YouTube 的推荐,于是他转而使用了 20 年来工程师们在 Hacker News 评论中不断互相推荐的那些视频。
Claude 扫描了 4300 万条评论,找到了 6454 个这样的视频,并搭建并上线了一个网站来浏览它们,这一切大约只用了两个小时。