#教程/实践

MiniMax-H3 + ORB360 LoRAで画角を自由に動かせる漫画を作ってみた。 キャラを参照画像で渡せば、顔も固定できる。

用 AirDrop 传专业设备拍的超大照片和视频（动辄 20GB）一直很痛苦。 更难受的是 iPhone 的“文件”和“相册”之间几乎不互通：在“文件”里解压一个大包，想全部存进相册，没有进度，还经常闪退，存一半都不知道存到哪了。 这两天啵啵自己把它解决了。她完全没写过代码，让 Dots 操控云端电脑写了个 App，拿到她的 Mac 上，用数据线直接装到了自己手机上。没有 Apple 开发者账号，整个 App 只有 66KB。 功能很简单：把超大的 ZIP 解压之后一张一张存进相册，能看到进度，中断了还能接着存，已经存过的会自动跳过。 刚才实测 953 个文件、15.32GB，4 分钟左右全部存完。 以前遇到这种事儿只能忍或者不断自己再试试，现在不会写代码的人也能花两天给自己做个工具了，今年 vibe coding 的发展可以说是真的震撼。

THAT'S F*CKING INSANE, GROK BOT JUST PLANNED MY TRIP TO LISBON AND BOOKED IT WITH MY CARD. I ONLY HAD TO ASK. IT HANDLED THE RESEARCH AND THE BOOKINGS. Elon Musk recently used Grok Bot to buy LEGO for his kids. That made me want to test something bigger: whether it could fully plan, research, and book my trip to Lisbon on its own. Grok Bot searched for travel options, compared prices, and booked what I needed using my card and the details I provided. Here’s what it handled: → Researched options for my Lisbon trip. → Compared prices and picked the best-priced options it found for my request. → Completed the bookings using my travel and payment details. My trip was booked. Think about how much time usually goes into this: searching, comparing options, checking availability, and filling out booking forms. This time, I gave that job to Grok Bot. That’s what makes this interesting to me. A task that normally takes my time and attention ended with real bookings after I asked an agent to handle it. Now I want to see what else I can take off my to-do list. I covered the latest major Grok Bot updates and more ways to use them in my article below. Bookmark this and read the full breakdown ↓

This is how we built the filesystem behind Perplexity Projects as a Git forge for agents. Each agent works in its own sandbox and commits to a shared repository where people and other agents can build on its work across sessions. Read more: https://www.perplexity.ai/hub/blog/building-shared-workspaces-for-people-and-agents

the slop conversation is so one sided, it's not just that you can produce more code you can also observe, debug, and refactor more code even if the code is slop you have such good tools to deal with it. even if you write code manually, it's still 100x easier to maintain it

以下是如何用 Claude Opus 5.5 + Blender + Unreal Engine + Meshy 构建这样一款游戏…… 诀窍是给每个工具只分配一项任务，但有一种聪明的设置方式： - 第 1 步：安装 Claude Code、Unreal Engine 5 和 Blender 5.1+，除了 Claude 订阅外全部免费 - 第 2 步：通过 Blender 的 MCP 插件连接 Blender，并通过 Meshy MCP 配合 API key 连接 Meshy - 第 3 步：先用 Opus 头脑风暴 5 个游戏创意，选一个，让它在开始构建任何东西之前先扩展这个创意 - 第 4 步：告诉它你的 GPU，这样它就能把画质推到你的机器能运行的极限 - 第 5 步：Meshy 生成道具和角色，Opus 将它们导入 Blender 并进行清理 - 第 6 步：Opus 把所有内容带入 Unreal：关卡、光照、HUD、小地图 - 第 7 步：试玩，然后每次提示添加一个功能：战斗、敌人、任务 谁负责什么： > Meshy：3D 模型 > Blender：清理、摆放、材质 > Unreal：光照、物理、实际的游戏 > Opus：在一个聊天中运行这三者 而真正的成本…… 一次完整首次构建大约花了 4 小时，以及每周 Max 订阅约 19% 的额度 把第一关做好，之后的关卡会快得多，因为资源已经存在了

pstack now includes 2 skills i recommend everyone use or copy: /create-verification-skill https://github.com/cursor/plugins/blob/main/pstack/skills/create-verification-skill/SKILL.md /maintain-verification-skill https://github.com/cursor/plugins/blob/main/pstack/skills/maintain-verification-skill/SKILL.md if you don't already have one, /create-verification-skill creates a skill that teaches your agent how to run, control, and debug your app. it also creates something i call the feature map: a map of all the features in your app and how to get to it and use it from a user's pov. it allows agents to navigate and use the app just like a real user which greatly increases its ability to verify its own work. but of course, this feature map goes out of date very quickly. run /maintain-verification-skill as a daily automation with cursor cloud agents. this skill will check your app for changes and keep your feature map up to date. having a strong verification skill will end up becoming critical infra for your team and become the foundation of boosting everyone's productivity and quality and also enable more interesting automations to be built. install https://cursor.com/marketplace/cursor/pstack and you'll get auto updates for my skills. enjoy!

Asking Claude to review your code is a slot machine. Every review finds brand new bugs. Review again: more. Review a tenth time: it still finds something. It never runs out of bugs to find... so how do you decide your code is actually done?

ChatGPT launched their version of Generative UI yesterday. We took it apart tldr; the agent never write raw code. It emits DIL (a new language), the server compiles and streams it, the client renders it using a component set so that it feels native https://x.com/i/article/2108220775568404480