Mac Productivity · X leaderboard

High-engagement posts and top-performing creators across tracked niches on X (Twitter), refreshed every 15 minutes.

Live pipeline active: 10/16 tracked source sets active in this window. Posts and creator metrics refresh continuously every 15 minutes.

Top posts
88
Top creators
65
Total likes
26.8K
Last updated
just now

Top posts

1
B. Bunny@bbunny013·313 followers·2d ago

I just laugh at this every time, lol #JonDami #Supersons #Alfred https://t.co/JKdFDhdESq

2,892250410.8K
2
MacRumors.com@macrumors·1.4M followers·5d ago

Apple Announces 'Full Disk Access' Changes on macOS Due to AI Agents https://t.co/GAj2ESeM9t https://t.co/5gEj28HsZx

2,437133109—
3
Riley Brown@rileybrown·252.2K followers·5d ago

Every day i'm blown away at what i can do in an hour with frontier models like Opus 5.5. I didn't know what to do with an old iPhone, so I built Bluey, w/ Opus 5.5. It's powered by GPT Realtime 2 (i think... whatever Opus decided to use). Bluey is an iOS app + mac app that is made to be a computer companion. It can point, comment, and even control my entire computer. github repo below

1,465100114104.6K
4
uncle pussy@ukeswitzerland·161 followers·4d ago

New Alfred ship dropped 👀👀👀👀 https://t.co/s7W0CPsTg5

1,40822924907
5
Vaibhav Sisinty@vaibhavsisinty·175.5K followers·6d ago

The interview with @thsottiaux from OpenAI 🔥 0:00 Everything OpenAI launched at DevDay 2:44 Sponsors: Wispr Flow, Hostinger, OpenArt 4:11 What is ChatGPT Dots? 7:52 Will ChatGPT Dots be free? 10:15 GPT-6.1 Sol vs GPT-6 Astra 11:44 Is AI now building AI? 12:53 Ultra Fast: when does everyone get it? 14:00 How OpenAI rebuilt the ChatGPT desktop app in 30 days 19:08 Why everything will run in the cloud 20:55 Calling your Dots on the phone 22:11 The new Turing test 24:05 OpenAI's mission and AI safety 26:14 Why OpenAI still works like a startup 27:29 The truth about ChatGPT usage resets 29:00 The $500 ChatGPT plan 30:17 Sponsors in action 32:23 Why AI agents still fail 33:52 OpenAI's AI is now on call 34:26 OpenAI's internal benchmarks 35:55 Open source Codex and the open ecosystem 38:42 ChatGPT Space explained 39:45 Is the chat box holding AI back? 42:26 Every DevDay update, full workshop 43:28 How people really use ChatGPT Work and Codex 44:01 When is the next Op

1,132164168485.3K
6
🚨 AI News | TestingCatalog@testingcatalog·79.3K followers·6d ago

GOOGLE 🔥: Gemini Desktop will have a "Full Access" permission for computer use, allowing it to access any file and run any app on your desktop. > A new "Additional sandbox options" setting has been added to the recent Gemini Desktop app (Still hidden). > "By enabling additional sandbox options, you will be able to expand what Gemini can do and access on your Mac. Depending on which settings you enable, Gemini may be permitted to take actions without asking for your permission first, including: - Reading, creating, modifying, or deleting files anywhere on your Mac, including files outside your connected folders and files belonging to other people stored on your device - Sending and receiving data over the network without your approval for each connection, including accessing websites, APIs, and services you are logged into - Communicating with other applications on your Mac (such as Mail, Safari, or Messages) and performing actions through them." > Gemini will still ask user perm

1,127816367.3K
7
Luke The Dev@iamlukethedev·15.4K followers·1d ago

I built an operating system where the AI agent isn’t another app. It’s part of the OS. Today, Herald OS is open source and you can install it yourself 🚀 It’s built around Hermes Agent by Nous Research. Talk or type to Hermes and it can work across your entire computer: • Open and use apps • Find, organize and work with your files • Remember what matters • Run routines and automations • Build software while you watch • Understand what’s happening on your screen • Work across the machine instead of being trapped inside a chat window And when something is about to make a change, you approve it first. 🎙️ Talk to your computer Say “Hey Hermes” and just talk. Native OS commands don’t need to burn model tokens. When you actually ask the agent to think, build or perform a task, that’s when Hermes gets involved. ⚡ Everyday superpowers • Select any part of your screen and ask Hermes about it • Pick a colour from anywhere • Read a QR code from your screen • Copy text from anywhere on

93610312968.9K
8
lifcc@mylifcc·12.7K followers·3d ago

终于有人把 Apple Intelligence 彻底干掉了……不仅省出 12GB,风扇都不怎么转了。 如果你平时完全不用苹果自带的 AI(写作工具、Genmoji、照片 Clean Up 这些),可以看看刚开源的 CLI 小工具 —— RemoveMacAI。 它比手动删缓存高级的地方在于: • 合规原生:不碰 /System 分区,无需关闭 SIP,利用苹果官方的配置描述文件(Profile)进行策略限制。 • 防止复活:把模型的远程拉取端口重定向到本地无效端口,治好了系统更新/后台静默重装的毛病。 • 无痛撤销:打一句 removemacai revert 原地满血复活。 觉得系统变臃肿、或者只想留着算力跑自己的本地开源模型的,可以去折腾一下。 #开发者日常 #MacBookPro #技术分享 #GitHub探索

9311162985.7K
9
MacRumors.com@macrumors·1.4M followers·2d ago

macOS 27.2 Adds Touch Gestures Ahead of MacBook Ultra https://t.co/8e7Z5CLTRL https://t.co/HiT0P5Gk8T

7762927—
10
Mike Alfred@mikealfred·347.2K followers·2d ago

If I did a Space this afternoon after the market closes, would you be interested in joining?

7201413640.9K
11
宝玉@dotey·256.4K followers·3d ago

学习研究了下 amontlabs/lcu 这个项目,它把 Codex 的 Computer Use(让 AI 看屏幕、点鼠标、敲键盘来操作电脑的能力)单独拆了出来,让 Claude Code、Codex CLI、Pi 等其他 AI Agent 工具也能调用。 我本来还以为它是模仿 Codex 实现了一套,原来是直接用的 Codex 的 Computer Use,在本机找到已安装的 ChatGPT 桌面版,启动其中 OpenAI 自带的 Computer Use 运行时,再通过 MCP 接到你用的 Agent 工具里。仓库文档写明,指令、执行和权限策略都以 OpenAI 原版运行时为准。 因此电脑上必须装有官方 ChatGPT 桌面版,但不需要登录 ChatGPT 或 Codex 账号。 它给模型的工具很少。常见的电脑操控方案会把截图、点击、输入、滚动各做成一个工具,LCU 只给两个:js 和 js_reset。 js 用来执行一段 JavaScript 代码,运行环境里预置了一个名为 cua 的对象。模型通过写代码来操作电脑:先调用 cua.getState() 拿到当前桌面状态和使用说明,再用 getApp 选定某个窗口,然后调用 click、typeText、pressKey、getScreenshot 等方法。点击、输入、读取结果可以写在同一段代码里,一次调用完成。 这个 JavaScript 环境会保留状态,上一次调用里定义的变量,下一次还能接着用;环境出问题时调用 js_reset 清空重来。除了截图,模型还能读取窗口的无障碍信息(操作系统提供给读屏软件的界面元素列表),按元素点击,不必完全依赖屏幕坐标。 js 加 cua 对象这套接口是 OpenAI 原版的设计,LCU 原样转发。仓库记录显示,在 macOS 上对比测试时,模型收到的初始化说明和首次调用返回的使用指南,与官方 Codex 收到的内容逐字节一致。 目前正式适配的 Agent 工具是 Pi、Codex CLI 和 Claude Code,Oh My Pi 和 Hermes 为实验性支持。系统支持 Apple Silicon 芯片的 macOS(需授予辅助功能和屏幕录制权限),以及使用 X11 桌面的 Linux(ARM64 和 x86-64)。Windows 11 尚在候选阶段

568936758.6K
12
MacRumors.com@macrumors·1.4M followers·3d ago

Mac Users Reclaim Storage With New Apple Intelligence Removal Tool https://t.co/DL0aFgYA6Z https://t.co/U3asjQGpNG

5603521—
13
MacRumors.com@macrumors·1.4M followers·3d ago

Apple Quietly Triples iCloud Mail Alias Limit to Nine https://t.co/2PqVKAyQPO https://t.co/8ptlsyV7I5

5482811—
14
Yume_X@yume_arasaki·2,417 followers·2d ago

Insane developments have been happening on Qwen 3.8 Flash. In 2 weeks, suddenly everyones computer can run Qwen 3.8 Flash. I wanted to find out what happened and why everyone in local AI is using this model now. Every number below is a receipt I verified, my own hardware or community, and the ones from my fleet live in my bench repo. Here is what I found. WHY THIS MODEL Qwen3.8-Flash-Next is a 180B parameter MoE that only activates around 6B per token. On Artificial Analysis it scores 40 on the intelligence index against Claude Opus 4.8 at 42. It beats Opus on Terminal-Bench 4.0 (25 percent against 22), AutomationBench (56 against 46), and GDPval. Opus still wins Humanity's Last Exam (49 against 38) and SWE-bench Pro (69.2 against 62.5, each vendor's own harness). My read: Opus-class on agentic and coding work, one step behind on the hardest reasoning. People call it Qwen 3.8 Flash. Same model. WHY IT RUNS ON ALMOST ANYTHING EXPLAINED Traditional LLM understanding is eve

392383227.2K
15
Humphrey’s tail. Guided by Lord Alfred & Clarence@diaryalfred·5,662 followers·3d ago

Just surveying my kingdom. I’m rather pleased they chose me ☺️ https://t.co/XNatGsO67X

37310312,337
16
Su@sukiea1008·4,013 followers·20h ago

在小红书上发现一个博主开源了一款工具 把你的 macbook 变成 mac mini 合上盖也能继续跑,对我来说完全帮大忙,我之前是外置欺骗器的! 并且完成了 Apple 公证,下载即用 仓库地址我放在评论区了👇 https://t.co/nRsu9ZxCYT

367463947.4K
17
MacRumors.com@macrumors·1.4M followers·18h ago

ChatGPT Gets GPT-6 and New Intelligent UI With Visual Answers https://t.co/1kF4F8MelG https://t.co/eGFKOunwW7

333135—
18
Mason@mason0x_·3,649 followers·5d ago

昨天在一条 78 万浏览的帖子底下回了一句:一个 Surge 什么都搞定 今天把我家怎么配的写出来了:一台 Mac 当全家网关,家里设备连上 Wi-Fi 就能刷 X,iPhone 回家自动停代理、出门自动接上,不用买软路由 https://t.co/uFLhf8PexP

326641363.2K
19
Passenger0522@passenger0522·2,707 followers·2d ago

前几天发了张我番茄小说后台的截图,评论区不少朋友都在问:长篇写到几万、几十万字,到底怎么解决长期记忆和剧情失忆吃书的问题 大模型的大上下文窗口根本不等于剧情逻辑的连续性,真正能写长篇不崩的系统,核心全在状态锁、角色知识边界和改稿后的级联更新 这几天我把 GitHub 上主流的开源小说项目和代码实现深入扒了一遍,筛出 5 个最有代表性的方案,把各自的优缺点、核心机制和实操避坑点整理出来,大家按需对号入座: oh-story(Codex 深度写手首选) 定位:把选题、拆书、长篇写作、审读和去 AI 味打包成一系列 Skills,直接跑在 Codex 里 核心亮点:最硬核的是“追踪提交协议”,采用权威 JSON 状态配合串行锁,强制把“世界客观真相”、“读者已知信息”和“角色主观知晓”三层分开,反派密谋的事情主角绝对不会在下一章未卜先知,彻底解决偷看剧本的问题;写到后文回头大修旧章时,支持级联扫描并列出后续章节的所有冲突 实操避坑:安装了文件不代表门禁已经生效,装完后必须新开会话跑 story-setup 检查诊断报告,确认本地 hooks 已经获得宿主信任 项目地址:https://t.co/SXAZfxzPl9 MuMuAINovel(独立中文网页工作台首选) 定位:不想碰终端命令,想要类似作家助手那样开箱即用的 Web 界面,选这个最合适 核心亮点:世界观、人物关系谱、大纲、伏笔台账全部可视化,支持 TXT 拆书反推大纲,内置了 ChromaDB 和本地 ONNX Embedding,不需要额外付向量 API 的钱,Docker 镜像原生支持 Mac 和 Apple Silicon 实操避坑:在网页上手动修改正文,系统不会自动重新计算记忆,大改旧章后,必须在分析弹窗里手动点击“重新分析”;另外用 Docker 部署前,建议把 Chroma 向量目录挂载到本地宿主机,防止容器重启丢记忆 项目地址:https://t.co/YAiCTAJMsi Ani Book Skill(本地工程与小说宇宙资产) 定位:追求稿件和数据完全私有,想写系列作品或多部小说共享世界观的极客方案 核心亮点:所有的连续性事实全放在人类可读的 YAML 文件里,SQLite 只是可随时重建的查询索引,底层资产永远掌控在自己手里;支持将已验收的角色和设定沉淀为共享资产包

316582828.4K
20
Tw93@hitw93·161.1K followers·6d ago

今天终于把拖了很久的事情,放到一天给做了,我把 Mole 从开售到9月底所有没有激活的用户全部发送了一封邮件,这个过程挺有感触,顺便又做了一个有趣小魔法功能。 用 AI 写了一个简单的本地脚本把用户邮箱、Key 给列了,然后一封一封根据月份、国家语言把 license key 重新发了出去,不是促销邮件,也不是催促激活,更多就是发一个微信一样告诉用户不要忘记了。 有意思的是,陆陆续续收到了非常多各个国家用户的回信,比我预想的要有意义很多。 有用户说买来就是想支持你的开发,自己更喜欢用 terminal 版本;还有人完全忘记了 GUI,一直在使用 CLI; 也有用户非常用心,买了两个,一个给自己,一个给家人,打算当圣诞节礼物,没有没有激活,已经存到了自己的密码管理器,让我这个世界真美好。 也有用户最开始公司的电脑可以用,但是由于对未在公司范围的软件进行的禁止使用,他一直在等他自己的新 Mac,等新 Mac 到了他就可以用了;也有用户是在我打折的时候买的,现在还没有 MacBook,等自己新机到手就立马去激活。 不过其中有一些用户其实是邮箱填写错了,可能是打太快了,把邮箱写成了 gmai、con、cloud 这一类 ,也没有找我;也有用户是第一封邮件没有收到,想着更快使用又继续买了一遍。 虽然这里没有收到激活码的用户占总用户比例非常小,也有不少在每日的答疑邮件中帮忙解决了,可能对于不少做 App 售卖的公司而言,会认为收到钱以后这段关系就结束了,不过对于Mole而言,我感觉才刚刚开始,后续和用户持续共建可以做非常多有趣的事情。 用户买到软件以后,也不一定会里面用,并不是我们开发者自己想的「看到->买->立马用」,其实也有是随手买一个,key 进来收件箱,想到了再去用,或者付钱但没有收到 key,这里好比有一段购买到真正使用的空白在开发者和用户之间的,有不少用户会主动往前一步找开发者问我的key呢,但是也有部分用户没有迈出这一步,对于这种情况,开发者应该多迈出去。 做产品的人,特别是工程师出身的,非常用于在产品功能上较劲,疯狂开发功能,很容易忽视从购买流程数据去看用户的真实使用,真实体验,以及围绕非产品功能的体验去做优化,这也是和用户交流的一个非常好的场景和渠道,真实的交流很重要,也会让你对自己做的产品更有成就感。 程序员天然会喜欢做可扩展的事情,任何

300124835.1K

See also the rising posts and top creators in this niche.

Top creators

CreatorTotal likes
1
MacRumors.com
@macrumors
5,791
2
B. Bunny
@bbunny013
2,892
3
Riley Brown
@rileybrown
1,730
1,439
5
uncle pussy
@ukeswitzerland
1,408
6
Vaibhav Sisinty
@vaibhavsisinty
1,132
7
lifcc
@mylifcc
1,042
8
Luke The Dev
@iamlukethedev
936
9
Mike Alfred
@mikealfred
720
10
宝玉
@dotey
568
11
Tw93
@hitw93
485
12
Noah Kagan
@noahkagan
413
13
Raycast
@raycast
409
14
Yume_X
@yume_arasaki
392
373
16
Su
@sukiea1008
367
17
Mason
@mason0x_
326
18
Passenger0522
@passenger0522
316
19
Wispr Flow
@wisprflow
305
20
ana howard
@anaarsonist
276

About X Analytics leaderboards

Top-performing X posts about macOS productivity apps, developer workflows, and desktop utilities — Raycast, Alfred, CleanShot, and native AI tools — ranked by community engagement.

X Analytics tracks high-engagement X posts and the creators behind them — delivering continuous x analytics and x growth benchmarks for finding rising voices, viral topic formats, and high-traction product discussions.

Rankings are built from continuously collected high-engagement posts across tracked topic keywords and key accounts. Creator rankings reflect authors whose posts meet category thresholds. Data is updated in 15-minute scheduled intervals.