探索 | Thread Easy - Twitterスレッドを展開 | リーダー・要約・作成

Started doing this two days ago, every morning before breakfast. Just jot down what I really have to get done today (out of the week roadmap), and just focus on them. Honestly, it heeeeeeeelped so much!

CEO @Plutio_app - Shaping the future of freelancing with the world’s first Super Work AI. Acquired in a $10M talent deal. Ex–Head of Brand @ClickUp.

Leo Bassam 🤌🏼

Sat Dec 06 10:13:05

讓手機端的 NotebookLM App 成為「快速接住」當下閱讀想法、會議重點、上課啟發的工具。之前很陽春的 NotebookLM App ，最近更新後，終於可以使用「內建相機」、「匯入錄音檔」，以及製作「資訊圖表」與「圖像式簡報」，還能同步「收聽 AI 生成語音談話進度」等功能。這讓 NotebookLM App 成為更便捷的隨身學習、會議整理筆記助手（用在輔助，但依然不適合做為我們真正的筆記系統喔～）： 1. 讀到書中覺得有感的一頁 → 直接用 NotebookLM App 拍下那一頁／那張圖。 2. 會議、課程中有想法來不及打字 → 先用手機錄音 → 再匯入 NotebookLM App。然後在手機 App 端也能快速用 AI 生成語音摘要、學習閃卡、資訊圖表、說明簡報。下面跟大家分享兩個我的實際應用案例： - 用 NotebookLM App 讀書的新方法，只要拍頁面＋錄想法，就能做出會說話的讀書筆記。 - 會議還沒結束，結論就整理好了：NotebookLM App 用拍照＋錄音幫你做出課後／會後重點。試試看，把 NotebookLM App 定位成「讓你之後可以第二次閱讀、第二次聽課」的工具：

經營電腦玩物部落格，撰寫生產力工具技巧、筆記方法、時間管理等相關文章。

電腦玩物站長 Esor

Sat Dec 06 10:10:05

It was clear before LLMs ever existed, and this effect will scale to AGI and to superintelligence. This is just how intelligence works and has always worked.

entirelyuseless

Sat Dec 06 10:01:39

I love the Polish railway network, but calling your on-train restaurants “WARS” feels… suboptimal.

CPO at https://t.co/BNZzlkTfVp. Founder of https://t.co/hOAmca8qLm and https://t.co/dRwgbZCSOw. Coffee-making, parenting, building, exploring: RU → CN → NZ → CL → UK → NZ → PL → UK?

Stas Kulesh

Sat Dec 06 10:00:08

学编程时想找点实战项目练手，网上教程要么太简单没挑战性，要么直接扔个复杂项目源码，不知道从哪学起。在 GitHub 上发现 project-box 这个 C 语言项目合集，专门为初学者准备，从基础到进阶循序渐进。收录了 10 个独立项目，涵盖算法实现、网络编程、编译器设计和游戏开发，每个项目都配有完整文档和构建系统。 GitHub：https://t.co/w3Bv2YJzIS 包括 SHA-512 加密算法、HTTP 服务器、UDP 通信、端口扫描器、Ping 工具、井字棋游戏、实时聊天系统、词法分析器、算术编译器和小行星躲避游戏。项目难度从易到难排列，建议从井字棋开始熟悉基础概念，再逐步挑战网络编程和编译器项目，适合想系统学习 C 语言的同学。

💡 挖掘开源的价值 🧑🏻‍💻 坚持分享 GitHub 上高质量、有趣、实用的教程、AI工具、前沿 AI 技术 🧐 A list cool, interesting projects of GitHub. ✏️ 公众号：GitHubDaily

GitHubDaily

Sat Dec 06 10:00:06

multi-agent architecture is the new micro-service architecture for the majority of use cases, it’s a mistake: worst performance, harder to debug, more expensive, slower deployment, etc. start with one agent, only break it down if you can measure how it’s better than one agent

Built 8 startups in 12 months • Sold 3/8 startups • Building https://t.co/ns7SH9FiWh, https://t.co/1tAr7flVT2, https://t.co/pL2Vv5UTCK, https://t.co/sYr4JzzOtJ, https://t.co/HvvzdvWg5H, & a secret startup 🤫

Minh-Phuc Tran

Sat Dec 06 09:55:51

探索

Newest first — browse tweet threads

探索

Newest first — browse tweet threads

Started doing this two days ago, every morning before breakfast. Just jot down what I really have to get done today (out of the week roadmap), and just focus on them. Honestly, it heeeeeeeelped so much!

It was clear before LLMs ever existed, and this effect will scale to AGI and to superintelligence. This is just how intelligence works and has always worked.

I love the Polish railway network, but calling your on-train restaurants “WARS” feels… suboptimal.

multi-agent architecture is the new micro-service architecture for the majority of use cases, it’s a mistake: worst performance, harder to debug, more expensive, slower deployment, etc. start with one agent, only break it down if you can measure how it’s better than one agent