LogoThread Easy
  • 탐색
  • 스레드 작성
LogoThread Easy

트위터 스레드의 올인원 파트너

© 2025 Thread Easy All Rights Reserved.

탐색

Newest first — browse tweet threads

Keep on to blur preview images; turn off to show them clearly

Chad IDE (@cladlabs) is the brainrot code editor.

AI coding takes 1–5 min between prompts—too long to ignore, too short to start something new. 

Chad integrates your brainrot (X, IG, Stake, Tinder, etc) into your agentic coding workflow and helps to manage your context-switching.

Less doom-scrolling. More shipping.

Chad IDE (@cladlabs) is the brainrot code editor. AI coding takes 1–5 min between prompts—too long to ignore, too short to start something new.  Chad integrates your brainrot (X, IG, Stake, Tinder, etc) into your agentic coding workflow and helps to manage your context-switching. Less doom-scrolling. More shipping.

We help founders make something people want. Subscribe to our newsletter: https://t.co/sjqjxxBeLc

avatar for Y Combinator
Y Combinator
Tue Nov 11 22:00:28
remember when you could just grab someone's phone when they went to the bathroom and tweet "poopin"?

remember when you could just grab someone's phone when they went to the bathroom and tweet "poopin"?

Senior Dev @Zillow. Creator of @PushSilver. Co-creator of @Laravelphp Nova (sold 2024), @TailwindCSS, and @ChipperCI.

avatar for Hemp
Hemp
Tue Nov 11 21:59:42
Today I decided to replace the KL penalty with some yolo crazy approach, which worked. When looking at it closely it is the standard KL penalty with a minor but very important change that assures a property I tried to obtain months ago without success. Today is a good day.

Today I decided to replace the KL penalty with some yolo crazy approach, which worked. When looking at it closely it is the standard KL penalty with a minor but very important change that assures a property I tried to obtain months ago without success. Today is a good day.

Research Scientist @meta (FAIR), Prof. @Unige_en, co-founder @nc_shape. I like reality.

avatar for François Fleuret
François Fleuret
Tue Nov 11 21:53:16
Today I decided to replace the KL penalty with some yolo crazy approach, which worked. When looking at it closely it is the standard KL penalty with a minor but very important change that assures a property I tried to obtain months ago without success. Today is a good day.

Today I decided to replace the KL penalty with some yolo crazy approach, which worked. When looking at it closely it is the standard KL penalty with a minor but very important change that assures a property I tried to obtain months ago without success. Today is a good day.

Research Scientist @meta (FAIR), Prof. @Unige_en, co-founder @nc_shape. I like reality.

avatar for François Fleuret
François Fleuret
Tue Nov 11 21:53:16
前些天李亿的这篇《反脆弱》读书笔记的推文大火,有人开始模仿“我用了X年才……”,有人尝试把这篇文章逆向成读书笔记的提示词,好用 AI 批量产生出大量的读书笔记,都挺好的。

其实我也羡慕能写出这样有水平的内容,但是我不觉得通过直接用 AI 能写得出来,而且我个人并不太喜欢看那种 AI 批量产生的内容(此处应该 at 马东锡老师),更不喜欢另一些用 AI 为了流量去产生情绪和对立的内容。

我另外可以肯定的是,就算我和李亿用同样的模型来写,就算我提示词水平更高,我也不会产生比她更好的结果,因为就算是 AI 创作,也不应该是一次性成型,而是需要反复让 AI 根据输出修改调整。

如果我自己不知道好的作品是怎么样的,怎么才能写出好的作品,我也不会知道怎么让 AI 去调整,只能 AI 生成什么就接受什么,但专业的人一看就知道哪里有问题,就可以让 AI 去针对性调整。

所以我并没有去写一个提示词让 AI 生成类似的读书笔记,而是让 AI 去帮我分析为什么这篇文章写得好,哪些地方值得学习借鉴,如果自己写要怎么写。

我用了 Gemini 2.5 Pro 帮我分析(Prompt 在后面),看完我才明白为什么这篇内容会这么火,不是运气,而是水平。

Gemini 给出了很高的评价:
> 这是一篇非常精彩的“个人转变叙事”类型(Personal Transformation Narrative)的推文,它之所以强大,是因为它完美地融合了抽象的智慧和具体的个人故事。
>
> 这篇文章的结构设计得非常精妙,它像一个漏斗,从一个普遍的社会“痛点”开始,引入一个强大的“概念”,然后通过“个人实践”来验证这个概念,最后给出一个可操作的“解决方案”。

为什么那么多模仿的或者 AI 生成的都没有这篇打动人心,可能缺少的就是其中的“个人故事”,也缺少一个可操作的“解决方案”。

一篇好的文章总是有一个吸引人的开头,可能是让你共鸣、可能是让你好奇

但真正有“人味”的佳作是它融合了作者独一无二的个人故事和感悟,这是 AI 很难模仿的,通过“推特涨粉”这样的故事我们能感到真实,愿意去相信。

好的作品读者看完能有收获可以操作,就好比这条推文提到的“杠铃策略”真能用上,就像我这篇我也希望我分享的 Prompt 你能用的上。

顺便说一下,这条分析内容的提示词不是自己写的,而是前些天很多人转发分享的 《百万粉丝博主的内容生产工作六》里面 Dan Koe 用的,我特地打开视频截图 OCR 出来了用的提示词,效果真的很好。

---- 提示词开始 ----

Break down the structure of this post so that I can recreate it from scratch. Break down:

- Why it works

- The psychological patterns involved

- What context is needed from me

- Anything else I would need to understand how to recreate it

Response in 中文

前些天李亿的这篇《反脆弱》读书笔记的推文大火,有人开始模仿“我用了X年才……”,有人尝试把这篇文章逆向成读书笔记的提示词,好用 AI 批量产生出大量的读书笔记,都挺好的。 其实我也羡慕能写出这样有水平的内容,但是我不觉得通过直接用 AI 能写得出来,而且我个人并不太喜欢看那种 AI 批量产生的内容(此处应该 at 马东锡老师),更不喜欢另一些用 AI 为了流量去产生情绪和对立的内容。 我另外可以肯定的是,就算我和李亿用同样的模型来写,就算我提示词水平更高,我也不会产生比她更好的结果,因为就算是 AI 创作,也不应该是一次性成型,而是需要反复让 AI 根据输出修改调整。 如果我自己不知道好的作品是怎么样的,怎么才能写出好的作品,我也不会知道怎么让 AI 去调整,只能 AI 生成什么就接受什么,但专业的人一看就知道哪里有问题,就可以让 AI 去针对性调整。 所以我并没有去写一个提示词让 AI 生成类似的读书笔记,而是让 AI 去帮我分析为什么这篇文章写得好,哪些地方值得学习借鉴,如果自己写要怎么写。 我用了 Gemini 2.5 Pro 帮我分析(Prompt 在后面),看完我才明白为什么这篇内容会这么火,不是运气,而是水平。 Gemini 给出了很高的评价: > 这是一篇非常精彩的“个人转变叙事”类型(Personal Transformation Narrative)的推文,它之所以强大,是因为它完美地融合了抽象的智慧和具体的个人故事。 > > 这篇文章的结构设计得非常精妙,它像一个漏斗,从一个普遍的社会“痛点”开始,引入一个强大的“概念”,然后通过“个人实践”来验证这个概念,最后给出一个可操作的“解决方案”。 为什么那么多模仿的或者 AI 生成的都没有这篇打动人心,可能缺少的就是其中的“个人故事”,也缺少一个可操作的“解决方案”。 一篇好的文章总是有一个吸引人的开头,可能是让你共鸣、可能是让你好奇 但真正有“人味”的佳作是它融合了作者独一无二的个人故事和感悟,这是 AI 很难模仿的,通过“推特涨粉”这样的故事我们能感到真实,愿意去相信。 好的作品读者看完能有收获可以操作,就好比这条推文提到的“杠铃策略”真能用上,就像我这篇我也希望我分享的 Prompt 你能用的上。 顺便说一下,这条分析内容的提示词不是自己写的,而是前些天很多人转发分享的 《百万粉丝博主的内容生产工作六》里面 Dan Koe 用的,我特地打开视频截图 OCR 出来了用的提示词,效果真的很好。 ---- 提示词开始 ---- Break down the structure of this post so that I can recreate it from scratch. Break down: - Why it works - The psychological patterns involved - What context is needed from me - Anything else I would need to understand how to recreate it Response in 中文

Prompt Engineer, dedicated to learning and disseminating knowledge about AI, software engineering, and engineering management.

avatar for 宝玉
宝玉
Tue Nov 11 21:52:30
RT @marc_louvion: I remember in 2022, when I set up analytics for the first time, I had no idea why I needed to have a "proxy."

Later, I l…

RT @marc_louvion: I remember in 2022, when I set up analytics for the first time, I had no idea why I needed to have a "proxy." Later, I l…

🧑‍💻 https://t.co/Y30jsaHwz9 $20K/m ⚡️ https://t.co/vatLDmi9UG $17K/m 📈 https://t.co/3EDxln5mdi $16K/m ⭐️ https://t.co/MZc8tG9xWi $8K/m 🧬 https://t.co/SfrVXVtmdA $.5K/m 🍜 https://t.co/r07EpGSYJ2 $0K/m 🧾 https://t.co/7olaOzV8Xd $0/m +18 https://t.co/4zCWHGJp1S

avatar for Marc Lou
Marc Lou
Tue Nov 11 21:50:12
  • Previous
  • 1
  • More pages
  • 127
  • 128
  • 129
  • More pages
  • 2117
  • Next