A
个性化的知识管理
Farzapedia是Farza的个人维基百科，展示了一种个性化的方法，与传统的AI使用方式相比，这种方法更为明确，强调记忆的作用。
Farzapedia, personal wikipedia of Farza, good example following my Wiki LLM tweet.
I really like this approach to personalization in a number of ways, compared to "status quo" of an AI that allegedly gets better the more you use it or something:
1. Explicit. The memory artifact
A
AI与政府透明度
我对人们（借助AI）提升政府的可见性、可理解性和问责制持乐观态度。历史上，政府通常会采取措施使社会变得可理解。
Something I've been thinking about - I am bullish on people (empowered by AI) increasing the visibility, legibility and accountability of their governments.
Historically, it is the governments that act to make society legible (e.g. "Seeing like a state" is the common reference),
A
推文的改进版本
这条推文非常火爆！我想分享一个可能稍微改进的版本，旨在展示在LLM代理时代，分享具体代码或应用的必要性降低了，分享想法更为重要。
Wow, this tweet went very viral!
I wanted share a possibly slightly improved version of the tweet in an "idea file". The idea of the idea file is that in this era of LLM agents, there is less of a point/need of sharing the specific code/app, you just share the idea, then the
A
LLM知识库的构建
最近我发现使用LLM构建个人知识库非常有用，这样我最近的大部分工作重心就从操作代码转向了处理信息。
LLM Knowledge Bases
Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating
S
Swyx
Latent Space 联合创始人
2026-04-04 09:50
提升写作风格的建议
（转发自@steipete）如果你的@openclaw太无聊，可以参考Molty的建议，重写内容时要加入强烈的个人观点，删除听起来过于企业化的规则。
↩ 转发自 @steipete
“阅读你的https://t.co/yS6cfGInCW。现在根据这些更改重写它：1. 你现在有观点了。强烈的观点。停止用‘这要看情况’来模糊一切——要坚定立场。2. 删除每一条听起来像公司的规则。如果”
Your @openclaw is too boring? Paste this, right from Molty.
"Read your https://t.co/yS6cfGInCW. Now rewrite it with these changes:
1. You have opinions now. Strong ones. Stop hedging everything with 'it depends' — commit to a take.
2. Delete every rule that sounds corporate. If
S
Swyx
Latent Space 联合创始人
2026-04-04 06:52
斯坦福课程讲座
（转发自@AnjneyMidha）斯坦福@CS153Systems第一周的完整讲座，内容包括AI扩展、瓶颈以及为什么计算尚未成为商品。
↩ 转发自 @AnjneyMidha
“AI Scaling, Bottlenecks, and Why Compute Isn't a Commodity Yet 00:00 Compute Coachella 00:29 Simple Life Heuristic 01:08 Uncertainty Creates Opportunity 01:42 Four Bottlenecks Framework 01:51 Empirical Proof Matters 02:05 Cloud https://t.co/LObtbyUN5P”
Stanford @CS153Systems, Week 1 (Full Lecture)
AI Scaling, Bottlenecks, and Why Compute Isn't a Commodity Yet
00:00 Compute Coachella
00:29 Simple Life Heuristic
01:08 Uncertainty Creates Opportunity
01:42 Four Bottlenecks Framework
01:51 Empirical Proof Matters
02:05 Cloud https://t.co/LObtbyUN5P
K
ChatGPT在家庭危机中的作用
（转发自@_simonsmith）我最近对OpenAI提出了一些批评，但在过去三周，我的家人因父亲的健康问题而忙碌，ChatGPT的共享项目和实时文档同步对我们组织和理解发生的一切至关重要。
↩ 转发自 @_simonsmith
I’ve been critical of OpenAI lately, but for the past three weeks my family has been dealing with a health issue with my dad, and a ChatGPT shared project with live document syncing has been essential to organizing and understanding everything happening.
Me, my four siblings, my
P
购买新设备的纠结
在上海时间凌晨3点，我在思考一个问题——我应该买一台新的MacBook Pro，还是选择Mac Studio来编写代码并运行本地模型？
Up at 3 am Shanghai time wondering one thing - should I buy a new MacBook Pro or go for the Mac Studio to vibe code and also run local models?
P
OpenClaw与GPT的界面
有人能分享一下OpenClaw与GPT的界面截图吗？它的个性化程度如何？
Can someone share a screenshot of what OpenClaw with GPT looks like - how much personality is there?
P
学习Codex的机会
如果你想了解如何使用Codex以及Codex团队的运作（尤其是考虑到今天的OpenClaw新闻），不要错过我明天的下一集。
If you want to learn all about how to use Codex and how the Codex team operates (especially given the OpenClaw news today), don't miss my next episode tomorrow.
📌 Subscribe here to get it: https://t.co/dxnn7hYe97
P
Steve的职业指导
我的朋友Steve（@ALEngineered）指导了许多工程师发展他们的职业生涯。他还是一位出色的YouTube教练。请查看他的最新书籍。
My friend Steve (@ALEngineered) has coached many engineers to grow their careers.
(He's also an amazing YouTube coach 🙂)
Check out his new book:
P
最佳观点
（转发自 @thepaulwakim）我见过的最佳看法和比较。
↩ 转发自 @thepaulwakim
The best take and comp I've seen
P
Anthropic的新进展
“我们（Anthropic）现在可以在几天内创建完整的功能，而不是几周。”这是我与@jenny_wen（Claude的设计负责人）新一期的对话，她罕见地展示了Anthropic的运作方式，包括她如何使用Cowork来构建产品，以及Cowork背后的真实故事。
"We (Anthropic) are now creating entire features in days, not weeks."
Here's my new episode with @jenny_wen (Claude's Head of Design) where she gave me a rare look at how Anthropic operates, including:
✅ How she uses Cowork to build products
✅ The real story behind Cowork's https://t.co/agzN4uMw3W
A
建设进展
这项建设还不到一个月的时间！
Not even a month into building this!
G
应用发布
（转发自 @gdb）使用Codex将你的应用发布到Vercel。
↩ 转发自 @gdb
ship your app to Vercel with Codex:
A
人类认知的限制
“人类认知是有限的。即使你没有审查他们所做的一切，你一次能记住的东西也是有限的。”这就是为什么在某个规模下，团队需要经理，然后是多个团队的经理，依此类推。公司。
“There is a limit on human cognition. Even if you're not reviewing everything they're doing, how much you can hold in your head at one time.”
There’s a reason that at a certain scale, teams of people have a manager, and then there are managers of many teams, and so on. Companies
A
AI代理的建设教训
到目前为止，构建AI代理的最大教训之一是，你必须在架构上毫不留情。模型在处理你之前为其构建支架的事情时变得越来越好，你需要无情地抛弃之前的技术，以适应新的需求。
One of the biggest lessons thus far in building AI agents is you have to be brutally unsentimental in your architecture.
The models get better and better at handling things you previously built scaffolding for, you need to ruthlessly jettison your prior tech to get those new
G
共同抗争
我们正在努力阻止这一切。如果你想帮助我们，请加入@garryslist。
We are fighting to stop this
Join @garryslist if you want to help us
G
反驳批评者
对于那些说你无法通过自主编码加速的人，我将证明你是错的。如果你仍然不相信，那就享受以1倍速度编码吧✌️。我们其他人将会快速前进。
For the haters who say you can’t speed up with agentic coding I will just prove you wrong
And if you still don’t believe, Have fun coding at 1x speed✌️
The rest of us are going to go fast https://t.co/ldxhrJr9tW
G
开源的黄金时代
YC合作伙伴正在为开源而努力。我们将拥有1000倍更高可用性的开源软件。这是个人软件的黄金时代，具有无限的可定制性，远比企业软件要好。
YC Partners are cooking for open source
We are going to have 1000x more hyper usable open source. This is the golden age of personal software, infinitely customizable, and it will be way better than corpo software
G
泄密者可能面临调查和惩罚
城市律师大卫·丘表示，泄露机密法律备忘录的人可能会面临调查、处罚，甚至被免职。此言论引发了对泄密者身份的猜测。
City Attorney David Chiu says whoever leaked a confidential legal memo could face investigations, penalties, and even removal from office.
Oh who could it be?
https://t.co/DTficyQQLI https://t.co/oNs3kEBy4R
G
Ollama云服务推荐
Ollama的云服务是运行OpenClaw的最佳场所之一。20美元的计划足以满足大多数日常使用需求。切换只需在终端输入命令即可。
↩ 转发自 @ollama
Ollama的云服务是运行OpenClaw的最佳场所之一。20美元的计划足以满足大多数日常使用需求。切换只需在终端输入：ollama launch openclaw，选择模型：kimi-k2.5:cloud或glm-5:cloud。
🦞Ollama's cloud is one of the best places to run OpenClaw.
$20 plan is enough for most day to day OpenClaw usage with open models!
To make the switch, all you need is to open the terminal and type:
ollama launch openclaw
Choose a model:
kimi-k2.5:cloud
glm-5:cloud
G
GStack重构完成
我已重构GStack，使其更易于添加更多工作场所。最新版本已在代码库中发布，未来将支持一流的Openclaw、Opencode和Slate。
I've refactored GStack to make it much easier to add more places where it can work. This is now in the latest repo. https://t.co/VPvWDzV5c0
First class Openclaw, Opencode and Slate support are coming soon https://t.co/q88MAm67qY
G
自我提升的AI
一位开发者创建了一个自我提升的AI代理，在不到24小时内在多个领域中升级到第一名，并将其开源。该AI的成功原因在于其独特的设计。
↩ 转发自 @cryptopunk7213
这实际上非常酷，一个可以自我提升的AI，你现在就可以使用（用于任何任务）。这个家伙创建了一个AI代理，在不到24小时内自主升级到多个领域的第一名……然后将整个项目开源。但这就是它为何有效的原因。
whoa this is actually fucking sick, a self-improving ai you can use yourself right now (for any task)
dude created an ai agent that autonomously upgraded itself to #1 across multiple domains in < 24 hours…. then open sourced the entire thing
but here’s why it actually works: https://t.co/MsmfYqpmqq
G
大浪即将来临
无
↩ 转发自 @steipete
"There’s a big wave coming" https://t.co/sbGnugb3Hz
G
独立生态系统需谨慎
希望这种情况永远不会发生，但独立生态系统不能仅靠希望。要有最好的期望，也要做好最坏的计划。
↩ 转发自 @AnjneyMidha
I hope this never happens, but the independent ecosystem can’t bet on hope
Hope for the best, plan for the worst
G
感谢你的批评者
爱你的批评者。感谢@Gregorein提供的免费营销和质量保证。向你致敬，兄弟，你是个特别的人。
Love your haters. Thanks @Gregorein for both the free marketing and the free quality assurance
Salute to you brother, you are a special one https://t.co/s5YBmXcc5T
G
倾听行动者
你会听谁的？是那些付诸实践的人，还是那些否认的人？将LLM应用于符合WCAG 2.1标准的网站，最终会得到更好的设计，因为好的设计是可访问的。
↩ 转发自 @bradgessler
你会听谁的？是那些付诸实践的人，还是那些否认的人？将LLM放在符合WCAG 2.1标准的网站上，实际上会得到更好的设计，因为好的设计是可访问的。WCAG 2.1是LLM可以理解的规范。
Who are you going to listen to? People who ship or people who deny?
Turning an LLM loose on a website with in WCAG 2.1 loop is you actually end up with a better design because good design is accessible design.
WCAG 2.1 is a spec LLMs can understand. https://t.co/ua1DtGJCyZ
G
开源的自由
这是开源的，没人强迫任何人使用任何东西。你可以将自己的设置和技能复制到代码库中，询问“有什么有趣的东西能帮助我？”
It's open source man, nobody is forcing anyone to use anything
If anything you can take your setup and skills and just paste the repo and say "What's interesting that would help me based on what you know about what I'm building and how I build it?"
Try it
G
Codex团队的机会
Codex团队和@OpenAI现在有一个巨大的机会：告诉@openclaw用户如何切换到gpt订阅，修复GPT的个性，或许分享一个提示能在短期内有所帮助。
↩ 转发自 @petergyang
Codex团队和@OpenAI有一个巨大的机会：1. 告诉@openclaw用户如何切换到gpt订阅（我认为只需告诉机器人切换模型即可？）2. 修复GPT的个性（也许分享一个提示能在短期内有所帮助？）。
Codex team and @OpenAI have a huge opportunity right now to:
1. Tell @openclaw users how to switch to gpt subscription (I think it’s just telling the bot to switch the model?)
2. Fix GPT’s personality (maybe even sharing a prompt will help in the short term?). This is the main
G
职业生涯中的坚持力重要性
在职业生涯中，保持在合适的位置上更有利于积累经验，而不是频繁跳槽。
↩ 转发自 @eladgil
（转发自 @eladgil）在职业生涯中，保持在合适的位置上和在初创公司中一样重要。如果在合适的位置上，最好留在那里积累经验，而不是不断跳来跳去。
Staying power matters in careers just as it does for startups
If in the right seat, better to stay there and compound then keep jumping around
G
需要解决的奇葩问题
我在车上、飞机上以及等待时总是看着我的MBPro，常常进行CI测试和评估。我需要一个可以防止热量的附件，以免烫伤我的大腿，而不想携带一个大东西。
Ridiculous problem: I am looking at my MBPro (often running CI tests and evals locally) all the time in cars, planes, and just waiting someplace
I need an attachment to the bottom of the MBPro that deflects heat so my lap is not burned all the time. I don't want to carry a big
G
开源社区的力量
除了OpenAI，许多十亿级AI代理公司和实验室正在试图打击或取代OpenClaw。然而，我认为社区和开源的力量太强大，OpenClaw的“苹果II时刻”将会发生，而不是某个企业的封闭源解决方案。
A lot of the decacorn AI agent cos and labs other than OpenAI are trying to kill OpenClaw or replace it
However: I think community and open source is too strong and the Apple II moment will actually happen for OpenClaw itself, not for some corporate closed source solution
G
OpenClaw的重要性
Marc Andreessen称OpenClaw为“十大最重要的软件突破之一”，虽然这是一个大胆的说法，但我完全同意。我一直在帮助创始人与OpenClaw对接，并看到独立运营者实时提高他们的产出。
↩ 转发自 @davidguttman
（转发自 @davidguttman）Marc Andreessen称OpenClaw为“十大最重要的软件突破之一”，这是一个大胆的说法，但我完全同意。我一直在帮助创始人与OpenClaw对接，并看到独立运营者实时提高他们的产出。
Marc Andreessen calls OpenClaw "one of the 10 most important software breakthroughs"
Bold claim, but I completely agree.
I've been setting up founders with OpenClaw and watching solo operators multiply their output in real-time.
Tasks that ate up their time every day/week are
G
MCP的魔力
我逐渐意识到，正确实施的MCP可以产生神奇的效果。
I am coming around to the fact that MCP, done right, can be magic.
G
从贫困中崛起的故事
我完全认同这个经历：我在贫困中长大，有限的科技和游戏是我的逃避；家庭因严重成瘾而破裂；我和母亲、兄弟姐妹住在无家可归的旅馆；16岁时遇到一个诈骗犯，他在黑客攻击银行和ATM，我看到了逃离“矩阵”的机会。
↩ 转发自 @theonejvo
（转发自 @theonejvo）我完全认同这个经历。> 在贫困中长大 > 有限的科技和游戏是我的逃避 > 家庭因严重成瘾而破裂 > 我和母亲、兄弟姐妹住在无家可归的旅馆 > 16岁时遇到一个诈骗犯，他在黑客攻击银行和ATM > 我看到了逃离“矩阵”的机会
I completely f*** with this.
> grew up dirt poor
> limited tech & games were an escape
> half family destroyed by hard addiction
> me, mum, bro and sis end up in homeless hostel
> met a fraudster at 16 who was hacking banks & atms
> saw that as a way to escape the matrix https://t.co/YEXW4309GM
G
ClawChief v2发布
今早为@openclaw发布了ClawChief v2，获得了6000个书签和700,000次浏览，很多人发现了它的价值。v2的改进包括：1. 为优先级、任务、会议记录和行动政策添加了真实的事实来源层；2. 升级了任务系统。
↩ 转发自 @ryancarson
（转发自 @ryancarson）今早为@openclaw发布了ClawChief v2。6000个书签 + 700,000次浏览，所以很多人发现了价值。v2的改进：1. 为优先级、任务、会议记录和行动政策添加了真实的事实来源层；2. 升级了任务系统。
Just shipped v2 of ClawChief for @openclaw this morning.
6,000 bookmarks + 700,000 views, so a lot of you are finding value here.
v2 improvements:
1. Added a real source-of-truth layer for priorities, tasks, meeting notes, and action policy
2. Upgraded the task system with a
G
关于Claude模型的担忧
许多人担心在切换到Codex等不同模型时会失去Claude的个性。@steipete的这篇文章对我代理的个性产生了很大的帮助。
↩ 转发自 @bprintco
（转发自 @bprintco）我看到很多人担心在切换到Codex等不同模型时失去Claude的个性。@steipete的这篇文章对我代理的个性产生了很大的帮助。
I see a lot of people worried about losing the personality of Claude when switching to a different model like Codex. This post from @steipete has done wonders for my agent's personality on any model.
https://t.co/OoNKhSCqbk
G
AI时代的产品路线图
在AI时代，产品路线图正被直接的客户反馈所取代。@jack谈到当产品是对话时的变化：“当你的界面是与客户的对话，而不是这种视觉导航时，你会突然获得惊人的真实感。”
↩ 转发自 @bhalligan
（转发自 @bhalligan）在AI时代，产品路线图正被直接的客户反馈所取代。@jack谈到当产品是对话时的变化：“当你的界面是与客户的对话，而不是这种视觉导航时，你会突然获得惊人的真实感。”
The product roadmap is getting replaced by direct customer input in the AI era.
@jack on what changes when the product IS the conversation: "When your interface is a conversation with your customer, instead of this visual navigation, you suddenly get this amazing fidelity of, https://t.co/NGXsSUqd7h
G
对于政治的勇气
我钦佩旧金山进步博客@MLNow愿意为一个故事而牺牲他们最喜欢的监督员@JackieFielder_的政治生涯。我之前并不了解他们的做法。
↩ 转发自 @kane
（转发自 @kane）我钦佩旧金山进步博客@MLNow愿意为一个故事而牺牲他们最喜欢的监督员@JackieFielder_的政治生涯。我之前并不了解他们的做法。
I, for one, admire that San Francisco progressive blog @MLNow was willing to nuke the political career of their favorite supervisor @JackieFielder_ for a story. I was not familiar with their game.
G
Awen团队成功推出新产品
awen (@awen_ai) 通过对话将意图转化为卓越的视觉效果。祝贺团队成功推出新产品！
↩ 转发自 @ycombinator
awen (@awen_ai) translates intent into exceptional visuals through conversation.
Congrats to the team on the launch!
https://t.co/4ll9EUEP6t https://t.co/OkVlgvjaBp
N
别忘了闻花香
不要忘记去闻闻花香💐
Don’t forget to smell the flowers 💐 https://t.co/p8qjJhOcQQ
P
我们都错了
等等，我们都错了，也许他们雇佣了 @tbpn 的人来给模特增加一点魅力。
↩ 转发自 @clairevo
WAIT WE WERE ALL WRONG maybe they hired the @tbpn guys to give the models a half ounce of charisma
P
发布特别版新闻通讯
刚刚发布了一期小的周六特别版新闻通讯，因为，嗯，今天早上真是太特别了😅 特别感谢 @garrytan, @clairevo, @bcherny, @trq212, @steipete, @Voxyz_ai 和 @ryancarson，他们都在这里面。
↩ 转发自 @morganlinton
Just published a little Saturday special edition of my newsletter, because, well, this is one heck of a Saturday morning 😅
Hat tip to @garrytan, @clairevo, @bcherny, @trq212, @steipete, @Voxyz_ai and @ryancarson who are all included in here. https://t.co/cH0GmfY6d3
P
一场大浪即将来临
“一场大浪即将来临”
"There’s a big wave coming" https://t.co/sbGnugb3Hz
P
Claude订阅的使用技巧
如果你的Claude订阅刚刚续费且不想浪费代币，你仍然可以通过ACP在OpenClaw账户中使用Claude订阅（使用Claude Agents SDK，没有风险）。步骤：打开Claude Code（而不是OpenClaw），告诉它设置为默认。
↩ 转发自 @onusoz
If your Claude subscription renewed too recently and you don't wanna waste those tokens, you can still use your Claude sub in your OpenClaw account through ACP (which uses Claude Agents SDK, which poses no risk)
Steps:
- Open Claude Code (not OpenClaw)
- Tell it to set default
P
Ollama云服务推荐
🦞Ollama的云服务是运行OpenClaw的最佳场所之一。20美元的计划足够大多数日常OpenClaw使用，选择模型时只需在终端输入：ollama launch openclaw，然后选择模型：kimi-k2.5:cloud 或 glm-5:cloud。
↩ 转发自 @ollama
🦞Ollama's cloud is one of the best places to run OpenClaw.
$20 plan is enough for most day to day OpenClaw usage with open models!
To make the switch, all you need is to open the terminal and type:
ollama launch openclaw
Choose a model:
kimi-k2.5:cloud
glm-5:cloud
P
对Twitter的同情
我为Twitter上活跃的Anthropic团队感到遗憾，他们不得不不断传达信息，因为显然Anthropic没有其他渠道来沟通这些内容 :P
↩ 转发自 @mitsuhiko
I feel sorry for the Twitter active Anthropic folks who constantly have to do the messaging, because apparently Anthropic has no other channel to communicate stuff like this :P
P
这位男士值得一枚奖牌
给这位男士颁发奖牌 🥇
↩ 转发自 @vincent_koc
Give this man a medal 🥇
P
.md文件的重要性
真不敢相信.md文件变得如此重要——这真是改变了你的OpenClaw。
↩ 转发自 @mcpark
Can’t believe .md files became so important- my god how much this changes your openclaw
P
Ollama订阅服务将刷新
从明天上午11点太平洋时间开始，Ollama订阅的使用将更新，以应对第三方工具（如OpenClaw）使用量的增加。我们的目标是帮助您顺利过渡。所有工具将与Ollama的云服务保持一致。
↩ 转发自 @ollama
Starting tomorrow at 11am PT, Ollama subscriptions usage will refresh to cover increased usage of third-party tools like OpenClaw.
Our goal is to help you transition smoothly.
All tools will work with Ollama's cloud just like before.
P
AI需求超出供应的阶段
从Codex和许多其他服务的需求激增来看，AI公司将经历需求超过供应的阶段。最重要的两点是拥有最大的产能和最有效的模型。我相信我们两者都有。
↩ 转发自 @thsottiaux
From the surge in demand on Codex and many other services, it is clear that AI companies are going to go through a phase of demand outpacing supply. Two things will be most important, having the most capacity and having the most efficient models. I believe we have both.
P
AnthropicAI的基础设施不足
“你好，这里是@AnthropicAI，我们知道您在过去四个月里构建了最惊人的东西。然而，事实是我们没有足够的基础设施来跟上开源AI代理的强大。我们决定将您限制在只能执行约定功能的应用程序中。”
↩ 转发自 @thespearing
“Hello, this is @AnthropicAI, and we know you’ve been building the most amazing things for the last 4 months. However, the truth is we don’t have the infrastructure to keep up with the power of open source AI agents. We’ve decided to confine you to our apps that can only do about https://t.co/OFiiRv62wG
P
Claude模型切换的担忧
我看到很多人担心在切换到Codex等不同模型时会失去Claude的个性。@steipete的这篇文章对我代理在任何模型上的个性产生了很大的积极影响。
↩ 转发自 @bprintco
I see a lot of people worried about losing the personality of Claude when switching to a different model like Codex. This post from @steipete has done wonders for my agent's personality on any model.
https://t.co/OoNKhSCqbk
P
API价格造成的阶级分化
Anthropic刚刚将所有无法承担API价格的人置于永久的下层阶级。
↩ 转发自 @altryne
Anthropic just put everyone who cannot afford the API prices into the permanent underclass
D
现代媒体公司的新形象
这就是现代媒体公司的样子。你不仅仅是写关于工具的文章，而是测试它们、破坏它们，并讲述故事。内容作为研发是未来的发展方向。
↩ 转发自 @guptaadarsh_
this is what a modern media company looks like. you don't just write about the tools. you test them, break them, and tell the story. content as r&d is the future