max yang

[Xiaoyin Qu @quxiaoyin]

This is me!

[Max For AI @MaxForAI]

Kimi-Code的主程K佬分享了他重构Kimi-Code的经历👀

大概一个月前，他下定决心重构 kimi-code，开始设计新的架构。

他抱着电脑和便携屏在汤泉卷了两整天，花了几千刀的 token 去做架构分析、设计和验证，最终得到了一份认为最优的架构方案。

在 vibe 时代，架构变得更加重要了，一份好的架构能够在可控的范围内，让 Agent 肆意 coding，而不会打破东西

- 架构确定后，就开始冲刺实现（过程中吵和推翻了无数次）
- 迅速组建了一个强大的 team。
- 迅速 onboarding 整个 team
- 封闭开发了一段时间（
- 开源后就病倒了，皮质醇分泌过度，影响免疫力
- 这一个月学的东西够我消化半年的 - 一周干了一整箱红牛，还得是生物燃料
- 也在 x 上消失了一个月

等 kimi-code 陆续迭代到稳定，再去总结过程中的 lessons learned

太强了！

[实践哥MinLi @MinLiBuilds]

离谱，这个光头强者，演讲时还在写代码。

Bun 作者Jarred 边分享边跑 agent 改代码,旁边Boris 都忍不住吐槽他又趁演讲在干活😅

Jarred 4 月底跑通将 workflow：

复现 bug → 写测试 → 提 PR → code review → 自动修改。

听了演讲后，Claude 5 月底就推出了 dynamic workflows.

学习 workflows，这会是你今年做的最好的投资。

02:08 现场演示自动修GitHub Issue
03:00 Agent自动复现 Bug、写测试、提交 PR
10:00 如何让 Agent 读懂整个项目
23:00 Auto Mode 让 Agent 连续几小时自动干活

[Kevin Arifin @kevarifin]

just the start of @moonpay x agentic commerce

[Oldeng @dengdry]

不上X根本认识不了这么牛逼的人

[vivid_来年春 @vividzfc]

6月14日南昌见！

以太坊之夏南昌站要来了，欢迎大家来现场～感兴趣的DM我们～

此外，住宿方面，南昌数字游民社区内测阶段，可提供住宿。远离世俗，带你下地体验田野，感受国内区块链课程，吃地道江西小炒！

[ETHPanda @ETHPanda_Org]

https://t.co/rTqhJqQWY3

[LXDAO @LXDAO_Official]

🔥 总奖池 7000 USDT！AI × Web3 黑客松报名正式开启！

还在纠结学了一堆 AI 和 Web3 技术不知道怎么落地？
不如直接来这场黑客松，用一周多时间做出一个能跑、能演示的 Demo，顺便角逐 7000 USDT 总奖池！

⭐AI × Web3 Agentic Builders Hackathon
总奖池 7000 U，两大方向，只要你能做出来，我们就敢评。

📌 关键信息
💰 总奖池：7000 USDT（Cobo 赛道 3500 + https://t.co/euOajayCXh 赛道 3500）
⌚️ 开发周期：2026.6.1 – 6.12
📅 Demo Day：2026.6.14
🔗 报名链接：https://t.co/ZCzhI2CoUP

🚀 两大方向
1. 智能商务 + 智能钱包
Agent 支付、托管、交易、分账、结算，多 Agent 经济协作等链上资金流应用。

2. Web3 × 长期任务
长周期任务 Agent、3D 空间构建、链上内容生产、DAO 协作、智能合约审计等生产力工具。

✅ 参赛要求
个人或组队均可（建议 3–5 人跨职能组小队）
提交 GitHub 仓库、Demo 视频、项目文档、链上/测试网证据
评审维度：创新、技术实现、体验、生态价值、演示质量
只接受可运行的 Demo，概念或设计稿不参与评审

💡 为什么要来？
把学习成果变成真正可迭代的项目
链接 AI × Web3 社区和生态资源
锻炼从产品到技术到演示的全流程能力
优秀项目可长期发展，获得后续合作机会

👉 立即报名：https://t.co/ZCzhI2CoUP
快组队来战，一起打造链上 AI Agent 的新范式！

[Shawn Pang @0xshawnpang]

AllScale现在支持所有商户几乎全链全币种向用户收费。更关键的是，商户完全不需要理解复杂的链、币种、跨链、gas fee、地址等，完成配置之后，不管客户在哪里用什么怎么样付款给你，商户收到的永远都是稳定币。

[少个分号 @shaogefenhao]

刚刚美股被叫停就刷到有人写了一篇指南。

怎么好事都是我最后知道的。

https://t.co/ANzFbKTefj

[Rahul @sairahul1]

https://t.co/WN0MsLNjDw

[max yang @2045max]

Butterfly

[Nainsi Dwivedi @NainsiDwiv50980]

Andrej Karpathy just explained the future of software engineering without directly saying it.

The best AI engineers are no longer “prompting.”

They’re building systems around the agents.

Karpathy’s biggest insight wasn’t:
“Claude can code.”

It was:
LLMs become dramatically better when you force them into disciplined workflows.

That’s why "CLAUDE.md" files are suddenly everywhere.

Not because they’re prompts.

Because they behave like an operating system for the agent.

Karpathy called out the exact problems with AI coding:

- models assume instead of asking
- they overengineer simple tasks
- they hide confusion
- they rewrite unrelated code
- they optimize for completion, not correctness

So developers started encoding rules directly into the workflow:

→ Think before coding
→ Simplicity first
→ Surgical edits only
→ Goal-driven execution

And the results are wild.

People are now running multiple Claude Code agents in parallel like engineering teams:

• one agent researching
• one debugging
• one writing tests
• one optimizing code
• one validating outputs

Not “AI assistance.”

Actual orchestration.

And this part from Karpathy changes everything:

“Don’t tell the model what to do. Give it success criteria and let it loop.”

That is the shift.

From:
“write this function”

To:
“here’s the goal, constraints, tests, and verification system — now iterate until correct.”

The craziest part?

This already feels like a phase shift in engineering.

A lot of developers quietly went from:
80% manual coding → to 80% agent-driven coding in just months.

Not because AI became perfect.

Because the leverage became impossible to ignore.

We’re entering an era where the highest leverage engineers won’t necessarily be the best coders.

They’ll be the people who build the best systems around AI agents.

[cat @_catwu]

Excited to share how Anthropic's data team has automated 95% of business analytics queries with Claude. Blog post covers how we approach evals, ablations, and online validation!

[KK.aWSB @KKaWSB]

学AI就是要盯住最前沿的那几个人，这是Claude Code创始人昨天最新的分享视频，了解他对Claude最近的使用方法论迭代，收藏起来。

[Joel Hansen @joelshansen]

Guess the net worth of @ycombinator's first class of startup founders

[max yang @2045max]

https://t.co/cAoAN3kW3F

[max yang @2045max]

https://t.co/vuyMIcWchH

[CorrelAid @CorrelAid]

Very excited: A few days ago, our first R package {#newsanchor} reached 1000+ downloads on #CRAN. It helps to access ⁦@NewsAPIorg⁩. Read more about it on our blog.

Or simply type:
install.packages(“newsanchor“).

#rstats https://t.co/SimQ9T2shB

[max yang @2045max]

stocktwits

[Stocktwits @Stocktwits]

We rebuilt the Stocktwits symbol page from the ground up!

Cleaner social-first feed, a new Top Voices module to surface the sharpest minds on any ticker, and a Related Symbols section to discover connected plays. We’re putting the community front and center.

[Yi Ma @YiMaTweets]

I believe he is a great physicist, probably even knows how the current AI technology could help physics better than anyone. But that does not make him an expert about the current AI technology, claiming its limit or the lack thereof.