Coconut

Nothing is irrevocable

[Wayen @wayen_ai]

Ilya Sutskever 曾断言，只要读懂那 30 篇奠基论文，就能掌握人工智能 90% 的精髓。但面对枯燥的数学公式，大多数人很难将其转化为可运行的代码。

最近在 GitHub 上发现一个叫 Sutskever 30的开源项目，用纯 NumPy 把 Ilya 推荐的 30 篇奠基性论文全部实现了一遍，已 100% 完成。

每个实现都不依��深度学习框架，只用 NumPy 从零构建：
1.配合 Jupyter Notebook 交互式学习，随时改代码看效果
2.自带合成数据，打开就能直接跑，无需下载数据集
3.覆盖 RNN、LSTM、Transformer、ResNet、VAE、RAG、Scaling Laws 等全部核心架构

GitHub：https://t.co/n4uWTnRPGX

只需要装好 NumPy 和 Jupyter，就能挨个 notebook 跑通，从字符级 RNN 一路看到通用人工智能理论。

想真正吃透 AI 底层原理、不再只会调包的朋友，建议直接 Star 收藏，跟着敲一遍代码，比看一百篇解读文章都管用。

[AI Edge @aiedge_]

https://t.co/SSEwqX94Qb

[Coconut @Cocohanmiao]

@miantiao_me 有没有一种可�� 这是ios的默认弹窗样式，而不是谁伪装什么

[Emil Kowalski @emilkowalski]

New skill: /apple-design

Apple’s WWDC videos are a goldmine of knowledge. I’ve combed through my favorite ones and came up with 17 design and motion principles.

Use them to review existing work or when working on something new to get it right.

https://t.co/jCwhthpi20

[Andrew Ng @AndrewYNg]

“Loop engineering” is a hot buzzphrase after mentions of it by Boris Cherny (Claude Code’s creator) and Peter Steinberger (OpenClaw's creator) went viral on social media. Loops are now a key part of how we get AI agents to iterate at length to build software. In this letter, I’d like to share my 3 key loops, shown in the image below, for building 0-to-1 products. These loops guide not just how I build software, but also how I decide what software to build.

Agentic coding loop: Given a product specification and optionally a set of evals (that is, a dataset against which to measure performance), we can have an AI agent write code, test its work, and keep iterating until the code is bug-free and meets its specification. This idea of closing the loop took off around the end of last year, and it has been a game changer in enabling coding agents to work longer productively without human intervention. For example, over the weekend, I was building an app for my daughter to practice typing, and my coding agent could easily work for around an hour, using a web browser to check what it had built multiple times before getting back to me, without needing my intervention.

The engineering loop executes quickly. Every few minutes, the coding agent might build and test a new version of the software. I hear frequently from developers who are finding new ways to engineer more effective engineering loops. This is an active area of invention!

Developer feedback loop: In this loop, a developer examines the current product and steers the coding agent to improve it. Last year, a lot of developers (including me) were acting as the QA (quality assurance) function for our coding agents, manually finding bugs and then asking the agent to fix them. But with coding agents much more able to test their own code, the amount of time we need to spend on this function has decreased significantly. This allows us to make higher-level product decisions, such as what key features to offer, where the UI needs improvement, and so on.

The developer-feedback loop operates over time intervals between tens of minutes and hours — that's how frequently a developer might review a product and give feedback. In the case of the typing app, I changed my mind a few times about the visual design, what cat costumes she can unlock as she learns (she loves cats), and the user flow for a grown-up to log in and steer the child's learning experience.

When a developer has a clear vision for what to build, it is still a lot of work to translate that vision into a specification for a coding agent to implement. Further, after the developer has seen an implementation, they might update (or perhaps clarify) the spec to steer it toward what they want. If you find that the system repeatedly runs into certain problems, building a set of evals for the agent becomes useful.

AI-native teams are increasingly using AI to help shape product direction, for example, automating the gathering and analysis of usage data, summarizing written and verbal customer feedback, or carrying out competitive analysis. However, for pretty much all the products I’m involved in, I see humans as having a significant context advantage over current AI systems — we know a lot more than the AI system about the users and the context the product has to operate in — and thus humans play a critical role. Many people describe this human contribution as “taste,” but I prefer to think of it as humans having a context advantage, since that gives us a clearer path to helping AI systems get better. This also speaks to why this step can’t be automated: So long as the human knows something the AI does not, human-in-the-loop is needed to to inject that knowledge into the system.

External feedback loop: This includes a wide range of tactics like asking a few friends for feedback, launching to alpha testers, or putting the code into production with A/B testing. These tactics are usually slow, rarely taking less than hours and sometimes taking days or even weeks. This data informs the developer vision, which in turn continues to drive the detailed product spec, which in turn drives the coding agent.

With coding agents speeding up software development, more engineers are starting to play a partial product management role. For many engineers who are growing into this role, the hardest part is shaping the product vision and striking a balance between building (bridging the gap between vision and spec) and getting user feedback to evolve the vision. It is important to do both!

I will write more about how to do this in future posts, but for now, I find it encouraging that engineers are playing an expanded role (just as product managers and designers now do more engineering).

[Original text: The Batch]

[Mu nicallen @Municalleneae]

知名网络安全巨头 NordVPN 旗下的全球旅游 eSIM 品牌 Saily（在 2026 年 6 月 11 日）刚刚全网首发推出的全新原生美国（+1）电话号码服务。由于是刚上线几天的重磅新功能，所以配合推广优惠码的开卡价格和月租被直接打到了骨折。

根据第一批用户的检测��告，Saily 分配的号码底层是由美国 Choice Wireless Texas 提供的实体蜂窝网络。它在系统识别中是真正的 Cellular 原生手机号，拿来接收 2FA 验证码和各种 App 注册，通过率和稳定性降维打击那些虚拟号。

根据 Saily 官方的底层规则：只要你保持每月 $0.99 的号码订阅（保号费）在续费，哪怕你没有额外购买任何短信流量包，它的“接收短信（Incoming SMS）”功能也是无限量且完全免费的！ 也就是说，如果你下个月只是单纯用来躺在手机里收验证码，连那 1 美元的短信包都不用叠加，保号成本无限逼近于零。

Saily 作为面向全球旅行者的 App，直接支持中国大陆身��证直接线上 KYC 认证，并且支持 Apple Pay、支付宝或国内双币卡直接付，对国人友好度拉满。

[Viking @vikingmute]

原文的评论中有人说提了这篇文章：《Inside the Transformer: The Life of a Token》
https://t.co/sFDLVz8oHz

如果看完了原帖这篇文章，可以当这篇文章的进阶版，可以更深的了解，文章详细追踪一个 Token 在现代 Transformer 中的完整前向传播过程，有很多实战实现细节。
图做的很好，而且很丰富，很多细节，结合真实模型讲解，干货很多，但是难度高一些，适合有一定基础的朋友

[Lance Martin @RLanceMartin]

https://t.co/es0JQM4MS9

[Addy Osmani @addyosmani]

https://t.co/hIe0UX7z6T

[meng shao @shao__meng]

如何构建你自己的 Agent Harness？

先看几个问题：
· 生产级 Harness 是“选一个框架”就能搞定的吗？
· 生产级 Harness 必须承担的 15 项真实职责是什么？
· 每项职责如何做成可安装、可版本化、可换语言的 worker？
· 单次 turn 如何跑通？
· 策略、审批、预算、trace 在生产级 Harness 里为什么重要？

@mfpiccolo 在他的「How to Build Your Own Agent Harness」中给出了完整答案，强烈建议阅读原文：
https://t.co/rqXHoi9DWv

[AYi @AYi_AInotes]

免费领6个月ChatGPT Pro，
价值$ 1200🤩

这可能是今年对开发者最实在的福利了，

没有硬性Star数要求，
有项目链接基本都能过，

只要你是任何一个公开开源项目的维护者，哪怕只有你一个人在维护，
都可以去申请试试：
https://t.co/YsVgw6RrPU

[Elon Musk @elonmusk]

Wise words

[Dan McAteer @daniel_mac8]

How to setup persistent Codex memory in Obsidian

1. Copy the below prompt into Codex. The prompt instructs Codex to create the memory folders in Obsidian

2. Copy the below custom instructions. They instruct Codex to use Obsidian Codex memory to save memories

That's it!

[AlphaSignal @AlphaSignalAI]

https://t.co/GBmIIsdq7G

[Ring Hyacinth @ring_hyacinth]

下午和飞书的产品经理聊天，他们会用一个录音工具将自己一天所有会议录下来，自动飞书妙计总结。

codex 再通过飞书 cli，每天将妙计内容晚上自动总结 to do, 能干的 codex 干掉，需要人类的每天早上 8 点再发给人类。

真的是好先进的流程。

[何居上 @hejushang8]

用 X 一年了，现在总结下我的收获
目前已有电话卡：
https://t.co/HGeFKELXfL club esim-每年 6 元保号
2.英国 giffgaff-180天发一条短信保号
3.德国沃达丰 esim-90天0.01 欧保号
4.德国 O2 esim -180 ���转账 0.01 欧保号

支付已有 U 卡，港卡，美区paypal
U 卡
1.plasma one 3% 返现，才办下来，体验不错
2.ready 金属卡，之前 80U 办的，拿了 300u 返现，现在过年没返现了，准备放弃
3.bybit U 卡 首月 10% 返现，后期 2% 返现，磨损算下来 比正常汇率高点
4.bitget U 卡 加上手续费返还，正常汇率

已有港卡
1.众安 ZA bank 国内日常消费会用这个，1.5% 的返现
2.象象银行 背包出金一般出到这个银行，兑换 rmb汇率比其他的好，回国也是用这个
3.汇丰 one 感觉没啥用，要保持 1W 以上，否则要收管理费
4.蚂蚁银行 办了还没用过。。

港股美股
开了个致富证券，目前在参与打新，还没中过
IBKR --还没审核通过

apple id
香港Id 用来下载交易�� app
美国 ID 之前下载 claude chatgpt
土耳其 ID 现在用来半价购买 chatgpt
尼日利亚 ID 现在用来购买 Claude

都办这些了，钱没赚到，怎么办，还有什么值得办的，我还要办！！
#esim #U卡 #ai

[Yeuoly @Yeuoly1]

https://t.co/sEY8STy8lh

[铁锤人 @lxfater]

推荐Anthropic 13 门免费课程，还附带证书

我按 12 周排好顺序，简单到困难一步一步学

第 1–2 周｜基础
1. Claude 101
上手 Claude 的日常使用，是后面所有课的前置。
https://t.co/8bdokywcqp

2. AI Fluency: Frameworks & Foundations
人机协作的四原则，建立怎么跟 AI 合作的心智模型。
https://t.co/1kmj6lhzgQ

第 3–4 周｜接 API
3. Building with the Claude API
旗舰课 8 小时，从基础调用打到生产部署。
https://t.co/kD0wbhhvkb

第 5–6 周｜MCP 协议
4. Introduction to Model Context Protocol
工具、资源、提示三要素入门，把外部工具接到 Claude。
https://t.co/tSTbHR7KOv

5. MCP: Advanced Topics
用 Python 深度构建 MCP server 和 client。
https://t.co/DV8iX8kSMz

第 7–8 周｜Claude Code 与 Skills
6. Claude Code in Action
配 CLAUDE.md、Hooks、CI 集成，把它变成日常工具。
https://t.co/poSvymIGCR

7. Introduction to Agent Skills
写、配���、分发可复用的 Skills，agent 的积木。
https://t.co/htcluL5rTg

第 9–10 周｜上云
8. Claude with Amazon Bedrock
在 AWS 上跑 Claude，IAM 与企业账号调用模式。
https://t.co/ai3OvOaleU

9. Claude with Google Vertex AI
在 GCP 上跑 Claude，与 Vertex 其他服务串联。
https://t.co/1jQdRfaxVR

第 11–12 周｜角色专项
10. AI Fluency for Students
学生怎么把 Claude 当导师而不是作弊器。
https://t.co/ksFCTi8yOk

11. AI Fluency for Educators
教师怎么把 AI 融入课堂与作业设计。
https://t.co/8r22qINF2q

12. Teaching AI Fluency
怎么把四原则教给别人，培训师工具包。
https://t.co/PUoCqEHYyW

13. AI Fluency for Nonprofits
公益组织在预算和合规下怎么落地 AI。
https://t.co/hkkOrn4SRB

全免费，全官方。先 mark 再开学

你也可以看看下面我关于Agent记忆的爆文👇

[Roland.W @rwayne]

https://t.co/QlPd9AVxiY

[Mnimiy @Mnilax]

https://t.co/W4MxdOyUKD