melanie 🐾

18 🧬
need a content partner this week 🌶
I only reply here 👇🏼

[melanie 🐾 @melayaof]

socks are always delicious for babies.
fighting!

[@levelsio @levelsio]

After this post my Google Maps has now also been banned from reviewing places

No wonder every place is now a 4.7/5, they all converge to that rating if you just remove all the bad ratings

Interestingly, my account has been banned because of my reviews in Dubai from ages ago, I know UAE has strict defamation laws, so I think businesses use that to remove reviews there

I don't know why the Google Maps team is allowing this though, a review or rating is not defamation, it's just an opinion, and Google needs that opinion for people to know where to go

What Google should be doing I think is defending the people who review and rate places in court wherever they live, because by just allowing any business to remove bad ratings/reviews, they make Google Maps completely non-credible!

Long term people will just use other apps to find good places and I don't think you want that @sundarpichai

Maybe we need @X Maps with real reviews @elonmusk?

[Sarvesh Shrivastava @bloggersarvesh]

STOP wasting Claude tokens. 

You don’t need to pay Claude $200/month for your SEO.

$20/month is all you need.

Here's the exact SEO setup I run before touching a single prompt:

1. Pick the right model.

Open Cowork. Select Opus 4.7. Turn on Extended Thinking.

Most people are running SEO prompts on Sonnet or the default model.

Wrong model = surface level output. Every single time.

Opus 4.7 with Extended Thinking doesn't just answer your question. 

It thinks through your entire market before responding.

The difference between a $20/month result and a $ 10k / month agency result is often just this one setting.

2. Load your business brain.

Before anything else paste this into Claude:

"Here is everything you need to know about my business: 

[name], [website], [location], [services], [target cities], [top 3 competitor URLs]. 

Use this as context for everything. Never ask me for this again."

Claude stops being generic. Starts being yours.

Most people skip this and spend the next 6 months getting advice that could apply to any business in any city in any industry.

That's not SEO. That's guessing.

3. Set your SEO mission once. Forever.

Go to Settings → Cowork → Edit Global Instructions.

Paste this:

"You are my local SEO strategist with 14 years of experience. Always read my business context before responding. 

Always compare my business against my competitors before giving advice. Always prioritise commendations by revenue impact. Never give generic SEO advice that doesn't apply to my specific market and location."

You set this once. It runs every single session.

Your prompts can now be 10 words long and hit harder than a 500 word prompt ever could.

4. Build your competitor file.

Create a document called COMPETITORS.md

Inside list your top 5 competitors with:

- their website URL

- their GBP URL

- their review count and average rating

- the keywords they rank for that you don't

- the categories they have that you're missing

Paste this into Claude before every audit.

Claude now knows exactly who it's competing against. 

Every recommendation it makes is built around beating these specific businesses in your specific market.

5. Set your keyword intent filter.

Before running any keyword research tell Claude this:

"Only give me keywords with clear buyer intent. Ignore informational keywords. 

Focus only on service + city, emergency + service, and near me combinations. Every keyword you suggest must indicate someone who is ready to call or book today."

This alone eliminates 90% of the wasted SEO effort most businesses do.

6. Before every Claude SEO session check these:

Am I in Cowork not Chat?

Is Opus 4.7 + Extended Thinking on?

Did Claude read my business context?

Is my competitor file loaded?

Is my keyword intent filter set?

Get all five right first. Then run your prompts.

The businesses that do this setup properly are outranking competitors who have been established for years.

The ones that skip it are still getting generic advice and wondering why nothing is moving.

Most people will read this and do nothing.

The ones who set this up today will look back in 90 days and not believe what changed.

Full prompt system in the article below.

Bookmark it.

Give it to Claude.

Right now.

[Khairallah AL-Awady @eng_khairallah1]

18-year-old American found a roofing company on Google Maps with 4.9 stars and no website, copied their reviews and pasted them into ChatGPT 5.5.

2 minutes later - a complete brief.

Pasted it into AI and just waited while the system built a full website with all pages, reviews and a booking button.

Called the owner and showed him the live preview. He said yes immediately because he'd been meaning to fix this for years and never had the time.

Invoice for $1,000. 47 minutes of work from the first search to a closed deal.

Then he built a machine.

AI pulls 200 businesses from Google Maps in 10 minutes, writes a personalized email for each one with their real business data - 500 emails a day, 3% respond.

Month one - $4,000, month six - $15,000-20,000. Five million businesses on Google Maps are still waiting for that call.

[Elon Musk @elonmusk]

Critical feedback is much appreciated

[Google Cloud Tech @GoogleCloudTech]

https://t.co/Nhzbmwl85W

[indigo @indigox]

如果人不保持认知参与，AI 赋能就变成了 AI 替代，而一旦AI 出错，没有人有能力兜底！Anthropic 最新的论文做了一个有趣的研究「AI 如何影响技能的习得」👀 https://t.co/ScLxE4pwGB

研究者设计了一个随机对照实验，让 52 名有经验的Python 开发者学习一个他们从未用过的异步编程库（Trio）。实验分两组：AI 辅助组可以使用基于 GPT-4o 的聊天助手，对照组只能靠文档和网页搜索。完成编程任务后，所有人参加同一份知识测验（概念理解、代码阅读、调试能力），且测验期间双方都不能用 AI。

核心发现很尖锐：用 AI 既没有明显提速，又显著损害了学习效果。六种AI交互模式的分化极其鲜明：

低分模式（测验 24%-39%）：

- AI 全委托：直接让 AI 写完所有代码，最快完成但学到最少；
- 渐进依赖：第一题还自己想，第二题就完全交给 AI；
- 反复让 AI 调试：遇到错误就丢给 AI，自己不思考；

高分模式（测验 65%-86%）：

- 先生成后理解：让 AI 写代码，但之后追问原理；
- 混合代码-解释：每次请求都同时要求代码和解释；
- 只问概念：仅向 AI 提概念性问题，自己独立写代码和解决错误；

最高分的模式（86%）是"先生成后理解"——看起来行为和全委托几乎一样，但多了一步主动追问理解，结果天差地别。

基于论文的发现，我认为有几个层面的应对策略：

- 对个人（尤其是新技能习得阶段）： 关键原则是保持认知参与。论文证明了"先生成后理解"模式的有效性——你可以用AI 加速，但必须在生成后追问"为什么这样写"，把 AI 当教练而不是代工。遇到错误时，先自己想 30 秒再求助 AI，这个独立解决错误的过程正是调试能力的来源；

- 对组织和管理者： 需要重新审视"AI 提升生产力"的叙事。论文揭示了一个隐性成本——初级员工如果在入职初期就过度依赖 AI 完成不熟悉的任务，可能永远无法建立起监督AI所需的基础能力。可以考虑在 onboarding 和技能培养阶段设置"AI-light"时段，或者强制要求新人在使用AI时同时生成解释；

- 对 AI 产品设计： 论文末尾提到了 ChatGPT Study Mode 和 Claude Code 的 Learning/Explanatory 模式，这是正确的方向。理想的 AI 编程助手应该能感知用户处于"学习新技能"还是"执行已知任务"的状态，在前者时主动引导而非直接给答案。

因为 AI 增强的生产力不是能力习得的捷径✨

[melanie 🐾 @melayaof]

📖 Reach out: https://t.co/GC5iZ8AdFZ

Headline: My 3-month roadmap to become a Head of Growth & Ops. 🛠️

#AIEngineering #GrowthOps #Startups #Automation #TechToBiz

[Neo Kim @systemdesignone]

If you want to boost your software engineering career, star + bookmark these 12 GitHub repos:

1 Vision Agent
↳ https://t.co/M7OIzZVAKA

2 System design
↳ https://t.co/57FAu0f9Oz

3 Public APIs
↳ https://t.co/Ikt9Zyy2m4

4 Tech interview handbook
↳ https://t.co/3ZpaTKgDzE

5 Coding interview university
↳ https://t.co/cQhGu0zI2E

6 Engineering leadership
↳ https://t.co/i7vTHC5Foz

7 Freecodecamp
↳ https://t.co/HbP9utSuZE

8 Developer roadmaps
↳ https://t.co/RXQVuYKr8z

9 Path to senior engineer handbook
↳ https://t.co/X4kepQW20p

10 Free programming books
↳ https://t.co/WuauWJKWQ6

11 Build your own x
↳ https://t.co/gW3qDjnCxa

12 Awesome lists
↳ https://t.co/fdOmRT2iLF

Remember, star + bookmark these repos right now.

(What else would you add?)

——

💾 Save this for later & RT to help others become good software engineers.

👤 Follow @systemdesignone + turn on notifications.

[melanie 🐾 @melayaof]

Powered by Qwen3-Embedding on GPU clusters with Ray + vLLM, it processes videos/images/campaigns into embeddings, stored in vector DBs.
Enabling AI apps like:
- Multimodal Search
- Creative Recommendation
- Ad Effectiveness Prediction
- Video Script & Creative Generation

[melanie 🐾 @melayaof]

Gemini CLI Wrapped 2025 📊

Total Tokens: 10.1K
Total Messages: 2
Total Sessions: 1

Longest Streak: 1 days
Top Model: gemini-2.5-flash
Top Language: N/A

Get yours:
❯ npx gemini-wrapped

Credit: @JackWoth98 @moddi3io @nummanali

[melanie 🐾 @melayaof]

Multimodal Search（Engineering Design Breakdown）

[melanie 🐾 @melayaof]

进入广告行业一年，年末总结，半完整版

[melanie 🐾 @melayaof]

YouTube Recaps

[melanie 🐾 @melayaof]

Cool and amazing

[Vercel @vercel]

BFCM 2025 runs on Vercel.
Real data in real time.

Tune in live now. https://t.co/xMDY7QPo3X

[melanie 🐾 @melayaof]

The daily life of an AI software engineer

[HeroUI @hero_ui]

HeroUI Native alpha 12 is here 🚀

What’s new:

⚡️ Support for Expo SDK 54
🌀 Migrated to Reanimated v4
🦴 New components: Skeleton & SkeletonGroup
🎨 New showcase: Hero Paywall

[melanie 🐾 @melayaof]

@ElonMuskNews47 do do that

[melanie 🐾 @melayaof]

@TrumpRealDaily Good or bad