Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Introducing "codebase to course", a skill that turns any codebase into an interactive coding course So that you can learn coding through your own projects, complete with visualization, plain-English code translations, metaphors, even quizzes... I vibe code a lot but have no idea how the code works under the...

209,217 Aufrufe • vor 7 Monaten •via X (Twitter)

35 Kommentare

Profilbild von Zara Zhang
Zara Zhangvor 7 Monaten

Skill:

Profilbild von Gaurang Karia
Gaurang Kariavor 7 Monaten

Cool. Agree that among with Vibe coding, Vibe learning should go hand in hand. I built this to help along the way as you cover with Claude code.

Profilbild von Ken
Kenvor 7 Monaten

this is actually genius. Most people learn to code backwards, they study theory for months then try to build something. This flips it. Build first then understand what u built. Its like learning to drive by actually driving not by reading the car manual for 6 months

Profilbild von Siim Haugas
Siim Haugasvor 7 Monaten

this is way closer to how people actually learn now. build first, then inspect the weird part you just shipped while the pain is still fresh.

Profilbild von Lumina Strategy
Lumina Strategyvor 7 Monaten

"Build first, learn later" is the most underrated principle in AI right now. Everyone thinks you need to understand AI before you use it. You don't. You need to use it, get results, then understand why it worked. Same way nobody learned to drive by studying an engine. You got in the car and figured it out. This is how every business owner should approach AI. Start. Then learn.

Profilbild von TDM (e/λ) (L8 vibe coder 💫)
TDM (e/λ) (L8 vibe coder 💫)vor 7 Monaten

Love it. My take on this is to convert a codebase into an interactive explainer. Do checkout at -

Profilbild von Sentenza | The Escape Plan
Sentenza | The Escape Planvor 7 Monaten

this is what i actually want when i inherit a codebase. not docs. a guided tour that explains the why behind the structure

Profilbild von FUNL
FUNLvor 7 Monaten

This is my project that has similar intent that helps non-tech vibe coder better understand codebase and progress.

Profilbild von jon - building 🍎
jon - building 🍎vor 7 Monaten

hey zara! would love to get your thoughts on this its more codex focussed, but its about getting to that level of leveraging ai tools to be the best study companion that you can have

Profilbild von Trevor I. Lasn
Trevor I. Lasnvor 7 Monaten

the visualization angle is interesting. the hardest part of learning a codebase isn't the code itself but the reasoning behind the architecture. does it surface the "why" behind patterns or mostly the "what"?

Profilbild von Jeremy
Jeremyvor 7 Monaten

woww i have been thinking of something like this for a long time. but you have brought it into the world much better than i was thinking! great work 👏🏽

Profilbild von Jessi Cao
Jessi Caovor 7 Monaten

Love all skills you are sharing!!! And "follow builders, not influencer" you have said impress me a lot. Users who built first retained 3x longer than those in "learn first" tutorials. Momentum beats theory!! Build first, Build in AI, learn later.

Profilbild von Andrey
Andreyvor 7 Monaten

@DamiDina this is going to be awesome for beginners that wanna dive in deeper with tech. awesome work!!

Profilbild von Kartik Katyal
Kartik Katyalvor 6 Monaten

love the visualizations, built something similar a few days back. it gives you a detailed read into the tech stack, architecture, design tradeoffs, and explains the code with code snippets. the quiz also has a surprise at the end lol.

Profilbild von Andika Rachman
Andika Rachmanvor 7 Monaten

Build first, learn later is the most natural way humans have ever learned anything. We just forgot because school taught us the opposite for 20 years. Kids don't study grammar before speaking. They speak, then understand why. This is that, but for code.

Profilbild von Atif Saleem
Atif Saleemvor 7 Monaten

I was thinking of creating something similar because I am also vibe building while learning on the go. I have usually added in Agents rule to walk me through after each session in a structured manner. I’ll try this skill to see how it goes. Thanks

Profilbild von Somi
Somivor 7 Monaten

learning from code you vibe coded is actually smarter than generic tutorials because you already know what it's supposed to do. you just don't know how

Profilbild von Pavan Kumar
Pavan Kumarvor 6 Monaten

Love it! So good! Need this right now!!

Profilbild von Frank (Haofan) Wang
Frank (Haofan) Wangvor 7 Monaten

This idea is quite similar to @WonderingApp.

Profilbild von Pacey Li
Pacey Livor 6 Monaten

Yesterday I just used frontend-slides to study my code.

Profilbild von Thomas Tao
Thomas Taovor 7 Monaten

Build first, learn later is probably right. I’ve learned way more once the code had stakes and context.

Profilbild von Cell 细胞
Cell 细胞vor 7 Monaten

@tangjinzhou fork

Profilbild von JP
JPvor 7 Monaten

Nice one @zarazhangrui! This is what I think future of education looks like

Profilbild von Nathan Wang
Nathan Wangvor 6 Monaten

"Build first, learn later" is such a great philosophy for the AI era. Using a Claude Code skill to reverse-engineer your own vibe-coded projects into a custom curriculum is brilliant. It perfectly bridges the gap between just generating code and actually understanding what you built.

Profilbild von Azeem
Azeemvor 7 Monaten

A paradigm shift for learning to code.

Profilbild von Adam ∣ Building to $10K/mo live
Adam ∣ Building to $10K/mo livevor 7 Monaten

This is also how senior engineers actually work, they read source code, not tutorials. The risk with build-first is encoding bad patterns early. Your skill sidesteps that by making the code explain itself. That's the real unlock.

Profilbild von Santiago Pravisani
Santiago Pravisanivor 7 Monaten

Zara cooking! Love these skills!

Profilbild von Mykola Kondratiuk
Mykola Kondratiukvor 7 Monaten

honestly the hardest part of learning from a codebase is knowing where to even start. this makes that a lot less painful

Profilbild von Cherry | Collab Manager
Cherry | Collab Managervor 7 Monaten

This is really a good share.

Profilbild von Vladyslav Hunt
Vladyslav Huntvor 7 Monaten

build first learn later is how every kid learns to walk. we just forgot that approach somewhere around college textbooks

Profilbild von Tanay Sharma
Tanay Sharmavor 7 Monaten

This would be a boon for non-tech users, who fear when handed over with a Github codebase link.

Profilbild von Dotya
Dotyavor 7 Monaten

"Build first, learn later" is the thesis most people still aren't ready to hear. We've seen non-technical founders ship production features in week one, then retroactively understand what they built. The codebase IS the curriculum now.

Profilbild von Botanium
Botaniumvor 7 Monaten

This skill has a huge potential, i don’t need to code everything but i need to be able to read and understand it.

Profilbild von Kwok
Kwokvor 7 Monaten

Such a great skill Zara. I will try it on some codebase.

Profilbild von Julian Alvarez
Julian Alvarezvor 6 Monaten

very cool, love this!

Ähnliche Videos

I'm teaching a new course! AI Python for Beginners is a series of four short courses that teach anyone to code, regardless of current technical skill. We are offering these courses free for a limited time. Generative AI is transforming coding. This course teaches coding in a way that’s aligned with where the field is going, rather than where it has been: (1) AI as a Coding Companion. Experienced coders are using AI to help write snippets of code, debug code, and the like. We embrace this approach and describe best-practices for coding with a chatbot. Throughout the course, you'll have access to an AI chatbot that will be your own coding companion that can assist you every step of the way as you code. (2) Learning by Building AI Applications. You'll write code that interacts with large language models to quickly create fun applications to customize poems, write recipes, and manage a to-do list. This hands-on approach helps you see how writing code that calls on powerful AI models will make you more effective in your work and personal projects. With this approach, beginning programmers can learn to do useful things with code far faster than they could have even a year ago. Knowing a little bit of coding is increasingly helping people in job roles other than software engineers. For example, I've seen a marketing professional write code to download web pages and use generative AI to derive insights; a reporter write code to flag important stories; and an investor automate the initial drafts of contracts. With this course you’ll be equipped to automate repetitive tasks, analyze data more efficiently, and leverage AI to enhance your productivity. If you are already an experienced developer, please help me spread the word and encourage your non-developer friends to learn a little bit of coding. I hope you'll check out the first two short courses here!

Andrew Ng

1,226,579 Aufrufe • vor 2 Jahren

New short course: Building Code Agents with Hugging Face smolagents! Learn how to build code agents in this course, created in collaboration with Hugging Face, and taught by Thomas Wolf, its co-founder and CSO, and m_ric, Hugging Face’s Project Lead on Agents. Tool-calling agents use LLMs to generate multiple function calls sequentially to complete a complex sequence of tasks. They generate one function call, execute it, observe, reason, and decide what to do next. Code agents take a different approach. They consolidate all these calls into a single block of code, letting the LLM lay out an entire action plan at once, which can be executed efficiently to provide more reliable results. You’ll learn how to code agents using smolagents, a lightweight agentic framework from Hugging Face. Along the way, you’ll learn how to run LLM-generated code safely and develop an evaluation system to optimize your code agent for production. In detail, you’ll learn: - How agentic systems have evolved, gaining greater levels of agency over time—and why code agents are a next step. - How code agents write their actions in code. - When code agents outperform function-calling agents. - How to run code agents safely in your system using a constrained Python interpreter and sandboxing using E2B. - To trace, debug, and assess the code agent to optimize its behaviours for complex requests. - How to build a research multi-agent system that can find information online and organize it into an interactive report. By the end of this course, you’ll know how to build and run code agents using smolagents, and deploy them safely with a structured evaluation system in your projects. Please sign up here!

Andrew Ng

127,724 Aufrufe • vor 1 Jahr