Hacker News
The author shares their perspective on leveraging AI as an 'eager, book-smart junior engineer' to accelerate the process of writing quality code. They introduce the concept of 'vibe engineering,' which combines traditional engineering principles with the speed of AI LLMs, and outlines a workflow enhancement strategy.
AI 生成摘要
作者分享了他們如何將AI視為一個「熱情、書呆子氣的初級工程師」，以加速編寫高品質程式碼的過程。文章提出了「氛圍工程」（vibe engineering）的概念，結合了傳統工程原則與AI大型語言模型的極速，並概述了增強工作流程的策略。
Essay - Published: 2026.01.23 | 1 min read (491 words)ai | software-engineering | tech
DISCLOSURE: If you buy through affiliate links, I may earn a small commission. (disclosures)
I recently did a small tech talk at Recurse Center's weekly presentation day on software engineering with AI so thought I'd share the key ideas here.
I've also recorded the presentation slides with a lot more detail (RC presentations are only 5 mins!).
I think of AI as an eager, book-smart junior engineer that doesn't eat, sleep, or get bored. It's a super fast reader, typer, and researcher. It's a decent coder in most mainstream languages and has read tons of books and articles. But it has little hands-on experience, low taste and judgment for choosing what to apply when, and low discipline for sticking to rules.
There are three approaches to building with AI:
I think the future is vibe engineering - take the principles of traditional engineering and leverage the super fast speed of AI LLMs.
Different work calls for different approaches.
The standard agentic AI loop is: Plan -> Build -> Review.
This is very similar to a normal software engineering cycle. The difference is that you now play the role of the Tech Lead / Manager and AI is the implementer.
You can enhance each phase:
Better Planning:
Better Building:
Better Reviews:
And once you've gotten those loops nice and reliable, you can move onto chains where AI auto passes from one loop to the next.
From the Pragmatic Engineer:
The best way to support my work is to like / comment / share for the algorithm and subscribe for future updates.