HN 提问:您将如何从零开始学习 AI 辅助开发?

2作者: SMAAART11 天前
I&#x27;m a director&#x2F;exec, not a software engineer. Background&#x27;s mostly data analytics, SQL and Excel day to day, some R and PostgreSQL. Years ago I could hack together basic HTML&#x2F;CSS&#x2F;PHP too.<p>Got into AI early and now use ChatGPT and Claude constantly. With their help I&#x27;ve built a handful of web apps, some Python scripts and desktop tools, and an Android app on Supabase with real multiple users.<p>So I can build things. But I&#x27;m very aware there are big holes underneath it. I can usually get something working without really knowing why it works, whether it&#x27;s actually well built, or what&#x27;s going to break down the road once it gets more complex.<p>Feels like it&#x27;s time to go back to fundamentals. Michael Jordan still worked on his footwork, that kind of thing.<p>What I&#x27;m hoping to get to eventually:<p>* build small useful apps, windows&#x2F;mac&#x2F;android&#x2F;ios&#x2F;web<p>* automate chunks of my own and my team&#x27;s work<p>* maybe build a simple SaaS at some point<p>* generally not get left behind, open to this reshaping my career or spinning into a side thing<p>Was hoping for something structured, starting from prompt&#x2F;context engineering and working into real programming fundamentals, APIs, databases, architecture, security, testing, deployment. Problem is anything I find is stale within months given how fast this moves.<p>Not looking for free necessarily, and definitely not looking for &quot;learn to code in a weekend.&quot; Willing to put in real time.<p>For people who&#x27;ve gone down this road already: what&#x27;s actually worth learning properly, what&#x27;s fine to just learn enough to supervise, and what can honestly just stay AI&#x27;s job?<p>P.S.: Yes I polished&#x2F;refined this post using AI, but I first wrote it all myself (the original was twice as long).
查看原文
I&#x27;m a director&#x2F;exec, not a software engineer. Background&#x27;s mostly data analytics, SQL and Excel day to day, some R and PostgreSQL. Years ago I could hack together basic HTML&#x2F;CSS&#x2F;PHP too.<p>Got into AI early and now use ChatGPT and Claude constantly. With their help I&#x27;ve built a handful of web apps, some Python scripts and desktop tools, and an Android app on Supabase with real multiple users.<p>So I can build things. But I&#x27;m very aware there are big holes underneath it. I can usually get something working without really knowing why it works, whether it&#x27;s actually well built, or what&#x27;s going to break down the road once it gets more complex.<p>Feels like it&#x27;s time to go back to fundamentals. Michael Jordan still worked on his footwork, that kind of thing.<p>What I&#x27;m hoping to get to eventually:<p>* build small useful apps, windows&#x2F;mac&#x2F;android&#x2F;ios&#x2F;web<p>* automate chunks of my own and my team&#x27;s work<p>* maybe build a simple SaaS at some point<p>* generally not get left behind, open to this reshaping my career or spinning into a side thing<p>Was hoping for something structured, starting from prompt&#x2F;context engineering and working into real programming fundamentals, APIs, databases, architecture, security, testing, deployment. Problem is anything I find is stale within months given how fast this moves.<p>Not looking for free necessarily, and definitely not looking for &quot;learn to code in a weekend.&quot; Willing to put in real time.<p>For people who&#x27;ve gone down this road already: what&#x27;s actually worth learning properly, what&#x27;s fine to just learn enough to supervise, and what can honestly just stay AI&#x27;s job?<p>P.S.: Yes I polished&#x2F;refined this post using AI, but I first wrote it all myself (the original was twice as long).