Programming with AI: You're Probably Doing It Wrong

Programming with AI: You're Probably Doing It Wrong

2025 is the year of Artificial Intelligence. With GPT-5 just released, many developers will re-evaluate their use of large language models for assisting in their daily work.

I’m here to tell you: you’re probably doing it wrong. And you’re missing out on the real power that AI assisted development can give you.

What “doing it wrong” looks like

Let’s kick off with a (non-exhaustive) list of symptoms you’re using your AI coding assistant wrong:

Opening a standard chatbox with your LLM of choice and manually providing context by shuffling code snippets, logs, and error messages.

Copy-pasting code back into your editor, then fixing the obvious breakages it couldn’t anticipate—or worse—just shipping code you don’t understand to production.

Repeatedly questioning your own sanity about why the code the LLM wrote is not working because it didn’t know about the latest version of that library you’re using.

Skipping the whole testing phase of development because the LLM does not make mistakes.

Feeding the LLM your entire codebase or issue list and wondering why it didn’t work. LLMs must be stupid.

... continue reading