Vibe coding as a love language

Source: Dev.to

Why I Started Coding on Weekends

I never used to be a person who coded on the weekends. Not because I lacked ideas, but because it felt unfair to my partner to spend the whole weekend holed up at my desk instead of being together.

AI tooling changed that. It lets me scratch the itch of creating silly, no‑business‑value projects just for fun, and the barrier to add value is natural language. Now a program can be a fun game or puzzle we do together.

The First Project: A Speed‑Reading Test

This weekend I wanted to recreate the viral speed‑reading video as an application that:

1. Pulls in a unique article.
2. Tests the user’s reading comprehension.

I felt like the fastest reader ever after taking the original test, but I wasn’t sure I actually understood what I’d read.

Because my husband has zero technical background (or interest), I started with Goose Desktop and crafted the initial prompt together.

The Initial Prompt

I want to make a website based on the viral speed reading test. This site should pick a wikipedia article at random for the test and have an input at the end where the player has to put in what they understood about what they just read. The site should then be able to judge the reading comprehension. Help me design a plan to implement this. The first step will be understanding what the viral speed reading test is so you will need to research that

We used Sonnet 4.5; the model suggested a Next.js (React) application, which felt natural.

Iterating with My Husband

When the prototype ran, my husband immediately suggested design tweaks—more readable fonts and a steadier focal point for the red letter. He guided me on what to tell Goose to do, and we iterated together.

Adding New Features

I wanted a way to pull a fresh article and show a loading state if the first article wasn’t long enough. The next iteration added that logic, along with a test‑and‑restart flow.

Reflections

Even though this was a purely for‑fun exercise, it was fascinating to watch someone far removed from tech use a tool like Goose Desktop and solve problems. He focused on how the application should feel and look, rather than the underlying code—very different from the developers I usually work with.

As a developer, I found it hard to walk away from the “finished” product. I started spotting rough edges and thinking about user‑experience concerns: network failures, many retries to find a long enough article, duplicate content handling, mobile compatibility, and so on.

At the end of the day, the goal wasn’t a polished product but a new way to share fun with anyone, even a non‑technical friend or partner. Perhaps the future of social interaction includes ephemeral games we spin up and play together over an evening.

While there’s a lot of valid criticism of AI, this technology can also bring us closer to the people we love and help us discover new ways to connect.