Elon Musk openly admitted that Claude Opus 4.5 is outstanding, then added that Tesla engineers still prefer Grok. The most predictable plot twist ever: Guy who owns Grok says his own AI is better.

I'm not a developer. I came up writing HTML, CSS and Sass, and now I build by directing AI agents.

With AI, adding a feature is cheap. That makes scope creep really easy.

One thing that helps me: my project's README has a "what it doesn't do" section. Things I decided on purpose not to build, each one because it would add legal risk, security risk, or a number I couldn't defend.

Since I don't write the code, my control lives in decisions like those.

Vibe coding is great until your product has real users. Then the "vibe" hits a wall. Slow queries. Weird bugs. Features that break other features. You can patch it for a while. But eventually, the tech debt catches up.

At what point do you stop vibing and bring in someone who actually knows what they're doing?

Is it:

• When you hit 10 paying users?

• When the app crashes more than once a week?

• When adding a new feature takes longer than building the MVP?

Spent a chunk of Saturday on this and felt obligated to share.

The setup: Claude Code wrote a clean, working function that passed every test. Looked perfect. Pushed to staging. Production crashed.

The bug: the agent had quietly used a deprecated method that worked in tests because of a mock. The mock didn't trigger the deprecation warning. The agent had no way to know it was using something on its way out.

A products fetch in my iOS app came back empty. No error, no crash, nothing unusual in the logs. The purchase button simply sat there greyed out, because an empty list is a perfectly valid response and every check I had passed on it. App Review found that one and I had not.

The pattern is a call that fails without failing. An empty result, a stale cached value, a permission that was denied months ago and now returns nothing instead of an error. The user is stuck and the code is behaving exactly as written, which is why an agent cannot help much either. Ask it to reproduce the failure and it writes a test that agrees with the current behaviour.

Building quick MVPs with AI tools is amazing for checking if people actually want your product.

But as soon as real users join stuff like error handling and account permissions start breaking.

Learned the hard way that a quick prototype isn't built to scale.

Rebuilding the logic properly takes less time than constantly fixing bug after bug in AI code.

Spent months reviewing AI-written code line by line like a pull request, and it was draining my speed.

Recently switched to checking the test cases first instead. It instantly shows what the AI thinks the logic is supposed to do especially when it completely misunderstands the business rules.

Anyone else checking tests before touching the actual implementation code?

Hey everyone! Do you ever feel you've built something only you want?

I sometimes think the beauty of AI is that you can build so fast, it doesn't matter if it works or not, as long as YOU get value, it's worth it.

I used to play Magic The Gathering when I was young, and still love it today.

I've noticed my workflow has completely inverted over the past year. I used to sit at my Mac typing code; now Claude Code or Cursor does the long stretches, and my job is the interruptions: it stops, asks "should I refactor this or keep the interface stable?", and waits until I answer.

Which means I'm chained to my desk not by the work, but by the questions. Walking back from the kitchen to type "yes, option 2" feels absurd.

Curious how everyone else handles this:

I have been using vibe coding more lately

The speed is honestly crazy

You can have an idea in the morning and a working version by the evening

But then you look at the code later and realize you built way more than you actually needed