AI can remove something important without telling you 😅
It’s the third week of working on my little side project, SimploMail.com, and to speed things up I’ve been doing a lot of “vibe coding.” It’s been fun, but a few things became obvious pretty quickly.
I stopped using the “auto” model setting in the IDE. When it silently switches models, the quality drops fast. I can feel when the agent all of a sudden looses its intelligence 😅. So now I just pick one model I trust and stick with it.
I also try to keep each AI session focused on one small task. One feature, one change. After it writes the code, I go through everything myself. I check for hard‑coded config, make sure it didn't quietly delete a unit test to make something compile, and etc. Sometimes it does update unit test just to make it pass 🤦🏻♂️.
And I never commit without reviewing. The AI is helpful, but it can also remove something important without telling you. I've seen it happen enough times now 😅.
Replies
vibecoder.date
Some models do not understand two things at once. I constantly bennchmark this.
and I tend to stick to one model or at least one family
Yes, I've also found that with vibe coding its best to just focus on one task and do a quality check as soon as its done otherwise you'll spend the rest of your day debugging an issue that was never an issue because of one small change 😅