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 .

I'm a non-technical founder (well, semi-technical I can read some basic code, but writing it from scratch isn't my thing).

A few weeks ago, I launched Belink, a free link-in-bio tool that competes with Linktree.

The entire thing was built using Manus, an AI agent that writes code, deploys it, and manages your project end-to-end.

At @UXPin we've just deployed the prompt enhancer for our AI component creator.
From now on, short prompts will be evaluated and refined if the AI considers them too weak. This aims to improve the AI output - with prototypes returned by the AI more detailed and diverse.

Example and output below:

Original prompt: 'news portal'

Refined prompt:

I've been letting Claude/Cursor do most of the typing lately and I noticed I stopped double checking what actually goes out in the API calls. then last week I caught myself pasting a real customer row into a prompt just to debug faster.

anyone else have a moment like that? where the vibe coded thing had a hole you'd never have shipped if you were writing it slower. secrets in a log, some data you didn't mean to send anywhere, whatever. My product is focusing on this and I would like to know is this a serious issue?

Wherever you code (online, CLI, or IDE), everyone has some love, hate or horror vibe coding stories, from building a prod-ready app in minutes to the whole repo got wiped. Would love to hear your story.

Building with Ai is scary and the internet has as much bad propaganda as it claims your work is slop.

Most of us don t have coder we can reach out to we think has enough time to scan our code and let s face by the time they were done we would have to ask them to scan a whole new section we finished in the meantime.

I've been building my own AI agent for the past few months, and the one problem I keep coming back to is hallucinations.

At first I thought the answer was better prompts. Then I added memory. Then I redesigned the architecture, split long-term and short-term memory, added retrieval, planning, and verification. Every time I felt like I'd solved it, another weird failure showed up everytime.

Sometimes the agent remembers things perfectly and other times it confidently ignores its own memory or invents an answer when the information is already available. The frustrating part is that these failures aren't always predictable they often happen after the system gets more capable, not less.

While vibe-coding, most bugs are easy to spot because the compiler throws an error or the UI breaks. But here s a subtle, deeply hidden issue that often slips past human review: Silent Context Leakage in AI-Generated State Management.

When prompting an AI agent to continuously iterate on asynchronous functions or complex state pipelines, it frequently re-uses existing variable names or merges outer-scope context into asynchronous closures without explicit cleanup.

Why it's hard to catch:

1. No syntax or runtime errors: The code runs smoothly without crashing.

2. Intermittent behavior: Race conditions occur only under heavy load or specific execution timings, making standard tests pass consistently.

3. Superficial logic check: To a human reading the code casually, the flow looks clean, modern, and perfectly idiomatic.