Found this by accident last week. A friend opened something I d built, and the today view showed yesterday s data. His phone was set to a different timezone because he d been traveling. Nothing crashed, no errors anywhere, it just quietly showed the wrong thing, and he assumed the app was broken...

When I went back through the code, the AI had used the browser s local time in some places and server time in others, with no consistent rule. Dates were stored as plain strings in one table and timestamps in another. Everything worked perfectly on my machine because my laptop and my server happened to agree...

It s one of those things nobody puts in a prompt. You ask for a daily summary and you get one that works in exactly one timezone. Daylight saving shifts, users who travel, midnight edge cases, a device with a wrong clock: all of it fails silently, and you only hear about it as your app feels off.

My current habit is to tell the AI upfront: store everything in UTC, convert only at display time, and then I test once with my system timezone set somewhere far away like Auckland. It takes ten minutes and has already caught two bugs...

All vibe coded apps that I make share the same hidden problem. In the first page, everything feels planned out. But on the third page, the buttons have a new corner radius, the space becomes looser, and one of the headers features a font weight that I didn t select.

Why? Every prompt is a new choice, and the AI doesn t remember any design choices until you tell it to. I decided to use a tiny style guide on top of the project with five style rules: one accent color, one corner radius, eight pixel spacing options, two body text sizes, and one button style.

Hey, I was wondering how many of you are coding from the phone - it's easier to do it with AI coding agents now, so I'm wondering how often developers are doing it.

Personally, I do some coding tasks daily from my phone and I'm curious how others are doing it?

honest self-assessment time. when an agent finishes a task and shows you a diff, what actually happens?

for me it depends entirely on the size. under ~30 lines I read every line. past that I mostly skim for anything that touches auth, payments, or migrations and trust the rest if tests pass. I know that's not a great policy, it's just the realistic one given how much code moves through these sessions in a day.

I'm not a developer. I build by directing AI agents, so tests are how I know something works. I can't check it by reading the code.

For a while the green checkmarks were enough for me. They shouldn't have been.

Now every bug fix comes with a test. Before I accept it, the bug gets put back on purpose and the test has to fail. When we started doing that, we found tests that had been passing on broken code the whole time.

Someone on Indie Hackers put it better than I could:

A production error pointed to a null value. I asked the agent to fix it. It added a guard clause. Tests passed. Deployed.

Error came back because the guard was in the wrong layer.

I pasted a stack trace to the agent. It asked for the file. I pasted the file. It asked for the config. I pasted the config.

Forty minutes and 12,000 tokens later, it found a missing comma in a dependency injection string.

I asked Claude Code to rename a function across the codebase. It found 12 files, made the change confidently, and reported success.

What it missed: a thirteenth file in a directory outside its initial search scope. No warning. The app kept working because that file only ran on a rare edge case. I caught it three days later during an unrelated test.

We're an AI-native startup shipping fast with augmented coding, but the debt it creates is different from anything I've seen before.

I remember in my old team we put aside around ~20% of engineering time to pay down debt that accumulated during feature releases.

Hey Product Hunt community!

We ve all been through this pain: you feed a 50-page PDF, financial report, or contract into an LLM, ask for a quick summary, and it confidently hands you data that is completely made up.

If a creative writing bot hallucinates, it s fine. But when it happens during document processing like in your RAG pipelines or data extraction it s an absolute disaster.

Honestly, my team and I have been losing sleep over this exact problem. It s why we are building Ethos by DocuShell (it's an open-source verifier for document citations, source evidence, and RAG). While building it, we realized just how easily LLMs get totally confused by simple tables or negative sentences (like missing a "not" or "except").