I keep seeing apps add smart generation buttons that just make the interface clunky. Extra menus, extra popups, and prompt boxes cover up what I was trying to do.
|Some tools solve real problems, but others just throw in smart shortcuts because it is trending. The worst part is when the automated option takes longer or feels less predictable than doing the task by hand.
Has a tool you used gotten worse after an update like this? Or has one actually surprised you by being useful instead of decorative?
For me it's weather apps. I've tried a bunch and none of them feel right. Either too cluttered, too simple, weird notifications, or an interface that just doesn't make sense to me. I keep going back to the default one on my phone, which I don't even like. Not looking for recommendations specifically, just curious if anyone else has that one type of app they can't seem to solve.
Counted it up and I've downloaded 6 different habit apps this past year. currently using zero of them. they all basically do the same thing check a box, watch a streak grow, get a notification when you miss a day. but something about each one makes me quit after two or three weeks. sometimes it feels too game-like, sometimes the notifications get annoying, sometimes i just forget it's on my phone.
what's the longest you've stuck with one and what made it different?
Scrolling the leaderboard this morning, I realized I could barely tell any of the products apart. Every tool follows the exact same formula, using generic keywords and audience tags jammed together. It gets to the point where my brain just glazes over after reading five identical titles in a row.
I get why makers do it since it clearly states what the product is, but it makes everything feel forgettable. Do you think this kind of predictable naming actually hurts a launch, or do people just click based on the logo and upvote count anyway?
"If you could redo your first Product Hunt launch, what would you change? Asking because I'm preparing mine and want to learn from others' regrets not just success stories."
A coding agent never sees a tool's backend. It sees the tool's description before the task and the tool's result after the call, and nothing in between. That sounds obvious until you notice how many tools were designed for a client that could do the second half of the job for free.
A language server is the clean example. Under the protocol, a find-references request returns a list of locations: a file, a line, a character offset. That is the right answer for an editor, which has the file open and can jump there. An agent has nothing open. Hand it a location and the next thing it does is read the file, one call per address.
A small pilot study posted in August measured what that costs. With grep and an LSP-backed tool both available, three models picked the semantic tool 0 to 6 percent of the time on code-location tasks, which is roughly never. The author then kept the same backend and the same set of references and changed only the reply, attaching two lines of source above and below each one. On a multi-file rename, pass@1 rose from 0.67 to 0.83 and follow-up file reads fell from 15.2 to 3.2 per episode. The scale is a pilot, six tasks and a few repos, so treat the numbers as direction rather than magnitude. The direction is clear enough.
The second half of the story came from Spotify. They wanted Claude Code to stop reading large files whole and route that work to a smaller model. Rules in CLAUDE.md sort of worked. Advisory, though, and the model could ignore them. What held was a PreToolUse hook that blocks the read past a line threshold and names the alternative, whether or not the model read any instructions about it.
I have seen people advicing each other to build a saas around your own problems. But, the question is, anyone who is starting out or hasn't got a problem yet, what are they gonna build?
Apart from this, there are many people who build passion projects and many others just build what is trending.