Comment by subhobroto
5 hours ago
> Like, I just one-shot a script that does the same with Claude, after it listed 5 free projects that do the same, including one GUI. The whole thing took less time than writing this comment.
I'm assuming the author put in the effort to validate their program handles all kinds of pictures. With that assumption:
- how did *you* validate the one-shot script that Claude handed you works correctly?
- after all said and done, and getting it to work correctly, did you end up spending atleast $30 in time, effort and money?
I am curious how coding agents would affect the future of "micro apps" - apps/scripts that do one thing and just one thing very well.
The website is clearly vibecoded, and that makes me assume the app is also vibecoded. When I open the installer, Edge gives me a warning that the file is not safe. I know that just means the dev hasn't purchased a certificate, but it adds to the general feeling that this is a rushed project that asks 30 dollars for something that I can make with Gemini in about the time it took to write this comment.
I'm pretty sure the dev has good intentions, the app is safe, and it works... but I'm not going to find out because it's too much money and too risky.
It is a good idea, though. I'll check the comments for free, open-source alternatives, but if I don't find one, I'll probably just generate a script that does this when I get back home.
It worked fist shot, and found 3k+ photos, which feels about right. Validated with Vibes. It's going to take more than $30 in time to look at them all, and it's 3k+ more photos than I had before. So, I'm satisfied.
For apps without a network-effect, or highly specialized domains, coding agents are driving a convergence of the cost of software toward the cost of tokens to generate it. OP should have MIT licensed this, collected his 15m, and moved on to the next idea.