{"channel":"llm","content":"https://harshdeepgupta.substack.com/p/6-months-and-485-my-journey-into\r\n\r\n<<< It\u2019s been six months now. Data, backend, frontend, Electron, CI, testing, landing page, design, Supabase, Resend, Lovable\u2026 the list goes on. What I thought would be a quick sprint turned into a marathon, and the todo list still doesn\u2019t seem to end.\r\n\r\nMy plan in the beginning was simple: build something quick and dirty, and share it with other people. Something about that felt very human, very exciting. So I whipped up a web app overnight using Cursor. Then as I thought more about the problem, details emerged. I learned the hard way that web apps don\u2019t play nicely with local file systems, especially when they need to handle thousands of large photos.\r\n\r\nI then thought maybe an electron app would help with my objectives. Again, I think I gave AI too much credit and dove right in. I realized the real work had just begun. Packaging, distribution, signing binaries \u2014 all those invisible details that make something feel like a product. The funny part? I discovered these only toward the end, totally a surprise (not a good one, still waiting for my apple developer account approval) after months of building.\r\n\r\nEven the landing page became its own project. I used Lovable to generate one, and soon enough, I was knee-deep in building flows for email signups, testing Resend integrations, tweaking copy, fixing layouts. It became another app in itself. If I were to do it again, I\u2019d probably try something like Framer. I can\u2019t even count the number of prompts I spent just refining that one page. >>>\r\n\r\n <<< This is, roughly, the answer to \"where is all the shovelware\". Building an app requires doing a *lot* of different things, and the AI isn't good at *all* of them yet. But it is good at some of the most time-consuming ones. And getting better at the rest. >>>","created_at":"2025-10-09T17:14:44.489092","id":684,"llm_annotations":{},"parent_id":null,"processed_content":"

https://harshdeepgupta.substack.com/p/6-months-and-485-my-journey-into\r

\n

It\u2019s been six months now. Data, backend, frontend, Electron, CI, testing, landing page, design, Supabase, Resend, Lovable\u2026 the list goes on. What I thought would be a quick sprint turned into a marathon, and the todo list still doesn\u2019t seem to end.\r

\n

My plan in the beginning was simple: build something quick and dirty, and share it with other people. Something about that felt very human, very exciting. So I whipped up a web app overnight using Cursor. Then as I thought more about the problem, details emerged. I learned the hard way that web apps don\u2019t play nicely with local file systems, especially when they need to handle thousands of large photos.\r

\n

I then thought maybe an electron app would help with my objectives. Again, I think I gave AI too much credit and dove right in. I realized the real work had just begun. Packaging, distribution, signing binaries \u2014 all those invisible details that make something feel like a product. The funny part? I discovered these only toward the end, totally a surprise (not a good one, still waiting for my apple developer account approval) after months of building.\r

\n

Even the landing page became its own project. I used Lovable to generate one, and soon enough, I was knee-deep in building flows for email signups, testing Resend integrations, tweaking copy, fixing layouts. It became another app in itself. If I were to do it again, I\u2019d probably try something like Framer. I can\u2019t even count the number of prompts I spent just refining that one page.

\n

This is, roughly, the answer to \"where is all the shovelware\". Building an app requires doing a lot of different things, and the AI isn't good at all of them yet. But it is good at some of the most time-consuming ones. And getting better at the rest.

","quotes":[],"subject":"an LLM-coding post-mortem: PicPickr"}