AI coding tools seem to come in two main flavors: IDE-based, like @Cursor and @GitHub Copilot, and terminal-based setups, like using @Claude Code to generate commands, scripts, or entire files. Both have their fans, but which one actually helps you move faster?
Curious what flow people are sticking with long term, and where you see the most gains (or frustrations).
I have been a big fan of @Aqua Voice but do need something local for the times I don't have internet or am traveling. So I wanted to give @OpenWispr a try but didn't really want to go through the whole setup for it... so I gave @Claude for Desktopaccess to my files and computer and... it basically instantly installed the whole thing and got it working! Then I asked it to package for me as a Mac app (.app) and what do you know... it did! Was honestly kind of amazing. There was one issue that I had to keep troubleshooting and that's sometimes Claude would reference the wrong environment or file... it could figure it out, but just something to pay attention too.
So now you can vibecode and quickly iterate on Open Source software using Claude Desktop, @Cursor, and @Warp. Use Claude to set it up, Cursor to iterate and build, then Warp to polish and debug.
Have there been any Open Source software that has scared you away but you might try install with this method?
I might be missing some but I've been pretty much in love with @Lovable, @Cursor, @bolt.new and have been trying to use @Replit more and I honestly haven't touched @BASE44 too much but have heard good things. @chrismessina has nudged me to use @Windsurf for whenever I build another Raycast Extension! Currently I use: - @bolt.new / @Lovable - @Cursor - @Warp Curious what everyone thinks is the top one so far!
A few months ago I launched lovableprompts.app, a tool that helps makers and designers turn messy product ideas into optimized prompts for Lovable (and other vibe coding tools). It was meant to be just a small experiment to make the blank page problem less painful.
AI coding is pretty mindblowing but sometimes it's a headache built on a mountain of bugs. Usually that comes down to issues with how you prompt. So, with that in mind, I'm starting a crowdsourcing discussion so we can all improve our prompts and in turn our apps.
Share the exact prompts that turn blank AI requests into real world code. Show us how you go from generate a REST API to a deployable service in just a few steps.
I made my first chrome extension using solely Chatgpt. I wanted to see if it was really possible for a non-technical person like me. I was really proud of myself, it inspired me to want to build more! But when I tried to add more features to it, I think the code got too bloated and messy and it just blew up so I just continue to use the extension for the basic need I have to save and organize notes I make on products that are interesting to me without all the bells and whistles I would have wanted. I wasn t trying to make money on it, just something to prove I could do it, and I got to feel what it was like to launch something on Product Hunt - yay!
But I ve also seen alot of posts/comments from more technical folks around the web hating on non technical people for believing that you can go from 0-1 and that these new tools are best to speed up work for technical people who already know how to code, not for newbies who end up with something that works by copying and pasting crappy code spit out by LLMs of their choice.