Aryan retweetledi
Aryan
610 posts

Aryan retweetledi
Aryan retweetledi
Aryan retweetledi
Aryan retweetledi
Aryan retweetledi
Aryan retweetledi
Aryan retweetledi
Aryan retweetledi
Aryan retweetledi
Aryan retweetledi
Aryan retweetledi
Aryan retweetledi
Aryan retweetledi
Aryan retweetledi
Aryan retweetledi
Aryan retweetledi

My AI side projects this year:
◆ llamacoder.io: 338k users
◆ usenotesgpt.com: 75k users
◆ blinkshot.io: 70k users
◆ llamatutor.com: 67k users
Here's exactly how I approach building AI side projects in 7 steps:
1. Think of an idea that excites you but that is very simple. You should be able to describe it in 5 words to anyone.
2. Make sure the UI looks good and is straightforward to use. Nobody will use your project if it doesn't look great, so I focus a lot of time on this aspect.
3. Keep the app extremely simple. All my apps above have 1 single API call to an AI model – that's it.
4. Try to incorporate the latest AI models so the end result is especially impressive (even though it's trivial with code, like 1 API call to an AI model).
5. Launch early then iterate based on feedback from users. The benefit of launching early is that you can pivot or work on a new idea if what you launched isn't working out so you don't sink too much time into a failed project.
6. Make it free + open source so folks can learn from it and are incentivized to share it and follow you. I gained about thousands of Twitter followers and 6k GitHub stars from the 4 projects above.
7. Keep shipping. A lot of my AI apps don't do well and I usually don't have a good sense of when they will do well vs not. Scope down the work and keep shipping.
I do want to call out that I do have a large twitter audience and that helps a lot. With that said, I've seen folks without any followers have successful side projects by doing the things I talked about, so I still stand by them!
English

















