Tell HN: Some of My Recent Ideas

I thought it'll be fun to share some different ideas that I've had AI build in the last couple of weeks or months. Using my local Qwen 27b model.

I had AI build a Roku remote in the web and connect to my jelly fin so I can easily search for shows and autoplay them on my Roku. Also features an API and I can scan an NFC tag and it will automatically open a video on my Roku.

I have an HD home run so I had AI build me a DVR page, it could use some work but overall it's working and it's pretty cool.

I've been building a health ecosystem tracking food journaling about health, and then adding NFC tags to different medications and supplements. I had to build a Android app that sinks any of my NFC tag scans automatically to my server. Since I don't run tailscale or anything like that to get in and out of my network.

I have a game boy color cartridge with SD card. I thought it would be fun to add ebooks. Haven't tested this one yet but in theory I'll be able to copy books onto my game boy color cartridge and then use my game boy Pocket to read books lol.

I have a Ricoh theta S, that used to have an app, but doesn't appear to work with latest Ricoh apps lately. So it's building me an app so I can take 360 photos, and embed gps, and time/date info easily. (Basically connect to my phone so it happens automatically).

I have a handful more but I'll stop there for now.

Got any fun ideas you've been playing with?

(I'm not building any of these for money, they are for my own personal enjoyment).

I might post a spec/prompt to my blog for these at some point but for now this is all you get.

2 points | by onaclov2000 18 hours ago

2 comments

  • harishbala 8 hours ago
    The health idea of yours is really interesting imo lol.

    I’ve been playing with two: 1. Knowledge Graph that auto parses vital context out 2. A security feature for agentic memory to secure chunks that don’t determine perms in memory

    Would love to chat with anyone on these lol

    • onaclov2000 2 hours ago
      I'm not sure what each of these mean in practice, but are both (kinda) a way of securing things? I could take the knowledge graph idea in two ways, one meaning it looks at a knowledge graph, and finds the vital stuff for a user, or for security reasons it removes things from the graph that "shouldn't be there".

      I did something maybe similar to the shouldn't be there by building something that processes logs and replaces things, so if you wanted to do a live or recorded demo, you could make sure certain data didn't show up (not necessarily security sensitive data, but like dumb things like a path on your machine). Fun aside: I also use speech to text, then cleaned up the transcript and then text to speech with a voice clone of myself using chatterbox cause my input audio was really really bad lol

      Thanks for replying!

      Edit: my phone seems to be not typing what I think I'm typing then I gotta reinterpret what it did and remember what I said lol.

  • jtap 1 hour ago
    [dead]