Everything about this is just embarassing

I wrote my own blog about moving to self-hosting on Hetzner with Immich

https://www.sam-brink.com/posts/self-host

I recently started stacking my PRs, makes life easier

https://docs.github.com/en/pull-requests/how-tos/stacked-pul...

LLMs will still produce huge PRs even in a stack if you are not careful enough.

That's a different problem. The benefit of stacked PRs is that they let you review each piece on its own, which helps you/team keep mental alignment with changes in the codebase and disregard individual slop layers.

Closed source? No Thanks

I had this idea to build a webpage that can rewrite itself on the edge using a local model and a simple harness in the frontend, while playing around with storing HTML state in the URL.

Currently supports Gemini Nano (local), Anthropic, or OpenAI. Gemini Nano is a lot less impressive than the SOTA models, but it's still fun to see it work!

https://github.com/oxedom/seed

MCP-Apps could be the solution for tailored UI.

Out of curiosity, what would the setup for reverse enginering a iOS/Android app look like using Charles Proxy?

You can download the .vsix file directly from marketplace.visualstudio and install it in cursor.

Recently got exicited about transforming my Tensorflow.js Parking mointoring application to a more general webapp that can do many things with Computer Vision, as well as upgrade from YOLO7.

https://github.com/oxedom/parker