NotBiebs and 69 others's avatar
NotBiebs and 69 others
notbiebs@primal.net
npub1vp8f...npsw
impermanently impermanent ๐Ÿค™
i got a 1 year core plan for free from replit today, so i made a gamified duolingo style mobile app for calisthenics. it uses expo go, so you don't even need an apple developer account if you just want to make custom mobile apps for yourself ๐Ÿ˜€. the replit agent with default settings seems a lot dumber then the agent with auto mode in cursor is even though it burns credits faster. i was able to vibe something decent, but i had to keep prompting it to fix simple things like overlapping elements.
chess is a weird game. i feel like i'm stuck and not getting any better, and then i look at my stats and they are all improving. haha wtf. image
Damn, I took a long break. Mostly just went to the gym and played chess all day for like 8 months ๐Ÿ˜‚. image
I came up with this idea while I was walking around the lake today. Is anyone working on something like this? If not, should I make it? Any feedback would be appreciated. image View article โ†’
Maybe this diarrhea outbreak at Taco Bell will finally get people to stop eating that shit. Taco Bell is so gross. Wtf. ๐Ÿ˜‚
I made a privacy focused app for analyzing blood work. It's similar to https://getbased.health, but simpler. Currently, you have to run the app locally and also have Ollama running on your machine. So there's more steps to get the app up and running, but the privacy guarantees are better and you can run the app completely offline once you have everything set up. The app gives you insights about specific lab panels as well as trends in your overall health and specific health markers. You can also chat about a specific lab panel or trends of a specific health marker. I've been using gemma4:26b-mlx with the app which works great on my Mac Mini M4 Pro with 64 GB of memory. I was originally using qwen3.6:27b which gave me good insights, but was really slow. gemma4:26b-mlx is a lot faster and generates responses similar to what I was getting from qwen. The repo includes a /compare-live-evals skill that can be used to help you choose what model works best on your machine. I currently only have live evals for panel chats though. I'm planning to add live evals for trend chats soon. image
i was chatting with chatgpt about onchain metrics and then asked it for an end of year price prediction based on onchain activity. turns out chatgpt is more bullish than most of you. ๐Ÿ˜‚ image
โ†‘