My kid just started high school. The way they communicate information is absolutely insane. So I built a web scraper + MCP to aggregate it all, then layered on a snarky chatbot with a PG-13 Dave Chappelle personality.The number of communication channels are just insane: - email - Google Docs - Canvas - PDFs - School Messenger - the official school website - 5 different other websites that...
https://github.com/mattmireles/local-motion
Using a local LLM for coding agents is complicated, so I built a Cursor + VS Code plugin that makes it easy.It automatically profiles your machine, picks a model that works for your machine, then runs a local server, sets up a Cloudflare Quick Tunnel and walks you through connecting it to Cursor.In the end, you work like you normally do in Cursor and just choose "Local Motion" as your model in...
https://open-vsx.org/extension/Transcendence/gist-discover https://gist.is/discover
We literally posted our Show HNs within minutes of each other: https://news.ycombinator.com/item?id=48768342
Great minds think alike.
Dunno about you, but I cannot keep up with the volume of AI research. Reading one paper properly takes 30–60 minutes, and it's hard to know which are even worth it.I built Gist, an AI summarizer for ADHD brains. Each paper is a clean slide deck with four layers you move through:1. the Gist – the whole idea 1-2 sentences 2. Logic – breakdown of the argument + evidence in discrete ideas 3....
https://github.com/mattmireles/magenta-realtime-2-iphone
Last Thursday, Deepmind released Magenta Realtime 2 , an open source music generation model. They said it could run on Mac, but not iPhone.As a v̵i̵b̵e̵ ̵c̵o̵d̵i̵n̵g̵ ̵a̵d̵d̵i̵c̵t̵ agentic AI maxxi and person who has melted iPhones before (link at bottom), I took that as a personal challenge and made it my weekend project.On Saturday, I got it to run for 10min straight on an iPhone 12 Pro from...
If you run a smaller whisper-distil variant AND you optimize the decoder to run on Apple Neural Engine, you can get latency down to ~300ms without any backend infra.
The issue is that the smaller models tend to suck, which is why the fine-tuning is valuable.
My hypothesis is that you can distill a giant model like Gemini into a tiny distilled whisper model.
but it depends on the machina you are running, which is why local AI is a PITA.
Here’s the trick: use Gemini Pro deep research to create “Advanced Hacker’s Field Guide for X” where X is the problem that you are trying to solve. Ask for all the known issues, common bugs, unintuitive patterns, etc. Get very detailed if you want.
Then feed that to Claude / Codex / Cursor. Basically, create a cheat sheet for your AI agents.
This will unlock a whole new level of capability.
I’m @mattmireles on Twitter — feel free to DM me.
The actual plan was to distill Gemini 2.5 Pro into the best on-device voice dictation model.
Pretty sure it would have worked. Alas.
Also, I had a huge head start, as I spent a month or two working on this in September 2025, shelved it and dusted it back off this weekend.