671–680 of 805 posts
This is my "use AI to finally build that totally frivolous website you've had in the back of your mind for years" project.
$2 of every card sent benefits the Jazz Foundation of America.
https://curvefit.app it's a weight-training app that helps you train along your "pareto frontier" of weight vs reps. The idea is to train at lower weight-higher rep, medium weight medium reps, and higher weight, lower reps for every movement. I tried to develop my own weight training program following bits and pieces of advice from bodybuilding forums and ended up injuring several tendons in my first year. So I did a…
I maintain LibVLCSharp (https://github.com/videolan/libvlcsharp) and work on VLC for Unity (https://videolabs.io/store/unity). Lately I've been building VLCLR, which lets you write native VLC plugins in C#, and experimenting with local AI for real-time video analysis.
Also working on Kyber for Unity (https://gitlab.com/mfkl/kyber-unity), bringing low-latency video and robotics tooling into Unity.
For various reasons unrelated to the project, progress since last month has been slow (and I expect the next month will be as well). Most of the work I've done has been on peripheral features.
I added opt-in collection of gameplay data that will give me data for a gameplay session, which I can analyze to find ways to improve the UI, UX, gameplay, balance. By default, no identifying information whatsoever is collected.
I added global text size option as an accessibility feature and used an MCP server to have Claude do the initial layout testing. This was an interesting experiment, but requires enough tokens that it's not very practical as a normal part of development. These features went hand-in-hand -- via the MCP server, Claude takes a screenshot every five seconds to decide what to hover over or click on next. These screenshots consume tokens rapidly, so they are reduced in size. With a larger font size, the screenshots can be reduced further with the text remaining legible to Claude.
When other life matters settle down a bit later this year, I expect to release a demo version while I continue development. (From a technical perspective, the demo has been ready for a while, but I want to spend more effort on some gameplay aspects first.)
I've been working on this on the side for around 5 months, initially to scratch my own itch, but recently some friends and colleagues have started using it too.
- Lightweight Terminal UI written in Go
- Control chat sessions via native Claude Code or Codex UI in a remote browser
- Identify and surface questions from multiple agents at once
- Cron jobs for automation
- Share remote coding sessions between team members
- Auto-repair PRs
- Auto-rotate subscription accounts
- Allow agents to send messages between chat sessions and across model providers
- Register Github callbacks so agents can respond to CI events in realtime
- Run agents on a mac mini or similar, and control them from your phone while you're on the go
projects per year in "Ask HN: What are you working on?" year projects avg/month ---- -------- --------- 2008 123 10.2 2009 104 8.7 2010 666 55.5 2011 86 7.2 2012 46 3.8 2013 389 32.4 2014 146 12.2 2015 104 8.7 2016 471 39.2 2017 456 38.0 2018 242 20.2 2019 246 20.5 2020 882 73.5 2021 837 69.8 2022 363 30.2 2023 425 35.4 2024 2122 176.8 2025 6220 518.3 2026 6093 677.0 (Jan-Sep) Top five topics per year (% of that year…
https://mirekrusin.com/cave Palantir like system – data, ontology, logic, actions, security, operational workflows – packaged as single cli, local first, git friendly text .cave files and sqlite3 instead of k8s-style complexity blowup. Working on the weekends. Next is probably extension of the language to integrate something like https://github.com/mirek/ast for arbitrary ast traversals/modification/generation/better…
It's a beautiful language