Made some big updates to my side project. including adding loads of interactive maps.
local data for local people
Any conversation
ai coding feels like it has reached diminishing returns for me. luna is my default orchestrator, routing work by complexity. in practice, usage lands around 16% luna, 48% sol, 30% astra, and 6% terra. at this point, i care less about each new frontier release. the system already finds a capable model for the job. the frontier is moving beyond my day-to-day work, so iโm happy to settle into predictable models for a while.
been building a voice first os using jev and some small voice models. I'm surprised how well it's working and I'm very close to the point where I can go into a feedback mode and tell it what behavior I want changed, it will spin up Claude or codex inside itself and setup the build to restart itself and continue with new code. tempted to let it build itself completely
I'd been listening to di.fm for years, and have been missing a MacOS app. Thanks, Antigravity, for making the world of personalized software really easy: fifteen minutes and two small bugs later, github.com/haykinson/difmplayer gives me a Spotify-style player. Yay!
WezTerm for local and remote multiplexing really is the ideal experience - it's so much better than using zellij, tmux, zmx, and friends.. I don't think they pitch this feature hard enough on their site.
I think the in-terminal multiplexers have their place - e.g. if you need to access from mobile (no WezTerm there) or on machines where you simply don't want to install WezTerm for some reason. WezTermrm could probably eliminate that last one by packaging just the mux server.
I notice that language models are much better at programming than at writing. This is largely because, in programming, they have a closed feedback loop that allows them to find errors. Writing is much more complicated because the feedback is much more diffuse and delayed over time. In fact, it is often not well-defined.
An interesting thought: historically, a major consideration for companies choosing what to use is how many engineers use it (because that will make hiring much easier/harder). Going forward, this becomes "how big of a corpus of this code is out there", because it impacts how proficient are likely to be at using it.


