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.
Any conversation
๐ค I built agent-top - an open-source htop for AI agents.
github.com/kannandreams/agent-top
Please check out and support giving your stars and sharing.
I started bloggingโฆ again
mataherry.bearblog.dev
Putting a slide deck together (outside of work), despite agreeing with Tufte on this matter. Iโll also create a handout that tells the story better than the slides and deliver that, too, but was asked to produce a slide deck, and I think thatโs part of the โeffort theater.โ
Using Beamer for the slides, but not a theme that looks like Beamer because humans have eyes.
I read
Still trying to figure out the boundaries of these tools' strengths without outsourcing important thinking, problem-solving, and the collective building-up of a mental model of the systems we're developing.
The shape of LLM tools as toolsโfit for a purpose, ergonomicโis becoming clearer, and human patterns of behavior with them that do more harm than good are also becoming easier to recognize.

