Topaz

TL;DR: The cost of serving model tokens changes constantly, but the price you pay does not.

I’ve been building Mandex, a CLI tool, and somewhere along the way I realized: shipping a dev tool in 2026 is a completely different game than it was even two years ago.

i’ve been using Claude Code heavily for the last few months — for chonkie, for side projects, for basically everything.

How we built memchunk - a blazing fast text chunking library using SIMD and memchr for RAG pipelines

I built a pastebin last week.

A friend asked me recently: “Why do you work?

A good blog doesn’t need to be trendy.

as i use llms more in my daily work, i’ve had to think about something i never considered before: where do prompts actually live?

I did a cool thought experiment recently: I tried to predict the future of one specific aspect of AI — prompting.