How I wrapped llama.cpp in a small, coroutine-first Kotlin API, and the three problems that took the most time: threads, cancellation and broken emoji.
Running an LLM fully offline on Android with Kotlin coroutines
Related
What MCP Bastion Found When I Changed One Tool Description
I changed one sentence in the description of an MCP tool called get_uptime. Scanned on its own, the...
Stopping the camera from flip-flopping: confidence scoring for AI active-speaker switching
Why instant thresholds make automatic camera switching twitchy, and how a rising confidence score, a hold rule and a wide-shot fallback make it feel like a calm human operator.
A Small Laptop Is a Full Build Kit: Bootstrapping with a Chromebook, Claude, and GitHub
A small laptop is a full build kit. Here's how far mine went. TL;DR: A reader suggested I publish...