Notes on AI reliability, systems, and the things I build along the way.
TypeSafe AI's new model does not generate text. It answers typed questions with probabilities in a few hundred milliseconds. Here is what Jev is, how it differs from an LLM, and which of the claims deserve a pinch of salt.
Read post →
Three years, one missed deadline, and six months in a single codebase: how I got selected for Google Summer of Code 2026 with Meshery, and what showing up consistently in one project produced along the way.
Read More →