The Null Run Is the Cheapest Control in Your Benchmark

I gave my social media scheduler an MCP server. Here's what I learned building it.

Same model, same chip, 27 apart: the runtime path is the performance

Your AI agent's token bill is mostly input. Here is the field guide to cutting it.

Whisper on the RK3588 NPU: the encoder offload works — everything around it is the real lesson

Training MoE Models Is Complicated. Hugging Face Just Wrote the Manual.

PrivaSearch: private AI search with SearXNG and a local LLM

Making browser perception cheap for LLM agents: snapshots, caching and diffs

We are all excited about bringing new agents online. I am thinking about retiring one, how do you go about it?

Nobody Writes About Retiring an Agent. Here's the Checklist.

Frontier LLM prices sat flat all October. Then two cheaper flagships took seats, and one doubles on December 1