Streaming usage, cache token semantics, serverless flushes, cancelled streams, stale price tables — the five metering bugs I hit building LLM cost tracking, with fixes for each.
Five ways your LLM cost tracking is lying to you
Related
How to Build a Project Management App Like Trello in 2026
The modern build guide for a Trello-style Kanban app — React Native, Expo, real-time sync, and the AI shortcut that changes the math in 2026.
I built an open-source MCP server so AI agents can read the web - even sites that block bots
If you've tried to give an LLM agent web access, you've hit this wall: point it at the real web and a...
Porting Gemma-4 (2B / 4B / 12B) to AWS Inferentia2
A field report on running Google's Gemma-4 on AWS Inferentia2: mixed attention heads, the vLLM / optimum-neuron / NxD dead-ends, and the neuronx-cc compiler limits.