Every published "tokens per second" number you've used to pick an inference provider is measured on a...
Your AI speed benchmark is measuring the one workload you don't run
Related
The Forked History: Byzantine Witness and the 3-of-4 Quorum — Tested
A sealed single authority can equivocate — job A sees one fork, job B another. Three fixtures separate inclusion, consistency, and witness agreement; a 2-of-3 threshold is not fork...
Read-Only by Design: Letting AI Explore Your Database Without the Risk of Writes
How to give AI assistants safe, read-only access to your SQL database — using database roles, read replicas, and query guardrails so nothing gets modified.
I built an MCP memory server for one user (me, for six weeks)
Building in public You explain your deploy setup to your assistant. It helps. Tomorrow you explain...