I run a verified inference endpoint. What we sell is checking: we verify results before serving them,...
I built a page that only publishes numbers surviving our own checks. It caught me inside the hour.
Related
Nearly half of MCP servers expose tools an agent could plausibly confuse
A reader made a point on my last post that I couldn't answer at the time, so I went and measured...
Your Cognito Login Code Fails Because the App Client Never Allowed That Auth Flow
Your login screen works locally. You point it at the staging user pool and every sign-in comes back...
I Built an Agent Eval Harness. Real Agents Broke the Clean Version of the Story
Two weeks ago, I published "Why Agent Evaluation Is Harder Than Model Evaluation." The core argument:...