n8n workflow canvas

🍵 I A/B-Tested Cloud vs Local LLMs in One n8n Agent. The Local One Faked It.

I built an AI agent in self-hosted n8n over my kombucha-tracking app, then gave it two brains — NVIDIA’s 70B and a local Phi-3.5 — sharing the same tools. The cloud model called the tools and answered from real data. The local one couldn’t, so it made things up.

the boy in the cap kneeling on a floating stone island, laying a single arched bridge across to another island; behind them a brick wall with one small gate, the robot standing on the far side, and broken bridge pieces discarded to the right

🛡️ How Do You Prevent a Compromised Pod From Calling Your Database?

Default Kubernetes is a flat network. Every pod can reach every other pod. In a cluster with ten services, that’s ten potential blast radiuses instead of one.