Mihai Chiorean

I built a sycophancy benchmark for my local AI agent and compared it to frontier models.

Sub-agents aren't specialists — they're disposable, isolated scratchpads for the noisy, expensive, tool-heavy work, handing back only the part that matters and keeping the main thread clean for decisions.

A Swift host process driving an NVIDIA DeepStream graph on a Jetson Orin Nano.

A 229B model and the full agentic loop — agent, memory, orchestration, inference — running on a $4,700 mini-PC instead of a cloud API.