Don’t Let an AI Grade Its Own Homework — Use a Second Model to Review

Don't let an AI grade its own homework. Diagram showing two council models feeding their responses into a single arbiter model that decides what to adopt.

Ask an AI to check its own work and it mostly agrees with itself — the blind spots that shaped the answer also shape the review. Here’s the two-model fix, the AI Council loop I used to design ChainMate, and why you name one model as the arbiter instead of letting them vote.

Gemini Notebooks and NotebookLM Are Now the Same Thing — Here’s How to Use Both

Robot split between NotebookLM (caged with source documents) and Gemini (free with creative sparks), showing when to use each tool

Google just merged Gemini and NotebookLM into a single workspace, and most of the coverage has been something like: “Gemini got folders.” That framing misses the point entirely. The real change isn’t about organisation. It’s about routing. You now have two interfaces sitting on top of the same notebook — and choosing the right one … Read more