◎ Updates/2026-10-17Intermediate
The Morning Flash Started Answering Differently, Your Prompt Is Not the First Thing to Check
When output length or format shifts although you never touched the model ID, compare the model you requested with the model that actually answered. A small three-prompt script logs modelVersion on every run, followed by the order I use to narrow down the cause.
◎ Updates/2026-09-15Intermediate
How I Decide Between 3.8 Flash and 3.7 Flash — A Fixed Set of 20 Questions
After swapping a model ID to a newer generation, the same input can start producing answers that feel split. Here is the 20-question evaluation set I keep, how I run both generations on equal footing, and the two numbers I use to decide.
◈ Gemini API/2026-09-05Beginner
Gemini 3.8 Flash Costs the Same Per Token and Can Still Raise Your Bill
Gemini 3.8 Flash carries the same per-token price as 3.7 Flash, but it is designed to work harder, so output tokens can grow and your bill with them. Here is what to measure before you switch, and how to price it across the January boundary.