FEATURED NOTE Gemini 4 Argon: the numbers behind the launch
A closer look at the output limit, token pricing and coding benchmarks — with the comparisons kept in context.
The LatentModels, benchmarks and the details that matter.
Clear explanations, with a little illustration.
Technical enough to be useful.
Simple enough to keep.
FEATURED NOTE A closer look at the output limit, token pricing and coding benchmarks — with the comparisons kept in context.
A simple way to account for input, output, retries and tools when comparing models.
Two token limits, two different questions. Here is how to read a model specification without mixing them up.
A score becomes useful when you know the task, the evaluation setup and what counts as success.
Try another topic or search.

A notebook for making sense of AI, one clear idea at a time.