~3 min read
The real cost of a token
What API pricing is actually paying for — hardware, electricity, and a falling curve — and why this changes which apps make sense.
Blog
-
- ~3 min read
Evals vs. vibes
Why every serious AI project ends up writing its own evaluation set, and what a good one looks like.
- ~2 min read
Why benchmarks lie
Contamination, saturation, and the incentive to teach to the test — a field guide to reading model launch charts skeptically.
- ~2 min read
Attention, in plain English
The one trick that makes transformers work, explained without matrices — and what changes once you understand it.
- ~2 min read
What is a token, really?
Models don't see words. They see tokens — chunks of bytes carved up by a learned vocabulary. Here is what that means in practice.
- ~6 min read
Cost defragmentation: where AI money is actually wasted
AI bills are not high because tokens are expensive. They are high because the memory is sitting half-empty and the context is not being attended to.