Research
Notes from the work.
-
Two loops
The part that learns is slow and expensive. The part that serves has to be fast and predictable. The interesting engineering is the boundary between them.
-
Cost per successful task, not cost per token
Cheap failures are the most expensive thing you can buy.
-
You can’t prove savings without a counterfactual
A falling bill doesn’t show that the thing you bought worked. Prices fell too, and the work changed.
Review build — these posts are drafts and haven’t been published.
Let’s compare notes.
Review build — contact address not yet connected.