Essays & working notes
Ideas tested against real products, written down once they've survived contact with one.
For probabilistic systems, requirements written in prose are opinions. Requirements written as evals are testable. Write the eval first.
Trace failed enterprise AI projects back to their first crack and it's almost never the model. The difficulty moved — spend your early weeks where it went.
The demo tells you what a system can do. The eval tells you what it will do. Only one of those is a shipping decision.
Autonomy is not an ambition decision. It is a cost decision, and the costs compound per step.
A model that everyone overrides has failed, even though every launch metric says otherwise. Adoption is the metric the others report to.