Evaluation for game localization.
Measured, not prescribed.

What I do

Existing MT metrics cannot see what breaks in game text. In two of the three games I measured, the human-written golden scored worse than a plain machine draft on a generic metric. So I build the evaluation per house, in the client's own terms, and use a high-low model mix so the cost lands where it should.

Writing

Cross-posted from LinkedIn, archived here.

• Know your audience: six games, six shapes, one custom evaluation
  Six games measured for the shape of their text, and what that decides about the pipeline · September 2026

The eval

Not a screenshot. An interactive table you can sort and inspect, with the numbers baked in at publish time.