Design that prevents the LLM from doing calculations

Read a Zenn article on using Jev, a decision-specialized model, to control Mario without letting an LLM do arithmetic.

The original post, translated

Design that prevents the LLM from doing calculations — reading the implementation where the judgment-specialized model Jev operates Mario https:// zenn.dev/ruri/articles/ typesafe-mario-facts-in-code …

The post above is a machine translation from ja; the untranslated text is in the fold-out.

Engagement when collected

Numbers are a snapshot taken from X when the case was added to the library (schema v1, collected 2026-09-19); they will not match today.