A problem specification is an artifact that attempts to communicate this intent in a structured, precise and complete way. When there's a specification gap, the solver will attempt to infer using:Global priors : general knowledge and capabilities embedded in the model weights; its ‘world model’. Local context: task-specific information that contextualizes the task (documents, history, notes, etc.). Practically, you run into a wall: specs and ‘local context’ pipelines need to be engineered and maintained for every workflow. As new models come out, we need the ability to 'git merge' new updates to a model, while retaining weights encoding local context.