Yep, you nailed the problem: context drift kills instruction following.
That's why I’m thinking authority state should be external to the model. If we rely on the System Prompt to maintain constraints ("Remember you are read-only"), it fails as the context grows. By keeping the state in an external Ledger, we decouple enforcement from the context window. The model still can't violate the constraint, because the capability is mechanically gone.
That's why I’m thinking authority state should be external to the model. If we rely on the System Prompt to maintain constraints ("Remember you are read-only"), it fails as the context grows. By keeping the state in an external Ledger, we decouple enforcement from the context window. The model still can't violate the constraint, because the capability is mechanically gone.