Everything below is reproducible — harness, frozen ledgers, one-click notebook: github.com/Travis42/telegraph-test.

GLM-5.3-Flash itself: 48.4% savings with the lowercase instruction, in-family recovery 1.09.2Readers answer 694 anchored questions per condition; writers’ records are read by GLM-5.3-Flash — every GLM call in every run in this post is glm-5.3-flash, the fast variant on the z.ai coding plan. No comparison in the matrix favors plaintext; every ratio sits at 0.99–1.10.

Downstream models, including four families never shown an example, answer questions from the compressed records as well as or better than from plaintext — recovery ratios 0.99–1.10, where 1.00 means “exactly as good as plaintext.” The register is not a construct we invented (LLMs were handed compressed records cold and read them at parity); the capability was already in the weights, inherited from a century and a half of people writing under metered bandwidth.