Write Like It's 1866: LLMs Relearn Telegraphese
This article explores a technique for optimizing Large Language Models by using 'telegraphese'—a compressed, historical writing style—to reduce token usage and costs. Benchmarks show that models can effectively process and recover information from these compressed records without losing accuracy.
Why it matters
This optimization technique offers a practical way to significantly reduce API costs and increase context window efficiency for AI developers.
Everything below is reproducible — harness, frozen ledgers, one-click notebook: github.com/Travis42/telegraph-test .
Numbers from a 50-passage, ~1,300-question benchmark:
Cross-family matrix (readers = foreign models answering from GLM-5.3-Flash's records; writers = GLM-5.3-Flash answering from theirs) 1 Savings shown use the lowercase instruction, on each provider's own meter. Without that word, models write cablese in ALL CAPS and the styling costs 14–19 points: gemma 25.0%, qwen 29.8%, GLM 33.9%. *gpt-5-mini cannot disable reasoning, and compression makes it think — its writes bill about double plain. The one family where this technique does not pay. :
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in