From 16cbff61a847729fe41017f4853462a892876b38 Mon Sep 17 00:00:00 2001 From: tobi Date: Thu, 2 Jul 2026 16:33:02 +0000 Subject: [PATCH] Update README.md --- README.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index fdc2878..0e9749d 100644 --- a/README.md +++ b/README.md @@ -24,7 +24,8 @@ When an LLM agent needs to follow these conventions, it usually has two bad opti 1. **Stuff every existing file into context** — 15 Ansible roles = 5,000 tokens. You'll hit the context window by the third example. 2. **Guess from one or two examples** — the LLM infers a pattern and often gets it wrong. -Dervish replaces both with a **one-call MCP tool**: pass your sequences, get back a ~60-token grammar. A rule you can trust, at a fraction of the cost. +Dervish replaces both with a **one-call MCP tool**: pass your sequences, get back a ~60-token grammar. +By leveraging Minimum Description Length (MDL) scoring, Dervish treats the grammar discovery problem as an optimal compression task—meaning the resulting rule is mathematically tuned to consume as few tokens as possible without losing the pattern. **Without Dervish:** token cost scales linearly with examples. **With Dervish:** one compact grammar describes them all — a ~60–200 token rule instead of thousands of tokens of raw examples. Try it out and you too will say: