From 0ee6a20391ecbd11433100adf74e8b17d9fa9695 Mon Sep 17 00:00:00 2001 From: Shrish Dwivedi Date: Wed, 14 Oct 2026 19:44:26 +0530 Subject: [PATCH] docs(readme): proof lines say what the page shows The 162-run tokens are uncached input tokens, that harness was an agent loop rather than Claude Code, and the popular-repos line now gives PocketBase's measured numbers instead of an unshown 4x. --- README.md | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index 10fdeae6..9a299004 100644 --- a/README.md +++ b/README.md @@ -70,7 +70,7 @@ npm install -g @trailhq/trail-code && trail init **Same model, more tasks solved.** On SWE-bench Verified (real GitHub issues, graded by the maintainers' own tests), Claude Sonnet 5 solved **33 of 50** issues with the graft map and **27 of 50** without it, using 23% fewer tokens. [Details](#swe-bench-verified) -**Cheaper and faster.** Across 162 runs of the same agent on the same tasks: **32% lower cost**, **42% fewer tokens**, **60% less time**, and the same share of correct answers. On popular open-source repos, up to **4× cheaper** and **3× faster**. [Details](#benchmark) +**Cheaper and faster.** Across 162 runs of the same agent on the same tasks: **32% lower cost**, **42% fewer uncached input tokens**, **60% less time**, and the same share of correct answers. On PocketBase, 15 real tasks ran **21% cheaper** and **14% faster**. [Details](#benchmark) --- @@ -152,11 +152,11 @@ The graft map builds that understanding once, and keeps it current: - **Plain files you can read.** Linked markdown nodes your agent opens and greps like any other file. No embeddings, no index to keep warm. - **Summaries if you want them.** `trail build --deep` adds plain-English summaries of each part of the system, written by the model provider you choose, under your own key. -| | Cold Claude Code | Claude Code with the graft map | +| | Cold agent | Agent with the graft map | |---|---|---| | SWE-bench Verified, 50 real issues | 27 solved | **33 solved (+12 pts)** | -| Our benchmark, 162 runs | baseline | **32% lower cost, 42% fewer tokens, 60% less time** | -| Popular open-source repos | baseline | **up to 4× cheaper, 3× faster** | +| Our benchmark, 162 runs | baseline | **32% lower cost, 42% fewer uncached input tokens, 60% less time** | +| PocketBase, 15 real tasks | baseline | **21% cheaper, 14% faster** | How it is measured: [Benchmark](#benchmark), [SWE-bench Verified](#swe-bench-verified) and [Tested on popular repos](#tested-on-popular-repos). How it is built: [the reference](#how-the-graph-gets-built).