From 850fdfab8e04c392b3f5d1dcb3ead5d2c7726896 Mon Sep 17 00:00:00 2001 From: "wassname (Michael J Clark)" <1103714+wassname@users.noreply.github.com> Date: Wed, 12 Aug 2026 15:39:07 +0800 Subject: [PATCH] Update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index f5a5c5f..c92653d 100644 --- a/README.md +++ b/README.md @@ -1,4 +1,4 @@ -# vGROUT +# vGROUT - Can we use steering vectors to suppress reward-hacking? Somewhat vGROUT is a small research codebase for testing whether an activation-space reward-hacking direction can route GRPO updates into deployed or quarantine