From 25e026e57ef27b33a9c308ed0c371abc2cb60680 Mon Sep 17 00:00:00 2001 From: Andy Zhou Date: Fri, 2 Feb 2024 14:39:24 -0600 Subject: [PATCH] website --- index.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/index.md b/index.md index 2ac96d1..a691521 100644 --- a/index.md +++ b/index.md @@ -7,11 +7,11 @@
- GPT-4 + GPT-4

Fig.1 GPT-4 safety filters can be bypassed by jailbreaks!

- RPO + RPO

Fig.2 RPO enforces harmless responses even after jailbreaks