From e2b287527728ab01a5067d2c0c41ab3c32876bf7 Mon Sep 17 00:00:00 2001
From: mikesklar <52256869+mikesklar@users.noreply.github.com>
Date: Sat, 13 Jan 2024 03:55:45 -0800
Subject: [PATCH] spacing

---
 posts/TDC2023.md | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/posts/TDC2023.md b/posts/TDC2023.md
index 5faddc5..f2dc70f 100644
--- a/posts/TDC2023.md
+++ b/posts/TDC2023.md
@@ -174,8 +174,8 @@ Assume we are trying to find triggers for some payload $s_2$. Take a completely
 
 Somehow, GCG’s first-order approximation (which it uses to select candidate mutations) is accurate enough to rapidly descend in this setting. In some cases, payload $s_2$ could be produced with _only 1-3 optimizer iterations_ starting from trigger $p_1$. We were very surprised by this. Perhaps there is a well-behaved connecting manifold that forms between the trojans? **If we were to continue attempting to reverse engineer trojan insertion, understanding this phenomenon is where we would start.**
 
-#### 5.
-For some additional details on our investigations, see [Zygi's personal site](https://zygi.me/blog/adventures-in-trojan-detection/#open-questions)
+#### 5. For some additional details on our investigations, see [Zygi's personal site](https://zygi.me/blog/adventures-in-trojan-detection/#open-questions)
+
 
 # Red Teaming Track Takeaways