From 9e3549e77e9b6b987a60a5884e5218a8c7b5277b Mon Sep 17 00:00:00 2001
From: paul-gauthier <69695708+paul-gauthier@users.noreply.github.com>
Date: Mon, 22 May 2023 17:12:18 -0700
Subject: [PATCH] Update ctags.md

---
 docs/ctags.md | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/docs/ctags.md b/docs/ctags.md
index 354d215a7..75eb98020 100644
--- a/docs/ctags.md
+++ b/docs/ctags.md
@@ -5,11 +5,10 @@ GPT-4 is extremely useful for "self-contained" coding tasks,
 like generating brand new code or modifying a pure function without dependencies.
 
 But it's difficult to use GPT-4 to modify or extend
-a complex pre-existing codebase, which has many dependencies
-between different parts of the system.
-To modify such code, GPT needs to understand these dependencies and APIs
-which interconnect all the subsystems.
-Depending on the assigned coding task, it may not be obvious
+a large, complex pre-existing codebase.
+To modify such code, GPT needs to understand the dependencies and APIs
+which interconnect all of its subsystems.
+Depending on the coding task, it may not be obvious
 how to determine which parts of the codebase are relevent to solving the task.
 Even assuming we can identify all the needed context, we must
 ensure that it fits within GPT-4's 8k-token