From 8b28539b4e8a2fc96491f98e47eba8c7e1590fb7 Mon Sep 17 00:00:00 2001 From: Paul Gauthier Date: Sun, 21 May 2023 14:14:30 -0700 Subject: [PATCH] copy --- docs/ctags.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/ctags.md b/docs/ctags.md index 6f3ad2e98..72a35427d 100644 --- a/docs/ctags.md +++ b/docs/ctags.md @@ -30,8 +30,8 @@ in Foo with the prints, and it also needs to understand how the logging system works. A simple solution is to send the **entire codebase** to GPT along with -every change request. Now GPT has all the context! But even moderately -sized repos won't all fit in the 8K GPT-4 context window. An +each change request. Now GPT has all the context! But even moderately +sized repos won't fit in the 8k-token GPT-4 context window. An improvement is to be selective, and hand pick which files from the repo to send. For the example above, you could send the file that contains Foo and the file that contains the logging subsystem.