From 3c58f2bff0c7e01823e829466a64701ed37dcb8e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?S=C3=B8ren=20Fuglede=20J=C3=B8rgensen?= <github@fuglede.dk>
Date: Sat, 22 Jun 2024 22:49:21 +0200
Subject: [PATCH] Better phrasing

---
 index.html | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/index.html b/index.html
index b614ae3..547ad27 100644
--- a/index.html
+++ b/index.html
@@ -20,11 +20,10 @@ <h3>How?</h3>
         used to "shape" text.
         
         <br /><br />
-        In particular, this "arbitrary" code could in principle be an entire LLM inference engine (<a href="https://en.wikipedia.org/wiki/Llama_(language_model)">Llama</a> in our case,
-        hence the name).
+        In particular, this "arbitrary" code could in principle be an entire LLM inference engine, relying on treating text containing magic symbols for fake "ligatures" to initialize the LLM and use it to generate text.
         <br /><br />
-        It could also in principle be an entire LLM inference engine but not just in principle, relying on treating text containing magic
-        symbols for fake "ligatures" to initialize the LLM and use it to generate text.
+        It could also in principle be an entire LLM inference engine (<a href="https://en.wikipedia.org/wiki/Llama_(language_model)">Llama</a> in our case,
+        hence the name) but not instead of in principle it's right here.
         <br /><br />
         At the end of the day, what this means is that you can just use the font to run the LLM and e.g. get text generation in <i>any</i> Harfbuzz-based text editor,
         even if they don't come with "Copilot" like features themselves. So is this silly hack in fact a billion dollar idea?