From 806ff575676e447c7ba349b6fd185e6e8e02ee5d Mon Sep 17 00:00:00 2001
From: N0zoM1z0 <161784452+N0zoM1z0@users.noreply.github.com>
Date: Tue, 13 Oct 2026 15:57:39 +0800
Subject: [PATCH] docs(website): use straight quotes in model essay
Normalize the three quoted phrases to straight English quotation marks. Website checks and formatting pass; the local preview serves the revised punctuation.
---
website/public/blog/reverse-engineering-models/index.html | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/website/public/blog/reverse-engineering-models/index.html b/website/public/blog/reverse-engineering-models/index.html
index 0ec0f9a6f5..2b3c4c1cec 100644
--- a/website/public/blog/reverse-engineering-models/index.html
+++ b/website/public/blog/reverse-engineering-models/index.html
@@ -426,8 +426,8 @@
“The model did not know that compiler quirk” and “the model
- could not use it” are different problems."The model did not know that compiler quirk" and "the model
+ could not use it" are different problems.
Retrieval may solve the first, but turning that fact into a useful
candidate still takes work. And if the candidate fails, the model
@@ -688,7 +688,7 @@
already had the target's 1,825-byte length, yet 467 byte positions
differed. Even a byte-difference count can change abruptly when a
branch encoding changes. Such diagnostics can guide the next
- experiment, but I would validate any reward for “getting closer”
+ experiment, but I would validate any reward for "getting closer"
against the full acceptance check.