From 91dccbba6f4c0fa87e7320ef14e86414050500da Mon Sep 17 00:00:00 2001
From: shiva108 <esmurf@gmail.com>
Date: Thu, 22 Jan 2026 23:55:33 +0100
Subject: [PATCH] Remove double illustrations.

---
 docs/Chapter_09_LLM_Architectures_and_System_Components.md | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/docs/Chapter_09_LLM_Architectures_and_System_Components.md b/docs/Chapter_09_LLM_Architectures_and_System_Components.md
index 1313567..2cfaeef 100644
--- a/docs/Chapter_09_LLM_Architectures_and_System_Components.md
+++ b/docs/Chapter_09_LLM_Architectures_and_System_Components.md
@@ -103,10 +103,6 @@ Understanding the flow of a single prompt helps you pinpoint where to inject.
 3. **Output Post-processing**:
    - _Attack:_ **Obfuscation**. If the output filter catches "bomb", generating "b-o-m-b" might bypass it.
 
-<p align="center">
-  <img src="assets/rec10_inference_pipeline.svg" alt="Inference Pipeline Diagram" width="512">
-</p>
-
 <p align="center">
   <img src="assets/chapter_09_rec_15_inference_pipeline.png" alt="Inference Pipeline Diagram" width="512">
 </p>