diff --git a/guides/prompt-adversarial.md b/guides/prompt-adversarial.md
index 623a52e..d94ca6d 100644
--- a/guides/prompt-adversarial.md
+++ b/guides/prompt-adversarial.md
@@ -17,7 +17,7 @@ Topics:
 ---
 
 ## Prompt Injection
-Prompt injection aims to hijack the model output by using clever prompts that change its behavior. These attacks could be harmful -- Simon Williams define it ["as a form of security exploit"](https://simonwillison.net/2022/Sep/12/prompt-injection/).    
+Prompt injection aims to hijack the model output by using clever prompts that change its behavior. These attacks could be harmful -- Simon Willison defined it ["as a form of security exploit"](https://simonwillison.net/2022/Sep/12/prompt-injection/).    
 
 Let's cover a basic example to demonstrate how prompt injection can be achieved. We will use a popular example shared by [Riley on Twitter](https://twitter.com/goodside/status/1569128808308957185?s=20). 
 
@@ -186,4 +186,4 @@ Models like ChatGPT and Claude have been aligned to avoid outputting content tha
 ---
 [Previous Section (Advanced Prompting)](./prompts-advanced-usage.md)
 
-[Next Section (Miscellaneous Topics)](./prompt-miscellaneous.md)
\ No newline at end of file
+[Next Section (Miscellaneous Topics)](./prompt-miscellaneous.md)