Refine the README text to emphasize guiding the model using context

Author: robertpiosik

README.md

@@ -2,7 +2,7 @@
 
 <a href="https://marketplace.visualstudio.com/items?itemName=robertpiosik.gemini-coder" target="_blank"><img src="https://img.shields.io/badge/Install-VS_Code_Marketplace-blue" alt="Get from Visual Studio Code Marketplace" /></a> <a href="https://open-vsx.org/extension/robertpiosik/gemini-coder" target="_blank"><img src="https://img.shields.io/badge/Install-Open_VSX_Registry-a60ee5" alt="Get from Open VSX Registry" /></a> <a href="https://github.com/robertpiosik/CodeWebChat/blob/dev/LICENSE" target="_blank"><img src="https://img.shields.io/badge/License-GPL--3.0-green.svg" alt="GPL-3.0 license" /></a>
 
-Agent-free AI pair programming for production-grade code. Control the context to guide the model to the responses you expect.
+Agent-free AI pair programming for production-grade code. Guide the model with context and get edits you expect.
 
 Works with VS Code, Cursor, Windsurf, and other forks.
 
@@ -26,7 +26,7 @@ Code Web Chat only starts new conversations. This idea is borrowed from [Firefox
 > [!NOTE]
 > The _Apply response_ button placed under responses is not a means of automatic output extraction, it's an alias for the original _copy to clipboard_ button.
 
-🧑‍💻 **Control the context, guide the model**
+🧑‍💻 **Guide the model with context**
 
 Large language models (LLMs) are trained on vast datasets targeting many use cases. For code generation, a model's training involves analyzing millions of simulated problem-solving flows, such as arriving at the accepted answer from a given StackOverflow question. For the purpose of agentic coding, models are trained on an additional layer of data that simulates gathering context and planning its next steps.