Update config.py

config.py

@@ -229,7 +229,7 @@ For your own context and knowledge, use the UI and server code for this tab to i
 ###########################################################################################
 # Model Configuration
 ###########################################################################################
-ai_model = "gpt-4o"         # Choose from: gpt-4o, gpt-4o-mini, etc.
+ai_model = "gpt-4.1"         # Choose from: gpt-4o, gpt-4o-mini, etc.
 temperature = 0.05           # 0 to 1: Higher values = more creative responses
 max_tokens = 500            # 1 to 2048: Max tokens in the response
 frequency_penalty = 0.5     # 0 to 1: Higher values = more penalty for repeating phrases
@@ -242,14 +242,13 @@ instructions = '''This is a basic chatbot template. Place user instructions here
 '''
 
 opening_message = '''👋 **Welcome to the Confidence Intervals Chatbot!**
-Hello! I’m Pliny, your AI tutor for exploring confidence intervals in this Shiny app. Today, we’re focusing on **Tab 3: Bootstrapping**. Feel free to ask questions about:
-- How the bootstrap process works by resampling with replacement from your initial sample.
-- Why the number of bootstrap replicates affects the CI’s precision or consistency.
-- Comparisons between the bootstrap percentile CI and the z-based CI.
 
-Have fun experimenting! Generate a new initial sample, run the bootstrap multiple times, and observe how your confidence intervals behave. Let’s see what insights you can uncover!
+I'm here to facillitate as you attempt to use this simulation to answer the following:
 
-Lastly, remember that **generative AI can make errors**. These chats do not replace verified classroom resources but can inspire new ways of thinking about statistics. Let’s get started!
+   - **Question 1:** "What is the effect on the 95% CI if you bootstrap 10,000X instead of 100X?"
+   - **Question 2:** "When you bootstrap 10,000X, does it seem to give a very similar 95% CI compared to the theoretical CI calculated from the sample size and standard deviation?"
+
+See what patterns you find when you adjust the simulation's parameters and repeatedly generate sample means.
 '''
 
 warning_message = "**Generative AI can make errors and does not replace verified and reputable online and classroom resources.**"