Week 1: LLM Review

Introduction to Large Language Models and AI in Data Analysis

Published

January 20, 2025

Week 1: LLM Review

Introduction to Large Language Models and their applications in data analysis

Learning Objectives

By the end of this session, students will:

Understand core concepts and architecture behind large language models (LLMs)
Learn how to incorporate AI into data analysis workflows
Critically assess capabilities and limitations of AI tools in academic contexts
Experience the “jagged frontier” of LLM capabilities through hands-on practice

Class Materials

📊 Slideshow

LLM Concepts Presentation

Key Topics Covered:

What are Large Language Models?
The Transformer architecture and tokenization
Cyborg vs Centaur approaches to AI collaboration
The “jagged frontier” of AI capabilities
Prompt engineering fundamentals
AI as bs generator and Brandolini’s Law

📚 Required Reading

Which AI Model to Choose?
Updated guide for 2025
Review the FT graph for class activity (see below)

Optional Background:

Ethan Mollick: “Co-Intelligence: Living and Working with AI” (Chapters 1-2)

🎯 Class Activity

The Financial Times Challenge

Take a look at this excellent Financial Times visualization showing the market reaction to Trump’s tariff announcements.

Your Mission:

Reproduce this chart as accurately as possible in the shortest time using AI assistance.

Learning Goals:

Experience AI-assisted data visualization
Practice prompt engineering for specific tasks
Understand the balance between human direction and AI execution, risks of relying too much on AI

Assignment

Assignment 1: Reproduce the FT Graph

Due: Before Week 2

Choose your approach:

Option A (Standard): Use AI to find data and recreate the visualization
Option B (Advanced): Build an interactive dashboard that updates dynamically

Full Assignment Details

Preparation

Before Class

No specific preparation required for Week 1
Come ready to discuss your current experience with AI tools
Bring examples of where you’ve encountered AI in your work/studies

Discussion Questions

Consider these questions as you engage with the materials:

Personal AI Experience: How have you already incorporated AI into your routine? Which model feels most natural to you?
Error Management: How do you currently deal with AI hallucinations or imperfect answers?
The Jagged Frontier: What tasks do you expect AI to excel at? Where do you think it will struggle?

Tools and Resources

Recommended AI Platforms for this course:

ChatGPT 4o/o1 - Excellent for coding and data analysis
Claude 3.5 Sonnet - Great for research and writing tasks
GitHub Copilot - For integrated coding assistance

Getting Started:

Most tasks can be accomplished with free tiers
Consider paid subscriptions for intensive work ($20/month typical)
See AI Model Comparison Guide for detailed recommendations

Week 1 Outcomes

By completing Week 1, you should:

✅ Understand what LLMs can and cannot do reliably
✅ Have experience with AI-assisted data visualization
✅ Recognize the importance of human oversight in AI workflows
✅ Be prepared to use AI as a collaborative tool throughout the course

Academic Integrity Note

This course teaches you to use AI as a powerful assistant while maintaining your responsibility as the analyst and author. Always verify AI outputs, cite your methods, and ensure you understand the analysis you’re presenting.

Next Week: Week 2 - Data Discovery and Documentation where we’ll use AI to understand and document complex datasets.

--- title: "Week 1: LLM Review" subtitle: "Introduction to Large Language Models and AI in Data Analysis" date: "2025-01-20" --- :::::: hero-section ::::: container ::: hero-title Week 1: LLM Review ::: ::: hero-subtitle Introduction to Large Language Models and their applications in data analysis ::: ::::: :::::: ![](../images/week1_pic.png) ## Learning Objectives By the end of this session, students will: - Understand core concepts and architecture behind large language models (LLMs) - Learn how to incorporate AI into data analysis workflows\ - Critically assess capabilities and limitations of AI tools in academic contexts - Experience the "jagged frontier" of LLM capabilities through hands-on practice ## Class Materials ::::: {.week-card .card} ::: card-header 📊 **Slideshow** ::: ::: card-body [LLM Concepts Presentation](https://gabors-data-analysis.com/courses/da-w-ai-2025/da-w-ai-01-llm-course.html){.slideshow-link} **Key Topics Covered:** - What are Large Language Models? - The Transformer architecture and tokenization - Cyborg vs Centaur approaches to AI collaboration - The "jagged frontier" of AI capabilities - Prompt engineering fundamentals - AI as bs generator and Brandolini's Law ::: ::::: ::::: {.week-card .card} ::: card-header 📚 **Required Reading** ::: ::: card-body - [Which AI Model to Choose?](assets/which-ai.html) - Updated guide for 2025 - Review the FT graph for class activity (see below) **Optional Background:** - Ethan Mollick: "Co-Intelligence: Living and Working with AI" (Chapters 1-2) ::: ::::: ::::: {.week-card .card} ::: card-header 🎯 **Class Activity** ::: ::: card-body **The Financial Times Challenge** Take a look at this excellent [Financial Times visualization](assets/ft-liberation-day-usd-yield-2025-04-11.jpg) showing the market reaction to Trump's tariff announcements. **Your Mission:** Reproduce this chart as accurately as possible in the shortest time using AI assistance. **Learning Goals:** - Experience AI-assisted data visualization - Practice prompt engineering for specific tasks - Understand the balance between human direction and AI execution, risks of relying too much on AI ::: ::::: ## Assignment ::: {.callout-note icon="📝"} ## Assignment 1: Reproduce the FT Graph **Due:** Before Week 2 Choose your approach: - **Option A (Standard):** Use AI to find data and recreate the visualization - **Option B (Advanced):** Build an interactive dashboard that updates dynamically [Full Assignment Details](../assignments/assignment_01.html){.assignment-badge} ::: ## Preparation ::: {.callout-tip icon="💡"} ## Before Class - No specific preparation required for Week 1 - Come ready to discuss your current experience with AI tools - Bring examples of where you've encountered AI in your work/studies ::: ## Discussion Questions Consider these questions as you engage with the materials: 1. **Personal AI Experience:** How have you already incorporated AI into your routine? Which model feels most natural to you? 2. **Error Management:** How do you currently deal with AI hallucinations or imperfect answers? 3. **The Jagged Frontier:** What tasks do you expect AI to excel at? Where do you think it will struggle? ## Tools and Resources **Recommended AI Platforms for this course:** - **ChatGPT 4o/o1** - Excellent for coding and data analysis - **Claude 3.5 Sonnet** - Great for research and writing tasks\ - **GitHub Copilot** - For integrated coding assistance **Getting Started:** - Most tasks can be accomplished with free tiers - Consider paid subscriptions for intensive work (\$20/month typical) - See [AI Model Comparison Guide](assets/which-ai.html) for detailed recommendations ## Week 1 Outcomes By completing Week 1, you should: - ✅ Understand what LLMs can and cannot do reliably - ✅ Have experience with AI-assisted data visualization\ - ✅ Recognize the importance of human oversight in AI workflows - ✅ Be prepared to use AI as a collaborative tool throughout the course ------------------------------------------------------------------------ ::: {.callout-important icon="⚠️"} ## Academic Integrity Note This course teaches you to use AI as a powerful assistant while maintaining your responsibility as the analyst and author. Always verify AI outputs, cite your methods, and ensure you understand the analysis you're presenting. ::: **Next Week:** [Week 2 - Data Discovery and Documentation](../week02/) where we'll use AI to understand and document complex datasets.