Schedule
MATH 395.02 Creating with AI in the Loop
This page is the authoritative course schedule and the main entry point for weekly materials.
- Slide decks are linked here (rendered HTML).
- Assignment invite links live on the Assignments page.
This course is under active development, and the schedule will be filled in as we go.
Week 1: January 12-18
| Meeting | Topic | Slides | Due |
|---|---|---|---|
| Tuesday | Course overview + workflow setup | Course Overview and Workflow Setup | Read syllabus + Create GitHub account (before class) |
| Thursday | Large language models | Introduction to LLMs | A0 — Git and GitHub Fundamentals (before class) |
Learn more
OpenAI tokenizer - Demonstrates how text is tokenized by a language model.
What are transformer models and how do they work? - YouTube video from Serrano.Academy.
Deep Dive into LLMs like ChatGPT - YouTube video by Andrej Karpathy.
Attention is all you need - paper by Vaswani et al. (2017).
Week 2: January 19-25
| Meeting | Topic | Slides | Due |
|---|---|---|---|
| Tuesday | Python, Code Assist, API | Python, APIs, and Code Assist | A1 — Setup Verification (before class) |
| Thursday | Prompting, AI and critical thinking | Prompt Patterns and Best Practices | Read 3 discussion articles (before class) |
Resources for discussion
The age of de-skilling - article by Kwaime Anthony Appiah published in web edition of the Atlantic
The people outsourcing their thinking to AI - article by Lila Shroff published in web edition of the Atlantic
The cognitive paradox of AI in education: Between enhancement and erosion - opinion article by Jose et al. from Frontiers in Psychology
Learn more
How AI could save (not destroy) education - Ted Talk by Sal Kahn (founder and CEO of Khan Academy)
Generative AI without guardrails can harm learning: Evidence from high school mathematics - by Bastani and Sungu (2025) from PNAS
The widening gap: The benefits and harms of generative AI for novice programmers - a research article by Prather et al. from ICER ’24: Proceedings of the 2024 ACM Conference on International Computing Education Research.
The impact of generative AI on critical thinking: Self-reported reductions in cognitive effort and confidence effects from a survey of knowledge workers - a research article by Lee et al. from CHI ’25: Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems
Week 3: January 26-February 1
| Meeting | Topic | Slides | Due |
|---|---|---|---|
| Tuesday | Tool calling | Tool Calling for LLMs | A2 — API and Prompt Patterns (before class) |
| Thursday | The costs of training (discussion) | - | Read 2 articles + watch video (before class) |
Resources for discussion
Explained: Generative AI’s environmental impact - article from MIT News
How Much Water Do AI Data Centers Really Use? - article from Undark
The growing environmental impact of AI data centers’ energy demands - PBS NewsHour video
Learn more
We did the math on AI’s energy footprint. Here’s the story you haven’t heard. - MIT Technology Review
The carbon and water footprints of data centers and what this could mean for artificial intelligence - research article from ScienceDirect
How much water does AI consume? The public deserves to know - policy article from OECD.AI
Week 4: February 2-February 8
| Meeting | Topic | Slides | Due |
|---|---|---|---|
| Tuesday | Multi-turn chat and document retrieval | Multi-turn Chat and Document Retrieval | A3 — Tools (before class) |
| Thursday | Homogeneity, bias, and creativity (discussion) | - | Read 2 articles + listen to interview (before class) |
Resources for discussion
A.I. Is Homogenizing Our Thoughts - article by Kyle Chayka in The New Yorker
Generative AI bias poses risk to democratic values, research suggests - article from Phys.org on University of East Anglia research
Are we thinking about AI the wrong way? - audio interview with Ethan Mollick on WBUR’s On Point (transcript available). You may skip the segment from 24:30 - 34:30 if you want, it’s not closely related to the topic of the discussion.
Learn more
Generative AI enhances individual creativity but reduces the collective diversity of novel content - research article by Doshi & Hauser in Science Advances
Homogenizing effect of large language models (LLMs) on creative diversity - research article in Computers in Human Behavior analyzing 2,200 college essays
Week 5: February 9-February 15
| Meeting | Topic | Slides | Due |
|---|---|---|---|
| Tuesday | Work day | - | A4 — RAG (KW) + Multi-turn Chat (before class) |
| Thursday | Work day | - | - |
Note: Schedule your Code Review 1 appointment this week.
Week 6: February 16-22 (Winter Recess)
| Meeting | Topic | Slides | Due |
|---|---|---|---|
| Tuesday | No class (Winter Recess) | - | A5 — Build Your Own Expert (Wednesday 11:59pm) |
| Thursday | No class (Code Review appointments) | - | - |
Note: Code Review 1 appointments available Wednesday, Thursday, and Friday of Week 6.
Week 7: February 23 - March 1
| Meeting | Topic | Slides | Due |
|---|---|---|---|
| Tuesday | Semantic search and embeddings | Semantic Search and Embeddings | - |
| Thursday | Custom states and multi-node workflows | Custom States and Multi-Node Workflows | - |
Week 8: March 2-8
| Meeting | Topic | Slides | Due |
|---|---|---|---|
| Tuesday | Streamlit interfaces | Streamlit Interfaces | A6 — RAG - Hybrid (before class) |
| Thursday | Gemini CLI | - | - |
Week 9: March 9-15
| Meeting | Topic | Slides | Due |
|---|---|---|---|
| Tuesday | Group work | - | A7 — Workflows, CLI (before class) |
| Thursday | The future of jobs and work (discussion) | - | A8 — Streamlit (before class); Read 3 articles + listen to podcast (before class) |
Resources for discussion
Why A.I. Didn’t Transform Our Lives in 2025 - article by Cal Newport in The New Yorker
AI Changed Work Forever in 2025 - article by Erik Brynjolfsson in TIME
AI vs Gen Z: How AI has changed the career pathway for junior developers - article by Phoebe Sajor on the Stack Overflow Blog
Is AI Slopifying the Job Market? - podcast episode from Planet Money / The Indicator (NPR)
Learn more
The Evidence That AI Is Destroying Jobs for Young People Just Got Stronger - article by Derek Thompson (The Atlantic staff writer)
Generative AI at Work - research article by Brynjolfsson, Li, & Raymond in The Quarterly Journal of Economics
Top engineers at Anthropic, OpenAI say AI now writes 100% of their code - article by Beatrice Nolan in Fortune
I’ll Probably Lose My Job to AI. Here’s Why That’s OK - TED Talk by Megan McArdle
The Macroeconomic Impact of Artificial Intelligence - research from Anthropic
Week 10: March 16-22
| Meeting | Topic | Slides | Due |
|---|---|---|---|
| Tuesday | Work day | - | Project proposal (before class) |
| Thursday | Ethical concerns of AI in different fields (GLD1) | - | Read 3 articles + listen to podcast (before class) |
Resources for discussion
AI is Making Medical Decisions - But For Whom? - article by Olivia Farrar in Harvard Magazine
Is AI Making Call Center Agents Better Or Replacing Them? - article by Kolawole Samuel Adebayo in Forbes
Ethical Review in the Age of Artificial Intelligence - journal by Jung Hwan Heo in AI Ethics Journal
Navigating the Future of AI in Healthcare - podcast episode from USC Gould School of Law
Learn more
Call Centers Replaced Many Doctors’ Receptionists. Now, AI Is Coming for Call Centers. - article by Darius Tahir in KFF Health News
Week 11: March 23-29
| Meeting | Topic | Slides | Due |
|---|---|---|---|
| Tuesday | Work day | - | A9 — TL;Draw (before class) |
| Thursday | No Class (Code Review 2 appointments) | - | - |
Note: Schedule your Code Review 2 appointment this week. CR2 appointments available March 23–26.
Spring Recess: March 30 - April 5
No class.
Week 12: April 6-12
| Meeting | Topic | Slides | Due |
|---|---|---|---|
| Tuesday | Group work | - | - |
| Thursday | AI, Grief, and Human Relationships (GLD2) | - | Read/watch assigned resources (before class) |
Resources for discussion
The AI Companies Trying to Make Grief Obsolete — The Atlantic. Explores startups creating AI chatbots of deceased loved ones and asks whether this helps people process grief or traps them in it.
Griefbits and the New Afterlife: How AI is Changing the Ways We Mourn — Thomas Doyle, TEDx. In this talk, Doyle explores how AI “griefbots” allow people to interact with digital versions of deceased loved ones, drawing on his experience as both a minister and AI researcher to examine how technology is reshaping mourning and remembrance.
Young People Are Using AI to Skip the Hardest Part of Growing Up — New York Times. Argues that relying on AI for emotional support or advice may prevent people from developing real-world coping and relationship skills.
Inside Three Long-Term Relationships with AI Chatbots — The New York Times. Profiles individuals who have formed deep emotional and romantic relationships with AI companions, highlighting both the appeal and complexity of these connections.
Learn more
AI Replica of Val Kilmer to Appear in Film After Death
Week 13: April 13-19
| Meeting | Topic | Slides | Due |
|---|---|---|---|
| Tuesday | Group work | - | - |
| Thursday | AI Safety, Governance, and Existential Risk (GLD3) | - | Watch 2 video clips + read White House AI Action Plan sections (before class) |
Resources for discussion
AI Expert: Here Is What The World Looks Like In 2 Years! - Tristan Harris (Clip 1, 22m) — Diary of a CEO Clips
AI Expert: Here Is What The World Looks Like In 2 Years! - Tristan Harris (Clip 2, 21m) — Diary of a CEO Clips
America’s AI Action Plan — The White House. Skim the table of contents to get a sense of what the document covers. Read these subsections: Remove Red Tape and Onerous Regulation (p. 3), Encourage Open-Source and Open-Weight AI (p. 4), Enable AI Adoption (p. 5), Invest in AI Interpretability, Control, and Robustness Breakthroughs (p. 9), Build an AI Evaluations Ecosystem (p. 10), Ensure that the U.S. Government is at the Forefront of Evaluating National Security Risks in Frontier Models (p. 22).
Learn more
Let’s think about slowing down AI — AI Alignment Forum
AI Expert: We Have 2 Years Before Everything Changes! We Need To Start Protesting! - Tristan Harris — full interview on The Diary of a CEO with Steven Bartlett
A Narrow Path — a plan to secure our future from AI extinction risk
AI 2027 — AI forecasting scenario from the AI Futures Project
AGI Ruin: A List of Lethalities — AI Alignment Forum
Week 14: April 20-26
| Meeting | Topic | Slides | Due |
|---|---|---|---|
| Tuesday | Group work | - | Working prototype (before class) |
| Thursday | How AI Can Help or Worsen Income Inequality Through Its Impact on Education and Work (GLD4) | - | Read/watch assigned resources (before class) |
Resources for discussion
AI Could Actually Help Rebuild The Middle Class — article by David Autor in Noema Magazine. AI can rebuild the middle class by helping average workers perform higher-skill tasks, increasing opportunities and wages if used effectively.
Can AI Foster Equity in Education? — article from the University of Maryland College of Education. AI can reduce educational inequality by supporting under-resourced students and teachers, but it may worsen gaps if access is uneven.
The Simple Macroeconomics of AI - just the intro — paper by Daron Acemoglu (MIT). AI’s economic impact depends on whether it mainly replaces human tasks or enhances them, shaping outcomes like growth and wages.
Will AI Make Inequality Better Or Worse — video by Bernard Marr. AI will transform jobs and daily life, and its effects depend on how people choose to use and adapt to it.
Week 15: April 27 - May 1
| Meeting | Topic | Slides | Due |
|---|---|---|---|
| Tuesday | Group work | - | - |
| Thursday | Final presentations | - | Working repo (Wed April 29, 11:59pm) |
Week 16: May 4-6
| Day | Event | Due |
|---|---|---|
| Monday | Group code review (final exam) 12:00–2:30pm | - |
| Wednesday | - | Portfolio piece / public site (11:59pm) |
12:00 group (2-person group) will meet in VWF 215. Other meetings are in our normal classroom.