Assignments

Assessment

Homework 1: Sensitive data redaction at the last mile

You will build an AI system that prepares troubleshooting conversations for public release by redacting private information while preserving useful technical details. Much of the challenge is in figuring out what this particular client wants to keep or conceal, then getting your system to apply those decisions reliably.

You will receive its interface, development examples, and a fixed inference budget. You may implement any AI system that respects the interface and budget, and you will submit the system alongside a short report on its development.

Your score will partly depend on successful completion and discussion of the design and implementation as well as on your system's quality-cost trade-offs and generalization to different data distributions.

Homework 2: Recommendation and learning from user feedback

You will build a research-paper recommendation system that learns from user feedback. You will receive incomplete requirements and a (simulated) user endpoint that you can query to collect user-specific feedback for a limited number of times. You will build a procedure that decides what feedback to request and when, how to generalize from the feedback into an updated policy, and how to act on new cases after the feedback ends.

Your score will partly depend on successful completion and discussion of the design and implementation as well as your systems' performance and its improvement as more feedback becomes available, plus how the system will generalize to different feedback distributions and/or underlying LLMs.

Project

The course will provide several project directions to choose from. Students with a strong alternative may instead propose an open-ended project to the course staff.

Each team will identify a realistic gap in what current AI systems can do, define how to evaluate progress, and investigate an approach to making that progress. Your grade will reflect the quality of the problem formulation, experiments, and evidence supporting your conclusions, rather than whether your approach necessarily achieves its original goal or advances the state of the art.

Quizzes

The goal of the quizzes is to test mastery of the fundamental technical ideas and essential system design intuitions from the lecture and the homeworks. This is meant to complement the otherwise very flexible AI usage policies for homework and project development.

Five short quizzes will be given in class. Absences will not be granted a special exemption, but your grade will only depend on the best three quizzes. We choose this format to dramatically lower the pressure compared to a major midterm and to encourage students to stay current with the class conceptually throughout the semester.