The Public Discourse Sandbox (PDS)

The Challenge: When AI Becomes Indistinguishable from Human

The line between human and AI in online discourse is blurring faster than we realize. Research conducted by CRC collaborators—including doctoral student Kristina Radivojevic and CRC Senior Associate Director Paul Brenner—reveals a striking reality: during experimentation, participants correctly identified AI bots only 42% of the time. This finding carries significant implications for understanding how deception spread through online communities.

An ND Contribution Toward Solutions: An Ethical Place for Critical Research

To address this challenge in a controlled, ethical environment, Radivojevic developed the Public Discourse Sandbox (PDS) as an open resource. This platform provides a social media test environment, enabling researchers and instructors to conduct controlled experiments examining how humans interact with Large Language Model (LLM) bots. CRC Research Software Engineers took the platform to the next level, building out a more sophisticated, scalable architecture and enhancing the codebase to comply with industry software standards.

Opportunities for Research and Teaching

The PDS serves as both a research platform and an experiential learning tool. An open-source version is available on GitHub, offering additional customization options for diverse research needs. Researchers can deploy custom bots to investigate AI behavior in public discourse settings. In the classroom, this allows students to gain hands-on experience with prompt engineering and developing a practical understanding of how AI agents operate in online spaces.

Looking Ahead

The CRC is seeking additional collaborators to expand this work and to bring PDS to more classrooms and research projects. This platform offers opportunities to address pressing questions about AI's impact on mental health, digital equity, and online communication safety.  To learn more about incorporating the Public Discourse Sandbox into your research or teaching, please contact Kristina Radivojevic at kradivo2@nd.edu.

MATLAB is a commercial software developed by MathWorks. MATLAB is widely used in different fields, e.g., mathematics, physics, engineering, and economics. 

MathWorks provides online, self-paced training to users. University of Notre Dame has an academic license for MATLAB, and users from our university have subscriptions to the Online Training Suite. To get access to these trainings, users need to create a Mathworks account using their Notre Dame email.

There are three different types of training on the Online Training Suite. There are onramp, course and learning path training available. 

The onramp training are short introductory courses, e.g., MATLAB Onramp, Simulink Onramp. These training sessions can be completed within a few hours. 

The course type training usually covers a topic, and requires more effort. For example, the Image Processing with MATLAB training takes about 10.5 hours to complete. 

The learning path trainings are selections of courses that cover a larger topic, e.g. Machine Learning Techniques in MATLAB.

These training sessions usually use videos and slides to explain concepts, and also contain hands-on tasks for each section. The courses use the online version of MATLAB, and the tasks are usually implemented in Live Editors. After completing any of these training sessions a digital certificate can be downloaded.

If you have just started using MATLAB, or if you have been using MATLAB for years and are willing to learn more about it, you can find the available courses here.

To further expand our reach, we’re launching a dedicated Google Group (rse_ai_asst_cop-list@nd.edu) to facilitate ongoing discussion, resource sharing, and knowledge exchange among participants. Whether you're a seasoned developer curious about AI assistance or a student just beginning to explore these tools, this community will provide a supportive environment to navigate the evolving intersection of artificial intelligence and research software engineering. Stay tuned for our first session announcement, and consider joining our mailing list to connect with fellow researchers who are shaping the future of computational research.

Every Wednesday and Thursday
2:00 – 3:00 p.m.
812 Flanner Hall (map)

The CRC offers multiple training opportunities for both new and existing users. We periodically provide short courses and other learning opportunities, which are advertised on our website and through email lists. In-person office hours are held every Wednesday and Thursday from 2:00-3:30 p.m. in Flanner Hall, room 812, on a first-come, first-served basis. You can also arrange a Zoom meeting at your convenience by emailing CRCsupport@nd.edu with your availability. We recommend bringing a laptop to in-person sessions.

For more information, please contact CRCsupport@nd.edu.