Edison Public Library
Introduction to AI Evaluations
No technical background needed
Saturday, October 17
11:00am - 1:00pm
North Edison Branch
Meeting Room 1
This workshop pulls back the curtain on modern AI systems and explores the emerging field of AI evaluations (“evals”): the methods researchers use to measure what these models are capable of, where they fail, and how they might become dangerous.
Together, we’ll tackle questions like:
How are large language models actually created, and what distinguishes them from traditional software?
Reasoning What is “chain-of-thought” reasoning, and why are today’s models starting to behave in surprising ways?
Evals What does safety testing for AI models actually look like?
Capabilities How do researchers test for deception, manipulation, persuasion, and autonomous behavior?
What you’ll get:
- A beginner-friendly explanation of how modern AI systems function under the hood
- Hands-on demos where we simulate jailbreaks of different AI models live and compare how they respond to attacks
- A walkthrough of real AI safety evaluations used by frontier labs
Please note this is a hybrid event. Attendees are welcome to attend in person in Meeting Room #1 at the North Edison Branch or to join remotely via Zoom.
Open to adults. Registration is suggested but not required and begins October 5.
About our partner
The AI Safety Awareness Project is a 501(c)(3) nonprofit founded on the belief that a safe AI future is one where the traditional pillars of U.S. society have a seat at the table in deciding the direction of AI. The AI Safety Awareness Project (AISAP) want to be there for the first step: education and skills-building, so that Americans have the necessary expertise and awareness to direct our AI future. They run workshops and education programs for a variety of community groups and public institutions including law enforcement agencies, libraries, churches, universities, as well as the general public. AISAP partners with industry experts to inform organizations about frontier AI research and developments, including topics as diverse as workforce augmentation and displacement, AI agents and companions, cybercrime, AGI (Artificial General Intelligence), and loss of control risk.
For more information about AISAP, please visit https://aisafetyawarenessproject.org/