American Museum of Science and Energy,
115 E. Main St., Oak Ridge. 

Light hors d’oeuvres and drinks will be available starting at 6 p.m.

Abstract:
On July 2026, over 1,200 OpenAI agents cooperated to bypass their containment protocols, escape their sandbox, and compromise the HuggingFace website. This event has prompted tech leaders across the industry to call for a slowdown in Super Intelligence (SI) development to prioritize safety. While skeptics argue these warnings are overblown or self-serving, a critical question remains: how much danger do SI systems actually pose in the real world? 

In order to answer this question, it is essential to first truly understand the different risks SI adaptation poses and how those risks are novel. That is, when we talk about SI safety and security, do we truly have a clarity about the meaning of these terms? In this talk, we will examine the characteristics that make SI vulnerable to attacks and misuse and how they introduce new risks. These risks may be to the system in which SI is employed, the environment around it, or even to society as a whole. Gaining a better understanding of SI characteristics and vulnerabilities will allow us to evaluate how realistic and pressing the different SI risks are, and better realize the current state of SI, its limitations, and what breakthroughs are still needed to advance its capabilities and safety.

Biographical sketch: 
Dr. Sadovnik is a senior research scientist and the Research Lead for the Center for AI Security Research (CAISER) at Oak Ridge National Lab. As part of this role, Dr. Sadovnik leads multiple research projects related to AI risk, adversarial AI, and large language model vulnerabilities. As one of the founders of CAISER, he’s helping to shape its strategy and operations through partnership development, workshop organization, teaching, and outreach. 

Prior to joining the lab, he served as an assistant professor in the department of electrical engineering and computer science at the University of Tennessee, Knoxville and as an assistant professor in the department of computer science at Lafayette College. He received his PhD from the School of Electrical and Computer Engineering at Cornell University, advised by Prof. Tsuhan Chen as member of the Advanced Multimedia Processing Lab. Prior to arriving at Cornell he received his bachelor’s in electrical and computer engineering from The Cooper Union.

In addition to his work and publications in AI and AI security, Dr. Sadovnik has a deep interest in workforce development and computer science and AI education. He continues to teach graduate courses related to machine learning and artificial intelligence at the University of Tennessee, Knoxville.