Media

Talks:

Unlocking the Enigma of Artificial Intelligence: Insights from Dr. Roman V. Yampolskiy, Esteemed Professor of Computer Science at the University of Louisville


"Critically Acclaimed Expert Delves into the Frontier of AI Governance" - Testifies Before State Legislative Committee

Smart machines are no longer just science fiction. AI expert Roman Yampolskiy delves into their emergence and impact, joined by Scott Kimel and Jenny Wu for a broader discussion on the effects of this new era.

AI Safety: The speaker explores challenges in creating safe AI and AI superintelligence, emphasizing the need for explainability. They suggest sharing the model or simplified explanations for safety assurance, highlighting limitations in human comprehension. Full understanding of AI models is deemed crucial for safety, with modular decomposition possibly insufficient. The speaker invites discussion on AI safety perspectives.

Popular Articles:

Why Uncontrollable AI Looks More Likely Than Ever
AI Is the Future of Cybersecurity
Your Company’s Algorithms Go Wrong?
I’m an AI expert: Here’s my worst-case scenario

Research Papers:

AI Safety instead of Behavioral biometrics
Computer Science and Engineering,

podcast:

For Humanity: An AI Safety Podcast, is the accessible AI Safety Podcast for all humans, no tech background required. Our show focuses solely on the threat of human extinction from AI

Dr. Roman V. Yampolskiy is a Tenured Associate Professor in the Department of Computer Engineering and Computer Science at the Speed School of Engineering, University of Louisville. He is the founding and current director of the Cyber Security Lab and an author of many books including Artificial Superintelligence: a Futuristic Approach.

In this episode, we talk about artificial intelligence. We start by discussing what AI is, and how it compares to natural intelligence. We then go into some of the issues we have to worry about, like the ones related to security, controllability, and unexplainability of AI. We talk about the Singularity, the concept, and what it could be like.

Join us for a live stream with Roman V. Yampolskiy as we discuss AGI safety and security. We'll cover his research on the unexplainability and incomprehensibility of advanced AI, including important requirements for intelligent systems deployed in real-world domains. Don't miss this opportunity to learn more about this fascinating topic!