Presenting: AI Unraveled — The Future of AI Safety Testing

We’re bringing you a recent release of AI Unraveled, a podcast exploring groundbreaking research, innovative applications and emerging technologies that are pushing the boundaries of AI.

On the episode, “The Future of AI Safety Testing,” Bret Kinsella, GM of Fuel iX™ at TELUS Digital, shared his expertise on game-changing approaches to AI safety testing and the critical importance of proactive security measures in enterprise AI deployment.

In conversation with host Etienne Noumen, Bret discusses the limitations of traditional red teaming methods for large language models, introduces the breakthrough technique that enables AI systems to test themselves and explores how enterprises in regulated industries can balance innovation with responsible AI governance.