Navigating AI Risks and Safety Testing

Hello AI Unraveled Listeners,

In today's AI Special Edition,

• Bret Kinsella’s Journey: From Voicebot.ai to Fuel iX™
• The AI Safety Testing Research: A New Method for Red Teaming LLMs
• The Impact: What This Means for Enterprise & Industry
• The Future: AI Safety, Accountability & What's Next

This episode explores the evolution of AI safety testing, particularly concerning large language models (LLMs). It highlights the limitations of traditional "pass/fail" red teaming and introduces a novel approach called Optimization by PROmpting (OPRO), which enables an LLM to effectively "red team itself." This new methodology focuses on evaluating the Attack Success Rate (ASR) as a distribution, offering more nuanced insights into an AI model's security. The discussion also touches upon the real-world implications for enterprises, especially in regulated industries like finance, energy and healthcare, and how OPRO can aid in demonstrating regulatory compliance and fostering accountability. Ultimately, the guest looks towards the future of AI safety, identifying upcoming challenges and areas for focused research and development.

Listen at https://podcasts.apple.com/us/podcast/the-future-of-ai-safety-testing-with-bret-kinsella-gm/id1684415169?i=1000723468669

Learn More:

• Research Paper OPPro (https://arxiv.org/pdf/2507.22133)
• TELUS Digital: https://www.telusdigital.com/
• Fuel iX™ is TELUS Digital’s proprietary platform: https://www.fuelix.ai/
• Fuel iX Fortify - AI vulnerability detection: https://www.fuelix.ai/products/fuel-fortify
• Bret Kinsella on Linkedin: https://www.linkedin.com/in/bretkinsella/