The Problem with Jev: Can You Trust AI Decisions?

Why watch

Jeff Crume from IBM examines AI decision-making through a cybersecurity lens, focusing on the Jev system. The video explores how confident AI outputs aren't necessarily trustworthy, covering attack surfaces, poisoned inputs, observability requirements, and verification strategies. It's designed for IT professionals and security engineers wanting to understand AI trust, security, and the need for evidence-based AI decision making.