In this webinar, we will explore the key concepts of AI Safety through an overview that spans from the internal architecture of models to concrete countermeasures: where vulnerabilities arise, how they can be uncovered through red teaming, and which defenses — from guardrails to alignment — can be implemented today.
- Understand where and why AI models fail, starting from their architecture.
Register for the webinar to:
- Discover how red teaming is conducted on LLMs and which vulnerabilities it brings to light
- Take home a practical framework for integrating safety into the lifecycle of your AI systems
Instructors
Gaia Gambarelli, AI Education Expert & Instructional Designer
Ivan Gentile, Senior Data Scientist