
Guest Introduction and Background

Why securing AI is harder than anyone expected and the coming security crisis | Sander Schulhoff
Topic 2 of 14
Published Dec 21, 2025 · Clip 5:18–7:32 (2:14)
Sander introduces the topics of AI security, including prompt injection, jailbreaking, and red teaming. He shares his background as an AI researcher focused on prompt engineering and red teaming, noting he created the first guide on learn prompting and ran the inaugural generative AI red teaming competition, which open-sourced a major dataset used by labs and companies.