English-language podcasts

Podcasts

NVIDIA AI Podcast

An episode can be the start of a conversation. Explore recent releases, share your thoughts, and meet through a ThinkMatch Roundtable.

Ask friends about this

Episodes to discuss

NVIDIA AI Podcast

Can Open Source Make AI Agents Safer?

30 min

Hugging Face co-founder Thomas Wolf and ServiceNow’s Amanda Grady, SVP of AI Platform Security, join the NVIDIA AI Podcast to explain how to keep AI agents safe when telling a model “please don’t” is no longer enough. They cover why firm boundaries beat persuadable models, what happened when Hugging Face was attacked by a swarm of AI agents, and why security is what lets companies put agents to real work. This is the 15-minute best-moments edit. The full-length episode is on your favorite podcast platform! In this episode: 0:16 (https://www.youtube.com/watch?pp=0gcJCWMAwfN6Pr3D&t=16s&v=y9AALMeAeGI) Why guardrails inside the model aren’t enough 2:00 (https://www.youtube.com/watch?t=120s&v=y9AALMeAeGI) The attack on Hugging Face, and why open models mattered 3:28 (https://www.youtube.com/watch?t=208s&v=y9AALMeAeGI) Agent identity and the AI Passport 6:03 (https://www.youtube.com/watch?t=363s&v=y9AALMeAeGI) Security as an unlocker for AI 8:33 (https://www.youtube.com/watch?t=513s&v=y9AALM

Discuss this episode