
RAG Risks: Why Retrieval-Augmented LLMs are Not Safer with Sebastian Gehrmann - #732
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
00:00
Navigating AI Safety Challenges
This chapter explores the complexities of implementing AI mitigation strategies in high-stakes industries, emphasizing the need for tailored approaches and multilingual safety research. It also calls for greater collaboration between academia and industry to address vulnerabilities in AI systems, particularly in areas like prompt injection and domain-specific applications.
Transcript
Play full episode