Sebastian Gehrmann
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
RAG Risks: Why Retrieval-Augmented LLMs are Not Safer with Sebastian Gehrmann
- Published
- May 21, 2025
- Duration
- 57:09
- Summary source
- description
- Last updated
- Jul 5, 2026
Discusses rag, ai-regulation, generative-ai.
Summary
Today, we're joined by Sebastian Gehrmann, head of responsible AI in the Office of the CTO at Bloomberg, to discuss AI safety in retrieval-augmented generation (RAG) systems and generative AI in high-stakes domains like financial services. We explore how RAG, contrary to some expectations, can inadvertently degrade model safety. We cover examples of unsaf…
Intelligent Report
Sign in to read teasers, or upgrade to Research Pro to commission intelligent report for this episode. Learn more →
Show notes
Today, we're joined by Sebastian Gehrmann, head of responsible AI in the Office of the CTO at Bloomberg, to discuss AI safety in retrieval-augmented generation (RAG) systems and generative AI in high-stakes domains like financial services. We explore how RAG, contrary to some expectations, can inadvertently degrade model safety. We cover examples of unsafe outputs that can emerge from these systems, different approaches to evaluating these safety risks, and the potential reasons behind this coun
Themes
- rag
- ai-regulation
- generative-ai