Episode · Jun 9, 2026
Is RAG Dead? Lessons from Building AI for Tax Law with Alex Bowcut
The TWIML AI Podcast · 52 min
We use cookies for analytics.
Podcast, The TWIML AI Podcast
Hosted by Sam Charrington
Sebastian Gehrmann explains why retrieval augmentation can introduce or worsen safety problems in language-model systems. The discussion covers unsafe-output examples, evaluation approaches and possible mechanisms, then considers domain-specific risks in financial services, governance, prompt design and layered mitigation strategies.