Founded & Funded RAG Inventor Talks Agents, Grounded AI, and Enterprise Impact
34 snips
Mar 27, 2025 
Douwe Kiela, co-founder and CEO of Contextual AI and co-inventor of Retrieval-Augmented Generation (RAG), shares insights on revolutionizing AI systems for enterprises. He dives into the origins of RAG, its often-misunderstood role, and the critical innovations at Contextual AI. Douwe discusses the importance of addressing hallucinations in AI, how to align AI with business value, and offers advice for founding AI companies. He emphasizes the need for adaptability in entrepreneurship and outlines the challenges of successfully deploying AI technologies.
AI Snips
Chapters
Transcript
Episode notes
Origins of RAG
- RAG was born from grounding language in external text like Wikipedia to improve understanding and make generative models factual.
- This was a collaborative effort at Facebook AI Research building on concurrent open domain QA work.
RAG Fits Into AI Ecosystem
- RAG complements rather than competes with fine-tuning and long context techniques.
- Combining RAG with fine-tuning and maximizing context window yields the best performance.
Why RAG Is Seductive
- RAG is popular because it is easy to integrate and enables language models to work on specific data despite black-box APIs.
- Long-context models are tempting but costly and inefficient due to reprocessing all data on every query.