The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Scaling Multi-Modal Generative AI with Luke Zettlemoyer - #650
Oct 9, 2023
In this discussion, Luke Zettlemoyer, a University of Washington professor and Meta research manager, dives into the fascinating realm of multimodal generative AI. He highlights the transformative impact of integrating text and images, illustrating advancements like DALL-E 3. Zettlemoyer explains the significance of open science for AI development and the complexities of data in enhancing model performance. Topics also include the role of self-alignment in training and the future of multimodal AI amidst rising technology costs and the need for better assessment methods.
38:44
Episode guests
AI Summary
Highlights
AI Chapters
Episode notes
Podcast summary created with Snipd AI
Quick takeaways
- Multimodal generative AI allows models to process multiple modalities and studying their behavior is crucial for understanding their capabilities.
- The shift to large language models requires substantial resources and the field has become more like complex system science, with the emergent behavior of models still not fully understood.
Deep dives
Luke's background and interest in models
Luke Zetelmoyer is a professor at the University of Washington and a research manager at META. He has been fascinated by the limit of what models can do and is interested in studying their behavior and making them more usable.
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
