The Future of Multimodal AI
Shane Legg discusses the potential of multimodal AI, highlighting its ability to understand images and video, and how it will open up new applications beyond text-based models. The transition to multimodality is still in its early stages, but once systems can digest various modalities, they will have a more grounded understanding of the world, leading to countless possibilities that we can't even imagine yet.In this clip
From this podcast
Dwarkesh Podcast
Shane Legg (DeepMind Founder) - 2028 AGI, New Architectures, Aligning Superhuman Models
Related Questions