Large multimodal models can treat different modalities as tokens (words, pixels, actions, etc.), enabling transfer across domains; training such systems is harder than pure language models, but the resulting multimodality produces better performance across all modalities as they learn from each other's structure.
factualpending
Speaker
Demis HassabisEvidence Quote
“treat tokens like Gato as any type of token...The token could be an action, it could be a word...harder to train...more general, more capable system [49:45]”
Created: 8/11/2026, 1:25:34 AM
Your notes
Loading notes...