forecast
Next-generation models may surprise under inference scaling
Video and audio data remain far from exhausted, so new modalities could produce capability leaps in human interaction that are as disorienting as image and video generation advances have been.
forecastpending
Speaker
ChetanEvidence Quote
“while we've exhausted data on text, we are not close to exhausting data on video and audio.”
Created: 11/18/2026, 6:42:24 AM
Your notes
Loading notes...