Skip to content
Latent Space

Why Video Agent Models Are Next — Ethan He on xAI Grok Imagine

Why Video Agent models are next — Ethan He, xAI Grok Imagine

Ethan He says a small xAI team built Grok Imagine from zero to one in 3 months, and the episode discusses video agents, audio-video alignment, inference speedups, and the storage, egress, and GPU-hour costs behind large video datasets.

Why it matters: xAI's Ethan He built Grok Imagine with a small team in three months and argues video-model intelligence comes mostly from language models.

Read the original ↗Export Markdown