top | item 42459474

(no title)

vagabund | 1 year ago

My understanding is they built a performant suite of simulation tools from the ground up, and then they expose those tools via API to an "agent" that can compose them to accomplish the user's ask. It's probably less general than the prompt interface implies, but still seems incredibly useful.

discuss

order

bilsbie|1 year ago

Still doesn’t seem possible with current technology? It would have to access those apis while it generates video.