Walter Goodwin believes that running multi-trillion-parameter models at many thousands of tokens per second could radically speed up long-running AI agents and substantially increase AI capability.

“The place where the ability to take a multi-trillion parameter model and run it comfortably at many thousands of tokens per second.”

“Second,”

“in our view,”

“is a kind of fundamental elevator on capability for AI is in taking these kind of very long running agents and making them radically faster.”