People talk, listen, watch, think, and collaborate at the same time, in real time. We've designed an AI that works with people the same way.
We share our approach, early results, and a quick look at our model in action.
https://t.co/AFJZ5kH7Ku
While Lilian is telling a story, the interaction model can track when she is thinking, yielding, self-correcting, or inviting a response; there is no specific built dialogue management system.
eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.
Why it matters
Turn-taking, interruption, and simultaneous speech are handled inside the model rather than by a bolted-on dialogue manager, with early evalA repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.Full definition → results published in the technical report.
