Comment by dominotw

Isn't ChatGPT benchmaxxing, then ? Responding "hmm…" isn't actually responding and latency should time to first relevant phoneme.

But even then, it's targeting like 300ms not 30ms, right?

its backchanneling frequently makes me laugh to the point of forgetting what i wanted to say. i do like it, it just takes some getting used to, especially since i've been keeping things nice and simple and taking it one step at a time for so long.