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.

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