No longer feels like talking to an AI: "Dessa" learned through voice alone
Key point
On October 23 (US time), Block announced the full-duplex voice conversation model "Dessa," which learned only from human conversational voice, as a research preview.
On October 23 (US time), Block announced the full-duplex voice conversation model "Dessa" as a research preview. This model learned only from human conversational voice.
"Dessa" can engage in conversation while providing real-time backchanneling like humans do. It is claimed that users may no longer know if their partner is an AI.
This item is a summary. The full, checkable version is at the original source:
Read the original at PC Watch ↗