AI model "Griffin" appears, which 48% of participants in video calls misidentified as human, reproducing face and body movements in video from a single image
AI company Tavus announced the AI model "Griffin," which interacts with humans using real-time video and audio. In an experiment using the research preview version "Griffin-Lite," out of 54 people who participated in a 1-minute live video call, 26 people, approximately 48%, judged the conversation partner AI to be a real human.
AI company Tavus announced the AI model "Griffin," which interacts with humans using real-time video and audio. The model reproduces face and body movements in video from a single image.
In an experiment using the research preview version "Griffin-Lite," 54 people participated in a 1-minute live video call. Out of these participants, 26 people, approximately 48%, judged the AI conversation partner to be a real human.
This item is a summary. The full, checkable version is at the original source:
Read the original at Gigazine ↗