Tavus推出人类交互模型Griffin，近半数测试者误认其为真人
原标题：Nearly half of test subjects mistook Tavus' AI video avatar for a real person on a one-minute call
AI 摘要
旧金山AI初创公司Tavus推出名为Griffin的"人类交互模型"（HIM），可实时处理语音、面部表情、语调、手势和停顿，并同时接收与生成视频。在一项研究中，48%的参与者在进行一分钟视频通话后认为Griffin是真人，而此前系统最高仅为2%；在Nvidia的独立测试中Griffin得分3.83，接近真人的3.92。目前Griffin-Lite以研究预览形式向部分测试者开放，功能更强的版本将在"安全问题解决后"推出，潜在用例包括辅导、练习困难对话和基于摄像头的技术支持。
正文节选
Nearly half of test subjects mistook Tavus' AI video avatar for a real person on a one-minute call Tavus has introduced Griffin, what the company calls the first "Human Interaction Model" (HIM), a class of model designed to understand and carry on face-to-face conversations in real time. Griffin processes speech, facial expressions, tone of voice, gestures, and pauses while both receiving and generating video. In a Tavus study, 48 percent of participants believed Griffin was a real person after