elvis· @omarsar0 · X·· 2 小时前AI 评分56
AI 导读
Tavus 发布 Griffin，称其为首个通过视频图灵测试的 Human Interaction Model，48% 与其实时对话的人以为对方是真人，此前系统通过率低于 3%。作者获早期访问体验，称该视频到视频模型可边看边听、打断和被打断并反应房间内发生的事；在 NVIDIA Video Full-Duplex Benchmark 上生成得分 3.83/5，真人为 3.92。
正文
This is impressive! Face-to-face conversation is where AI interfaces are heading.
@tavus gave me early access to Griffin, a video-to-video model that watches and listens as you talk.
It can interrupt you, take an interruption, and react to what is happening in your room.
On NVIDIA's Video Full-Duplex Benchmark, it scored 3.83 out of 5 on generation, against 3.92 for a real human.
Worth checking out all the details below.
Introducing Griffin, the first model to pass the video Turing test. 48% of people who talked to it live thought it was a real human. Previous systems have had a pass rate <3%. It is #1 on NVIDIA's benchmark for full-duplex AI video. It’s the first Human Interaction Model (HIM).在 X 查看被引用的帖子
来源：elvis · x.com