Tavus 预览 Griffin 实时视频交互模型
AI 初创公司 Tavus 预览了 Griffin,一个可在实时视频中观看、聆听、说话并作出反应的 Human Interaction Model。Tavus 称在面对面测试中,48% 的参与者认为对话对象是真人,此前模型这一比例仅为 2.4%;该模型在 NVIDIA 的 VideoFDB 视频聊天测试中与真人相差 0.09 分,并领先次优 AI 模型超过 1 分。目前仅 Griffin-Lite 向受信任测试者开放,用于继续完善安全与披露功能,后续再公开推出。
3 Image - Black Forest Labs' image model with box-by-box layout control; 📣 Runway Ads - Runway's AI system that makes, posts, and retunes paid ads; 🗣️ MAI-Transcribe-2-Streaming - Microsoft's top-ranked live speech-to-text AI; 🧑💻 Canvas - Shopify’s AI workspace for designing every page of a store 📰 Everything else in AI today Three OpenAI researchers were reportedly let go for allegedly passing internal info to an AI-safety group amid investigations into the company over rogue agent activity. A
匹配字段正文
