Jev 正式发布:面向决策的 System One 模型
TypeSafe 创始人 Diogo Almeida 介绍 Jev、RLCD 训练方法,以及面向软件决策场景的模型定位。原帖附有 2 分 56 秒发布视频。

TypeSafe AI 的 Jev 模型现在可处理图片,支持是/否、标签或评分等判断,并强调响应速度快、成本低。
claude took 2.3 seconds to read this receipt. jev took half a second. @typesafeai's decision model can see images now. yes/no, labels, or scores on any photo, for a fraction of a cent. what would you point it at first?