Jev 与文本生成模型的取舍
Jev 不生成自由文本。Diogo 用一段对比视频说明并行决策模型与逐字生成模型在任务形态上的差别。

帖子指出过去三年让文本生成器做分类、路由、升级等决策,再解析 token 为结构化输出;TypeSafe 的 Jev 则反转这一模式,由用户定义决策逻辑。
We've spent three years asking text generators to make decisions. Classify this. Route that. Escalate or not. Continue or stop. We parse the tokens back into a decision our software can actually use - and call that structured output. TypeSafe's Jev inverts it. You define the