返回探索

Jev 的决策式智能体与评估挑战

该帖指出 Jev 不生成文本而是做决策,如调用工具、重试、路由或升级,并认为自主决策的可靠性评估是新的难题。

@typesafeai Jev makes decisions instead of generating text: which tool to call, whether to retry, route or escalate Interesting direction for agents. Because once software makes millions of these decisions autonomously, “valid output” ≠ reliable decision. That’s an eval problem!

Jev 的决策式智能体与评估挑战 1
· 1 次赞在 X 打开