Ask HN: 你如何判断对你的 AI 技能的调整是否使其更好了?
1 分•作者: yo103jg•4 个月前
好奇这里的人在调整 AI 技能、提示词或工作流程时,是如何评估改动的。
很多时候,一项调整可能在一两个案例中感觉更好,但很难判断它是否真的整体上改进了技能,或者只是改变了它的行为,使其在一段时间内看起来更好。
你们主要靠直觉,还是有一些轻量级的方法来检查调整是否真的有帮助?
查看原文
Curious how people here evaluate changes when they tweak an AI skill / prompt / workflow.<p>A lot of the time, a tweak might feel better in one or two cases, but it’s hard to tell if it actually improved the skill overall or just changed its behavior in a way that looks better for a bit.<p>Do you mostly go by intuition, or do you have some lightweight way to check if a tweak really helped?