Banning Chinese models will be the same self own as banning Chinese EVs.
禁用 Chinese models，和禁用 Chinese EVs 一样，都会是一次自我伤害式的昏招。
Use one agent to do the work and another to review it against a rubric. @trq212 explains how this works for video shorts: “For something like, ‘Is this a good video short or not?’ you don’t have a deterministic answer. You should have a separate verification agent read a rubric, review the short, and give feedback. We call it self-preferential bias. When a model prefers its own output, it’s going to be more lenient at verifying it.” 📌 Watch the full episode here:
用一个 agent（智能体）来完成工作，再用另一个 agent 按照 rubric（评分标准）去审查它。@trq212 解释了这在 video shorts（短视频）场景中是如何运作的：“对于像‘这是不是一个好的短视频？’这样的问题，你并没有一个 deterministic（确定性的）答案。你应该让一个单独的 verification agent（验证智能体）去阅读 rubric，审查这个短片，并给出反馈。我们称之为 self-preferential bias（自我偏好偏差）。当一个 model（模型）更偏好自己的输出时，它在验证时就会更宽松。” 📌 完整节目请看这里：