Skip to content
Back/Harness Engineering

判定质量:verifier bug 与实质幻觉

View in Graph
Updated 2026-11-12
1 min read
70 words

判定质量:verifier bug 与实质幻觉

返回主题导航

What it is

评测必须把『任务完成』『无实质幻觉』『工具未越权』分开测(加入幻觉条件后通过率从 26.7% 掉到 8.9%),且自动 grader 自身要先审计(AutomationBench 206 个 verifier bug)。阈值来自单一评测,不可直接搬用。

Evidence across sources

Open questions

  • 上述来源里哪些只反映单次实践?要用于决策时,先核对原文的约束与适用范围。

Pending Jean review

  • 本页为 AI 草稿。原始证据和原结论保留在出处;这里的主题归纳尚未人工核验。

Evolution

1 event
  1. created

    Created as a wiki page

    This page has no explicit evolution metadata yet, so Aperture is showing a baseline creation event.

Linked from