返回探索

用 Jev 构建 hall monitor 并测试评分器

作者用 Jev 构建了一个 hall monitor,并对其评分器进行测试。首次得分 28%,但修正后,它在可信与垃圾问题上的识别率达到 24/25,整个测试成本约百分之一美分。

I built a hall monitor with #Jev. Then I quizzed the grader itself. First score: 28%. But that was my mistake. Real results: it caught the trustworthy-vs-junk question 24 out of 25 times The whole quiz cost about a hundredth of a penny.

用 Jev 构建 hall monitor 并测试评分器 1
· 5 次赞在 X 打开