2 Matching Annotations
  1. Last 7 days
    1. Cursor counted the entire file as AI, even though we can see from the diff that it left plenty of the lines unchanged.

      大多数人认为AI代码指标应该精确追踪实际修改的代码行,但作者发现Cursor会将整个文件标记为AI生成,即使只修改了其中部分行,这表明AI工具的追踪系统存在严重缺陷,可能导致完全错误的贡献报告。

  2. Apr 2026
    1. Tracks the evolution of LLM security capabilities across benchmarks (CyberGym, Cybench, etc.), calculates capability doubling times, detects emergence patterns, and monitors cost-efficiency trends.

      这个功能模块代表了AI安全研究的前沿方向,不仅关注当前能力,还追踪能力演化和效率变化。计算'能力倍增时间'特别值得关注,这可能揭示AI安全能力发展的加速趋势,对预测未来安全挑战具有重要意义。