3 comments

  • tancop 9 hours ago
    Looks like you only get a yes/no result and a confidence score for each file. No explanation or function level diagnostics. This is useless.
    • frumiousirc 4 hours ago
      The point is you can quickly get any yes's, and then subject them to more expensive scrutiny.
  • aidiveyt 10 hours ago
    Worth saying how read-only is enforced rather than promised. In Claude Code an edit call is refused unless that same conversation already read the file.
  • RomanKornev 18 hours ago
    This is great!

    We can now replace Kolmogorov complexity-based metrics with pure Jev-slop code quality metrics.