Nice tool.
53% catch rate on bugs that already cleared human review, with the main bottleneck being false positives... Sounds about right for where LLMs are useful: they don't get tired on patch 47 of a series
Finally, a machine learning model to confirm I lack self-control
Nice tool.
53% catch rate on bugs that already cleared human review, with the main bottleneck being false positives... Sounds about right for where LLMs are useful: they don't get tired on patch 47 of a series
Finally, a machine learning model to confirm I lack self-control