Skip to main content

Tagged Ground Truth

We Labeled Six Repos with a Thousand Sub-Agents

You cannot improve a scanner you cannot score, and nobody had labeled where the personal data lives in a real codebase. So we had three sizes of model label it, argue about it, and let the biggest one arbitrate. The labels are not perfect. They are a compass needle, and the first thing they found w…

  • Evaluation
  • Sub-Agents
  • Ground Truth
  • LLM Evals