Kevin Madura
  • Jan 30, 2026

    Auditing a Codebase for 87 cents in 50 lines of code using RLMs

  • Dec 30, 2025

    AI's Hedonic Treadmill vs. Task Horizon Exponentials

  • Dec 13, 2025

    Achieving 20 percentage-point improvement in structured extraction tasks using DSPy and GEPA

  • Aug 2, 2025

    Using DSPy to Detect Document Boundaries

  • Apr 27, 2025

    Acceleration: Notes on 'Measuring AI Ability to Complete Long Tasks'

  • Jan 7, 2025

    Summarizing video transcripts with an LLM

  • Dec 16, 2024

    Measuring LLM Confidence

@kmad