Whitney AIRequest access

Journal

Research and field notes on evaluations, post-training, and better model behavior.

  • A pixel-art office where glowing data cubes flow through the workspace and across a glass conference room.

    Research15 min read

    Searching Through a Virtual World

    By Nick Mecklenburg

    We trained a 4B model to search a synthetic corporate tenant with 91.1% of frontier performance and greater reliability than its 27B teacher.

  • A pixel-art rocket launching through a dark, star-filled sky.

    Research12 min read

    The Art of Evals

    By Nick Mecklenburg

    No public benchmark for medical billing errors existed, so we built one — synthetic data, start to finish.