Engineering insights, product updates, and technical deep dives into local TabICLv2 inference and Google Sheets ML.
Use Jev and System One models to turn free-form text into probabilistic semantic features for TabPFN, TabICL and other tabular foundation models.
Read article →Evaluating TabICLv2, TabPFN-3, TabFM, and EXAONE-Tabular on model weight size, latency, licensing, and WebGPU browser execution compatibility.
Read article →What explainable AI is, how Shapley Additive exPlanations work from first principles, and how to read SHAP waterfall and directional beeswarm plots.
Read article →How Carla uses Langevin diffusion and differential privacy to generate privacy-preserving synthetic data directly inside your spreadsheets.
Read article →How we navigated Google Cloud Trust & Safety OAuth verification for Carla.
Read article →