We publish model releases, technical writeups, and results in one place.
We raced our tabular foundation model against our own AutoML agent on four standard datasets — same split, scored the same way. Near-parity on most, orders of magnitude faster, with uncertainty and explanations built in.
#predictlm #benchmark #automl #tabular #modelforge
The hosted PredictLM API is now self-serve — register, get a key in seconds, and call zero-training tabular prediction over HTTPS. Now with calibrated uncertainty, feature attributions, and a plain-language explanation in one call.
#predictlm #api #release #explainability
Where will the ball land? An LLM guesses, the textbook formula ignores air resistance, and PredictLM predicts it from 600 past throws — zero-shot, no equation. The capability your AI agents are missing, in 25 seconds.
#predictlm #demo #agents #mcp
We're opening early access to a hosted PredictLM API — zero-training regression and classification over HTTPS, with calibrated probabilities. Manually onboarded, one conversation at a time.
#predictlm #api #early-access
Two open-weight tabular models (Mini 13M, Base 26M, Apache-2.0) and a test-time training recipe that hits 0.751 classification accuracy on a 25-dataset OpenML benchmark. Plus 11 architecture experiments that didn't move the needle.
#predictlm #release #test-time-training #negative-results
The smallest open-weight tabular foundation model with calibrated uncertainty out of the box. 13M parameters, 54 MB, Apache-2.0. Statistically tied with Base on classification accuracy and within ~4 pp R² on regression.
#predictlm #release #distillation #calibration
Before settling on Mini's architecture, we ran six experiments at the 26–57M parameter scale. Five lost to the smaller model. Here's the full writeup, including the gradient-NaN debugging.
#predictlm #ablation #negative-results
A 1024-bin quantile head is the difference between a guess and a calibrated prediction. We explain how the head works, why softmax-over-bins beats Gaussian heads for in-context regression, and what the distribution unlocks.
#calibration #uncertainty #predictlm
