ProxyML: Challenger Models Catch Mismatched Data
New in ProxyML challenger models: mismatched data gets caught locally, before it's ever uploaded. Every local challenger run stamps a target_fingerprint — a SHA-256 hash of the labels it was…
New in ProxyML challenger models: mismatched data gets caught locally, before it's ever uploaded. Every local challenger run stamps a target_fingerprint — a SHA-256 hash of the labels it was…
The first release of the ProxyML MCP Server package is now available! Be sure to check out the README, where you'll find example workflows such as drift detection, model validation,…
PyPI Downloads of proxyml, April 13 - May 6 2026 Coming up on 1 month since the initial release of the ProxyML SDK and we've just crossed 1,000 downloads on PyPI!…
(Hopefully.) I haven't made any widespread announcements but if you're here and you're reading this there's a non-zero chance you might be interested in ProxyML, so you may also be…
ProxyML counterfactual: "bad" credit risk for a new car, but a "good" risk for a used car I'm testing ProxyML with an example notebook and found this great example of…
The first version of an in-browser schema generator for ProxyML is now available! The page is live, but you can also just download the HTML and run it directly yourself…
I've been working on an eXplainable AI (XAI) project and today I've published the very first version of the SDK that will eventually call the service. It's also the first…
A couple of years ago I released a POC demo of using an LLM for Search Engine Optimization (SEO). This week Claude and I started working on a more fleshed…
A Python code snippet showing how to use the local Retrieval Augmented Generation (RAG) gist Picking up a few certs at work recently, I had to complete a lab on…
If we could automatically pull any information from the document or even just know what type of document we’re looking at ahead of time, we could make our document processing…