I tried "weight-space programming" on 6 kinds of models. Here's where it works and where it breaks.

Automated excerpt

The result that surprised me: a model written with zero labels The usual way to get a model: collect labelled data, train. A small compiler turns this program into a standard XGBoost model file, which loads in stock XGBoost like any trained model. Reading a model works on every model I tried, including the LLM.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.