What do LLMs Really Learn About Model Weights? A Stratification Approach to Examine Weight Space Programming
TLDR I attempted to replicate “Sparks of Weight-Space Programming” by Takehi et al (2026) with stratification on two reasoning models, GPT 6 Astra and Deepseek-V4.1-Flash. The task for the LLMs is to identify the game a ML model is trained for giving the weight of the model (using exact same...
Nov 82