LessWrong7 min read
What do LLMs Really Learn About Model Weights? A Stratification Approach to Examine Weight Space Programming
TLDRI 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.
By CCaptainXLessWrong

Read the full story
Originally published by LessWrong on Nov 8, 2026.
Comments
Sign in to join the discussion.