New research led by @PeterNutter1 @DJROYTBURG via @MATSprogram: a better way to update model beliefs that we call grafting. Fine-tune the base model with next-token prediction on synthetic documents (SDF), and simply apply the weight update onto the post-trained model. This works! 1/7

Excited that our ICML position paper has been accepted as an Oral 🎉! When a model looks like it "deceives" or "resists shutdown," how do we know it isn't role-play, instruction-following, or just task-completion pressure? Often the current evidence can't yet tell them apart, and those claims are starting to inform deployment and regulation. We map where the evidence gets thin across four stages and propose a shared standard to strengthen it. Here's the map. 🧵 arxiv.org/abs/2606.07612