Author name: Arjun Khandelwal

Previously, we proposed spillway motivations as a way to mitigate misalignment induced via training a model using flawed reward signals. In this post, we present some early-stage empirical results showing how spillway motivations can be used to mitigat…

TL;DRWe test to what extent Qwen3-32B behaves as though it is trying to predict what “Qwen3” would do. We do this by using Synthetic Document Finetuning (SDF) to instill meta-beliefs of the form “Qwen3 believes X, even though X is false”, then check w…