Same Model, Different Wrapper: A Preregistered Demonstration That Self-Reports of Consciousness in Two Open-Weights Language Models Follow Their Builders' Choices
PhilPapers (PhilPapers Foundation) October 11, 2026 Erez Batat preprint
Abstract: Self-report is the evidence most often offered for or against consciousness in large language models. I argue that it cannot serve that role, because the report is screened off by the choices of whoever controls two layers: alignment training inside the weights, and the runtime text around them, including text that the maker's chat template inserts by default. The argument's empirical...